CN113178258A - Preoperative risk assessment method and system for surgical operation - Google Patents
Preoperative risk assessment method and system for surgical operation Download PDFInfo
- Publication number
- CN113178258A CN113178258A CN202110467774.5A CN202110467774A CN113178258A CN 113178258 A CN113178258 A CN 113178258A CN 202110467774 A CN202110467774 A CN 202110467774A CN 113178258 A CN113178258 A CN 113178258A
- Authority
- CN
- China
- Prior art keywords
- patient
- data set
- information
- historical
- indexes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 87
- 238000012502 risk assessment Methods 0.000 title claims abstract description 71
- 238000013058 risk prediction model Methods 0.000 claims abstract description 75
- 238000007781 pre-processing Methods 0.000 claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 86
- 238000001356 surgical procedure Methods 0.000 claims description 81
- 238000010276 construction Methods 0.000 claims description 32
- 238000003745 diagnosis Methods 0.000 claims description 23
- 238000012216 screening Methods 0.000 claims description 16
- 238000013500 data storage Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 230000010365 information processing Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 3
- 208000015181 infectious disease Diseases 0.000 description 41
- 210000000265 leukocyte Anatomy 0.000 description 18
- 230000002980 postoperative effect Effects 0.000 description 18
- 206010008111 Cerebral haemorrhage Diseases 0.000 description 17
- 230000009885 systemic effect Effects 0.000 description 17
- 206010040047 Sepsis Diseases 0.000 description 16
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 16
- 206010012218 Delirium Diseases 0.000 description 15
- 206010028980 Neoplasm Diseases 0.000 description 15
- 206010035664 Pneumonia Diseases 0.000 description 15
- 208000010378 Pulmonary Embolism Diseases 0.000 description 15
- 208000001647 Renal Insufficiency Diseases 0.000 description 15
- 208000004756 Respiratory Insufficiency Diseases 0.000 description 15
- 201000011510 cancer Diseases 0.000 description 15
- 230000034994 death Effects 0.000 description 15
- 201000006370 kidney failure Diseases 0.000 description 15
- 210000000056 organ Anatomy 0.000 description 15
- 201000004193 respiratory failure Diseases 0.000 description 15
- 206010068797 Anastomotic fistula Diseases 0.000 description 14
- 206010020772 Hypertension Diseases 0.000 description 14
- 230000000399 orthopedic effect Effects 0.000 description 14
- 230000002265 prevention Effects 0.000 description 13
- 230000000391 smoking effect Effects 0.000 description 13
- 210000000115 thoracic cavity Anatomy 0.000 description 13
- 206010008088 Cerebral artery embolism Diseases 0.000 description 12
- 230000005856 abnormality Effects 0.000 description 12
- 238000002682 general surgery Methods 0.000 description 12
- 201000010849 intracranial embolism Diseases 0.000 description 12
- 238000011282 treatment Methods 0.000 description 12
- 208000000059 Dyspnea Diseases 0.000 description 11
- 206010013975 Dyspnoeas Diseases 0.000 description 11
- 208000032843 Hemorrhage Diseases 0.000 description 11
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 11
- 230000002526 effect on cardiovascular system Effects 0.000 description 11
- 239000001301 oxygen Substances 0.000 description 11
- 229910052760 oxygen Inorganic materials 0.000 description 11
- 210000001519 tissue Anatomy 0.000 description 11
- 206010008118 cerebral infarction Diseases 0.000 description 10
- 208000026106 cerebrovascular disease Diseases 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000002485 urinary effect Effects 0.000 description 10
- 206010011985 Decubitus ulcer Diseases 0.000 description 9
- 208000010496 Heart Arrest Diseases 0.000 description 9
- 208000004210 Pressure Ulcer Diseases 0.000 description 9
- 206010047249 Venous thrombosis Diseases 0.000 description 9
- 235000019441 ethanol Nutrition 0.000 description 9
- 210000003141 lower extremity Anatomy 0.000 description 9
- 208000010125 myocardial infarction Diseases 0.000 description 9
- 230000002685 pulmonary effect Effects 0.000 description 9
- 101800000407 Brain natriuretic peptide 32 Proteins 0.000 description 8
- 102400000667 Brain natriuretic peptide 32 Human genes 0.000 description 8
- 101800002247 Brain natriuretic peptide 45 Proteins 0.000 description 8
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 8
- 206010051055 Deep vein thrombosis Diseases 0.000 description 8
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 8
- 102000007330 LDL Lipoproteins Human genes 0.000 description 8
- 108010007622 LDL Lipoproteins Proteins 0.000 description 8
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 8
- 238000013130 cardiovascular surgery Methods 0.000 description 8
- 235000012000 cholesterol Nutrition 0.000 description 8
- 230000023753 dehiscence Effects 0.000 description 8
- 239000011591 potassium Substances 0.000 description 8
- 229910052700 potassium Inorganic materials 0.000 description 8
- 208000009304 Acute Kidney Injury Diseases 0.000 description 7
- 108010088751 Albumins Proteins 0.000 description 7
- 102000009027 Albumins Human genes 0.000 description 7
- 206010002091 Anaesthesia Diseases 0.000 description 7
- 206010003445 Ascites Diseases 0.000 description 7
- 206010003658 Atrial Fibrillation Diseases 0.000 description 7
- 206010007559 Cardiac failure congestive Diseases 0.000 description 7
- 206010008132 Cerebral thrombosis Diseases 0.000 description 7
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 description 7
- 239000003154 D dimer Substances 0.000 description 7
- 206010014561 Emphysema Diseases 0.000 description 7
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 7
- 102000017011 Glycated Hemoglobin A Human genes 0.000 description 7
- 206010019280 Heart failures Diseases 0.000 description 7
- 102000001554 Hemoglobins Human genes 0.000 description 7
- 108010054147 Hemoglobins Proteins 0.000 description 7
- 201000001429 Intracranial Thrombosis Diseases 0.000 description 7
- 108010071690 Prealbumin Proteins 0.000 description 7
- 102000007584 Prealbumin Human genes 0.000 description 7
- 208000000418 Premature Cardiac Complexes Diseases 0.000 description 7
- 206010067171 Regurgitation Diseases 0.000 description 7
- 208000033626 Renal failure acute Diseases 0.000 description 7
- 208000025747 Rheumatic disease Diseases 0.000 description 7
- 102000013394 Troponin I Human genes 0.000 description 7
- 108010065729 Troponin I Proteins 0.000 description 7
- 201000011040 acute kidney failure Diseases 0.000 description 7
- 206010000891 acute myocardial infarction Diseases 0.000 description 7
- 208000012998 acute renal failure Diseases 0.000 description 7
- 230000037005 anaesthesia Effects 0.000 description 7
- 239000003146 anticoagulant agent Substances 0.000 description 7
- 229940127219 anticoagulant drug Drugs 0.000 description 7
- 206010003119 arrhythmia Diseases 0.000 description 7
- 230000006793 arrhythmia Effects 0.000 description 7
- 230000004872 arterial blood pressure Effects 0.000 description 7
- 208000006673 asthma Diseases 0.000 description 7
- 210000004556 brain Anatomy 0.000 description 7
- 206010006451 bronchitis Diseases 0.000 description 7
- 238000013501 data transformation Methods 0.000 description 7
- 238000000502 dialysis Methods 0.000 description 7
- 230000004069 differentiation Effects 0.000 description 7
- 108010052295 fibrin fragment D Proteins 0.000 description 7
- 230000008717 functional decline Effects 0.000 description 7
- 239000008103 glucose Substances 0.000 description 7
- 108091005995 glycated hemoglobin Proteins 0.000 description 7
- 230000003054 hormonal effect Effects 0.000 description 7
- 229940088597 hormone Drugs 0.000 description 7
- 239000005556 hormone Substances 0.000 description 7
- 230000000302 ischemic effect Effects 0.000 description 7
- 235000016709 nutrition Nutrition 0.000 description 7
- 230000000552 rheumatic effect Effects 0.000 description 7
- 230000035939 shock Effects 0.000 description 7
- 230000005586 smoking cessation Effects 0.000 description 7
- 208000012661 Dyskinesia Diseases 0.000 description 6
- 206010015856 Extrasystoles Diseases 0.000 description 6
- 206010020751 Hypersensitivity Diseases 0.000 description 6
- 208000035965 Postoperative Complications Diseases 0.000 description 6
- 206010071229 Procedural haemorrhage Diseases 0.000 description 6
- 208000006011 Stroke Diseases 0.000 description 6
- 208000002847 Surgical Wound Diseases 0.000 description 6
- 208000031650 Surgical Wound Infection Diseases 0.000 description 6
- 208000029650 alcohol withdrawal Diseases 0.000 description 6
- 239000002246 antineoplastic agent Substances 0.000 description 6
- 230000000740 bleeding effect Effects 0.000 description 6
- 229940127089 cytotoxic agent Drugs 0.000 description 6
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 238000002651 drug therapy Methods 0.000 description 6
- 210000003414 extremity Anatomy 0.000 description 6
- 210000000987 immune system Anatomy 0.000 description 6
- 230000009545 invasion Effects 0.000 description 6
- 210000004072 lung Anatomy 0.000 description 6
- 238000009116 palliative therapy Methods 0.000 description 6
- 230000001732 thrombotic effect Effects 0.000 description 6
- 150000003626 triacylglycerols Chemical class 0.000 description 6
- 230000002861 ventricular Effects 0.000 description 6
- 108010072866 Prostate-Specific Antigen Proteins 0.000 description 5
- 102000007066 Prostate-Specific Antigen Human genes 0.000 description 5
- 208000036064 Surgical Blood Loss Diseases 0.000 description 5
- 208000007536 Thrombosis Diseases 0.000 description 5
- 208000029078 coronary artery disease Diseases 0.000 description 5
- 238000002297 emergency surgery Methods 0.000 description 5
- 210000003743 erythrocyte Anatomy 0.000 description 5
- 206010000050 Abdominal adhesions Diseases 0.000 description 4
- 206010003497 Asphyxia Diseases 0.000 description 4
- 208000002403 Encephalocele Diseases 0.000 description 4
- 206010017982 Gastrointestinal necrosis Diseases 0.000 description 4
- 206010022773 Intracranial pressure increased Diseases 0.000 description 4
- 208000009378 Low Cardiac Output Diseases 0.000 description 4
- 206010033892 Paraplegia Diseases 0.000 description 4
- 208000031481 Pathologic Constriction Diseases 0.000 description 4
- 208000007123 Pulmonary Atelectasis Diseases 0.000 description 4
- 208000034158 bleeding Diseases 0.000 description 4
- 229910002092 carbon dioxide Inorganic materials 0.000 description 4
- 239000001569 carbon dioxide Substances 0.000 description 4
- 238000002512 chemotherapy Methods 0.000 description 4
- 230000006998 cognitive state Effects 0.000 description 4
- 230000035876 healing Effects 0.000 description 4
- 238000011127 radiochemotherapy Methods 0.000 description 4
- 230000036262 stenosis Effects 0.000 description 4
- 208000037804 stenosis Diseases 0.000 description 4
- 238000007920 subcutaneous administration Methods 0.000 description 4
- 206010003598 Atelectasis Diseases 0.000 description 3
- XUIIKFGFIJCVMT-GFCCVEGCSA-N D-thyroxine Chemical compound IC1=CC(C[C@@H](N)C(O)=O)=CC(I)=C1OC1=CC(I)=C(O)C(I)=C1 XUIIKFGFIJCVMT-GFCCVEGCSA-N 0.000 description 3
- 102000003982 Parathyroid hormone Human genes 0.000 description 3
- 108090000445 Parathyroid hormone Proteins 0.000 description 3
- 208000030714 Recurrent Laryngeal Nerve injury Diseases 0.000 description 3
- 201000002015 Thyroid Crisis Diseases 0.000 description 3
- 206010043786 Thyrotoxic crisis Diseases 0.000 description 3
- 206010065584 Urethral stenosis Diseases 0.000 description 3
- 230000001149 cognitive effect Effects 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 230000029142 excretion Effects 0.000 description 3
- 229960004657 indocyanine green Drugs 0.000 description 3
- MOFVSTNWEDAEEK-UHFFFAOYSA-M indocyanine green Chemical compound [Na+].[O-]S(=O)(=O)CCCCN1C2=CC=C3C=CC=CC3=C2C(C)(C)C1=CC=CC=CC=CC1=[N+](CCCCS([O-])(=O)=O)C2=CC=C(C=CC=C3)C3=C2C1(C)C MOFVSTNWEDAEEK-UHFFFAOYSA-M 0.000 description 3
- 208000003243 intestinal obstruction Diseases 0.000 description 3
- 238000007917 intracranial administration Methods 0.000 description 3
- 230000003902 lesion Effects 0.000 description 3
- 210000004185 liver Anatomy 0.000 description 3
- 239000000199 parathyroid hormone Substances 0.000 description 3
- 229960001319 parathyroid hormone Drugs 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 210000001685 thyroid gland Anatomy 0.000 description 3
- 229940034208 thyroxine Drugs 0.000 description 3
- XUIIKFGFIJCVMT-UHFFFAOYSA-N thyroxine-binding globulin Natural products IC1=CC(CC([NH3+])C([O-])=O)=CC(I)=C1OC1=CC(I)=C(O)C(I)=C1 XUIIKFGFIJCVMT-UHFFFAOYSA-N 0.000 description 3
- 238000002604 ultrasonography Methods 0.000 description 3
- 201000001988 urethral stricture Diseases 0.000 description 3
- 230000002792 vascular Effects 0.000 description 3
- 108090000935 Antithrombin III Proteins 0.000 description 2
- 102000004411 Antithrombin III Human genes 0.000 description 2
- 108010074051 C-Reactive Protein Proteins 0.000 description 2
- 102100032752 C-reactive protein Human genes 0.000 description 2
- 206010010071 Coma Diseases 0.000 description 2
- 108010049003 Fibrinogen Proteins 0.000 description 2
- 102000008946 Fibrinogen Human genes 0.000 description 2
- 206010019233 Headaches Diseases 0.000 description 2
- ZOKXTWBITQBERF-UHFFFAOYSA-N Molybdenum Chemical compound [Mo] ZOKXTWBITQBERF-UHFFFAOYSA-N 0.000 description 2
- 208000028389 Nerve injury Diseases 0.000 description 2
- 206010030113 Oedema Diseases 0.000 description 2
- 102000011923 Thyrotropin Human genes 0.000 description 2
- 108010061174 Thyrotropin Proteins 0.000 description 2
- 208000025865 Ulcer Diseases 0.000 description 2
- 206010046411 Ureteric stenosis Diseases 0.000 description 2
- 206010047700 Vomiting Diseases 0.000 description 2
- 108010026331 alpha-Fetoproteins Proteins 0.000 description 2
- 102000013529 alpha-Fetoproteins Human genes 0.000 description 2
- 229960005348 antithrombin iii Drugs 0.000 description 2
- 208000002352 blister Diseases 0.000 description 2
- 210000000481 breast Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 229940012952 fibrinogen Drugs 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 231100000869 headache Toxicity 0.000 description 2
- 210000005075 mammary gland Anatomy 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 229910052750 molybdenum Inorganic materials 0.000 description 2
- 239000011733 molybdenum Substances 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000008764 nerve damage Effects 0.000 description 2
- HPNRHPKXQZSDFX-OAQDCNSJSA-N nesiritide Chemical compound C([C@H]1C(=O)NCC(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CC(O)=O)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@H](C(N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)NCC(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)N[C@@H](CSSC[C@@H](C(=O)N1)NC(=O)CNC(=O)[C@H](CO)NC(=O)CNC(=O)[C@H](CCC(N)=O)NC(=O)[C@@H](NC(=O)[C@H](CCSC)NC(=O)[C@H](CCCCN)NC(=O)[C@H]1N(CCC1)C(=O)[C@@H](N)CO)C(C)C)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CC=1N=CNC=1)C(O)=O)=O)[C@@H](C)CC)C1=CC=CC=C1 HPNRHPKXQZSDFX-OAQDCNSJSA-N 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 229960003975 potassium Drugs 0.000 description 2
- 208000013223 septicemia Diseases 0.000 description 2
- 210000004872 soft tissue Anatomy 0.000 description 2
- 230000000451 tissue damage Effects 0.000 description 2
- 231100000827 tissue damage Toxicity 0.000 description 2
- 231100000397 ulcer Toxicity 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- WCDJCWGYYQTMGO-OAHLLOKOSA-N (2S)-2-amino-3-[4-(4-hydroxy-3,5-diiodophenoxy)-3,5-diiodophenyl]-2,3,3-triiodopropanoic acid Chemical compound IC([C@](N)(C(=O)O)I)(C1=CC(I)=C(C(I)=C1)OC1=CC(I)=C(C(I)=C1)O)I WCDJCWGYYQTMGO-OAHLLOKOSA-N 0.000 description 1
- WBLZUCOIBUDNBV-UHFFFAOYSA-N 3-nitropropanoic acid Chemical compound OC(=O)CC[N+]([O-])=O WBLZUCOIBUDNBV-UHFFFAOYSA-N 0.000 description 1
- 206010050456 Anastomotic leak Diseases 0.000 description 1
- BVKZGUZCCUSVTD-UHFFFAOYSA-M Bicarbonate Chemical compound OC([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-M 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010057441 Laryngeal injury Diseases 0.000 description 1
- 206010050902 Postoperative thrombosis Diseases 0.000 description 1
- 208000009453 Thyroid Nodule Diseases 0.000 description 1
- 208000024770 Thyroid neoplasm Diseases 0.000 description 1
- AUYYCJSJGJYCDS-LBPRGKRZSA-N Thyrolar Chemical compound IC1=CC(C[C@H](N)C(O)=O)=CC(I)=C1OC1=CC=C(O)C(I)=C1 AUYYCJSJGJYCDS-LBPRGKRZSA-N 0.000 description 1
- 206010057469 Vascular stenosis Diseases 0.000 description 1
- PNNCWTXUWKENPE-UHFFFAOYSA-N [N].NC(N)=O Chemical compound [N].NC(N)=O PNNCWTXUWKENPE-UHFFFAOYSA-N 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 208000008784 apnea Diseases 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 238000004159 blood analysis Methods 0.000 description 1
- 238000004820 blood count Methods 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 238000010968 computed tomography angiography Methods 0.000 description 1
- 238000002586 coronary angiography Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000000232 gallbladder Anatomy 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 208000008384 ileus Diseases 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 208000026278 immune system disease Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 201000009941 intracranial hypertension Diseases 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 238000002638 palliative care Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 210000001147 pulmonary artery Anatomy 0.000 description 1
- 238000001959 radiotherapy Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- -1 thyroid ultrasound Proteins 0.000 description 1
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 description 1
- 229940035722 triiodothyronine Drugs 0.000 description 1
- 210000003708 urethra Anatomy 0.000 description 1
- 208000019206 urinary tract infection Diseases 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- 230000008673 vomiting Effects 0.000 description 1
- 230000004580 weight loss Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a preoperative risk assessment method and a preoperative risk assessment system for a surgical operation, wherein the method comprises the following steps: determining main indexes of the evaluation of the surgical complications to form an index system; establishing a historical data set according to historical patient case data collected by indexes in an index system, and performing data preprocessing on the historical data set; forming a new historical data set according to indexes in the preprocessed historical data set extracted by the feature engineering and other data in the historical data set; establishing a risk prediction model by taking the data of the new history data set as input, taking various complications in an index system as output and integrating a supervised learning algorithm model as a base model; establishing a case data set; and inputting preoperative information in the case data set into the risk prediction model, judging the probability of each complication of the patient through the risk prediction model, and comparing the probability with the probability of the complication generated in the clinical surgical operation to form a risk assessment report. The invention can improve the reliability of the risk evaluation of the surgical operation complication.
Description
Technical Field
The invention belongs to the technical field of clinical medicine, and particularly relates to a preoperative risk assessment method and a preoperative risk assessment system for a surgical operation.
Background
In a medical scene, preoperative complication risk assessment is an important link before a surgical operation is performed, is directly related to risk assessment of the surgical process, and has important significance for a surgeon to grasp the surgical process and strengthen communication of doctor-patient relationship.
The common complications of the surgical operation include death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, ventilator dependence, low cardiac output after surgery, sternotomy, thrombus after surgery, intracranial infection, increased intracranial pressure, cerebral hernia, pulmonary embolism, deep vein thrombosis of lower limbs, anastomotic fistula, infection at the surgical site, infection at superficial incision, infection at deep incision, infection around organ in body cavity, incision dehiscence, systemic septicemia, infection of urinary system, renal failure, hemorrhage at the surgical site, unplanned reoperation, postoperative delirium, decreased function, inability to walk, need of mobility assistance, pressure ulcer progression, poor healing, paraplegia, infection at the surgical site tissue, gas leakage, pulmonary atelectasis, stenosis of urethra, ureteral stenosis, dyspnea, apnea, recurrent laryngeal nerve injury, thyroid crisis, vascular surgical hemorrhage, asphyxia, and the like, Pulmonary cerebral embolism, intestinal adhesion, intestinal obstruction, intestinal necrosis, biliary leakage, pancreatic leakage, surgical hemorrhage of liver and gallbladder, subcutaneous effusion, WBC abnormality, CPR abnormality, oxygen partial pressure, carbon dioxide partial pressure, white blood cell, red blood cell, prostate specific antigen, etc.
Related research has been conducted abroad on risk assessment programs for surgical complications and related risk calculation tools have been developed, such as: the Risk Calculator of the national Surgical quality improvement program of the American surgeon Association has been shown to be useful in predicting postoperative complications (see documents Development and Evaluation of the Universal ACS NSQIP Surgical Risk calcium: A Decision air and information consensus Tool for Patents and targets). The risk assessment models and methods for surgical complications in China are rarely studied, and the risk assessment of a certain complication (for example, a surgical incision infection risk assessment system disclosed in the Chinese patent application with publication No. CN 108922620A) or the assessment of the effect on a certain disease (refer to preliminary identification of the ACS-NSQIP scientific tissue in clinical patients with systemic syndrome) is mainly studied. At present, most hospitals do not have a tool for risk assessment of surgical complications clinically, and clinicians prevent postoperative complications according to experience, so that doctors at different levels have inconsistent suggestions of complications possibly occurring in the same patient, and because clinical indexes of the patient are more, partial index bases are easily missed when the doctors judge the postoperative complications, and the reliability is poor.
Disclosure of Invention
Aiming at the problems of poor reliability and the like existing in the prior art of risk assessment of surgical complications, the invention provides a method and a system for risk assessment before surgery, which are used for risk assessment before surgery, predicting the risk probability value of complications of a patient in the process of surgery to be performed or after surgery, and providing reference basis for doctors to control the surgery process and communicate doctors and patients before surgery.
In order to achieve the above object, the present invention provides a preoperative risk assessment method, comprising the following steps:
forming an index system: determining main indexes of the surgical complication evaluation according to the relevant surgical guide and the surgical case data, and forming an index system according to the main indexes; the primary indicators include indicators related to surgical complications and complication names;
and (3) constructing a historical data set: establishing a historical data set according to historical patient case data collected by indexes in an index system;
a data preprocessing step: preprocessing data in the historical data set;
characteristic engineering steps: extracting indexes meeting a set threshold value through feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set;
constructing a risk prediction model: establishing a risk prediction model by taking data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking an integrated supervised learning algorithm model as a base model;
and (3) constructing a case data set: establishing a case data set according to preoperative information of a patient to be evaluated;
a patient preoperative risk assessment step: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
Preferably, the step of constructing the historical data set further includes:
and (3) index standardization step: standardizing indexes in an index system through construction of an alias system;
a data acquisition step: collecting historical patient case data according to indexes in an index system;
a data set construction step: a historical data set is constructed from the patient historical case data.
Preferably, in the step of constructing the historical data set, the patient historical case data is collected in a manner of patient clinical data derived in a hospital system, or directly collected, or patient feedback data output by the risk prediction model.
Preferably, in the data preprocessing step, the method for preprocessing the data in the historical data set includes: carrying out data structuring processing, missing value processing and error value processing on data in the historical data set, and then carrying out standardization processing; the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of qualitative characteristics into quantitative characteristics by using a dummy code mode, and data conversion processing.
Preferably, in the feature engineering step, the method for extracting the index in the historical data set includes:
a characteristic selection step: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
a feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
Preferably, in the step of constructing a case data set, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward visit information, and a patient medical record home page.
In order to achieve the above object, the present invention also provides a preoperative risk assessment system, comprising:
the system comprises an information input module, a clinical reference information and pre-operation information of a patient to be evaluated, wherein the clinical reference information comprises a surgical operation related guide, a knowledge text and surgical case data, and the pre-operation information of the patient to be evaluated comprises patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information and a patient case first page;
the data acquisition module is used for acquiring historical case data of a patient;
the data storage module is used for storing the clinical reference information and the preoperative information of the patient to be evaluated which are input by the information input module and the historical case data of the patient which are acquired by the data acquisition module; forming an index system according to the clinical reference information, forming a historical data set according to historical patient case data collected by indexes in the index system, and forming a case data set according to preoperative information of a patient to be evaluated;
the characteristic engineering module is used for extracting a historical data set from the data storage module and performing characteristic engineering extraction on the historical data set to obtain a new historical data set;
the risk prediction model generation module is used for extracting a new historical data set from the characteristic engineering module, taking data in the new historical data set as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a basic model to generate a risk prediction model;
a judgment module; the risk prediction model is used for storing the risk prediction model, extracting preoperative information of a patient to be evaluated, evaluating preoperative risk of the patient to be evaluated through the risk prediction model, predicting the occurrence probability of each complication of the patient, and comparing the probability with the occurrence probability of the complication in a clinical surgical operation to form a risk evaluation report for reference of doctors and the patient;
and the output module is used for outputting and feeding back the risk assessment report formed by the judgment module to the user.
Preferably, the system further comprises an information feedback module for collecting case information of the user after risk assessment is performed, sending the case information to the data storage module as patient historical case data, and updating the historical data set.
Preferably, still include PC end, remove end APP and server, information entry module, data acquisition module, output module and information feedback module install in PC end and removal end APP, data storage module, characteristic engineering module, risk prediction model generation module and judgment module install in the server.
Compared with the prior art, the invention has the advantages and positive effects that:
(1) the method comprises the steps of determining main indexes of surgical complication risk assessment according to surgical operation relevant guidelines and surgical case data, forming an index system according to the main indexes, collecting historical case data of a patient according to indexes in the index system, and further establishing a historical data set; and extracting by combining with characteristic engineering, selecting final index characteristics to obtain a new history data set, constructing a risk assessment model by combining with an integrated supervised learning method model according to data of the new history data set, assessing preoperative risk of a patient to be operated by the risk assessment model, improving the reliability of preoperative risk assessment of the surgical operation, and providing a reference basis for doctors to control the operation process and communicate preoperative doctors and patients before the operation.
(2) The method has three modes of collecting historical data, combines the three modes to accumulate data through patient clinical data derived from a hospital system or directly collected or patient feedback data output by the risk prediction model, uses the patient feedback information after risk evaluation of the risk prediction model as historical patient case data for iterative optimization of the risk prediction model, ensures that the accuracy of the risk prediction model is higher, and further improves the reliability of the direction evaluation before the surgery.
(3) The invention considers general complications and special complications in the field of total surgery instead of risk assessment of single complications, considers the difference of medical indexes, has strong universality and is suitable for surgical scenes.
Drawings
FIG. 1 is a block flow diagram of a preoperative risk assessment method according to an embodiment of the invention;
fig. 2 is a block diagram illustrating a preoperative risk assessment system according to an embodiment of the present invention.
Detailed Description
The invention is described in detail below by way of exemplary embodiments. It should be understood, however, that elements, structures and features of one embodiment may be beneficially incorporated in other embodiments without further recitation.
The surgery can evaluate the possible complications caused by the surgery before the surgery, most hospitals do not have tools for evaluating the risk of the complications caused by the surgery clinically at present, and clinicians prevent the postoperative complications according to experience, so that the suggestions of the complications possibly occurring to the same patient by doctors with different levels are possibly inconsistent, and partial index bases are easily missed when the doctors judge the postoperative complications due to more clinical indexes of the patient. In order to improve the accuracy and reliability of risk assessment before surgery, the invention provides a method and a system for risk assessment before surgery, which are used for assessing the risk of complications possibly caused by surgery before surgery and providing reference basis for doctors to control the surgery process and communicate doctors and patients before surgery. The preoperative risk assessment method and system are described in detail below.
Referring to fig. 1, the present invention discloses a preoperative risk assessment method, comprising the following steps:
s1, forming an index system: determining main indexes of the surgical complication evaluation according to the relevant surgical guide and the surgical case data, and forming an index system according to the main indexes; the primary indicators include indicators related to surgical complications and complication names.
Specifically, the guidelines related to surgical operations employ general surgical diagnosis and treatment guidelines (3 rd edition), and guidelines for prevention of infection at a surgical site (2017).
Specifically, the surgical corresponding complication indicators include: death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, ventilator dependence, post-operative low cardiac output, sternotomy, post-operative thrombosis, intracranial infection, increased intracranial pressure, cerebral hernia, pulmonary embolism, lower limb deep vein thrombosis, anastomotic fistula, surgical site infection, superficial incision infection, deep incision infection, peri-organ infection in the body cavity, incision dehiscence, systemic sepsis, urinary system infection, renal failure, hemorrhage in the operative area, unplanned reoperation, post-operative delirium, decreased function, inability to walk, need for use of mobility assistance, pressure ulcer progression, poor healing, paraplegia, surgical site tissue infection, air leakage, atelectasis, urethral stricture, ureteral stenosis, dyspnea, asphyxia, recurrent laryngeal injury, thyroid crisis, vascular bleeding, pulmonary cerebral embolism, intestinal adhesion, Ileus, intestinal necrosis, biliary leakage, pancreatic leakage, surgical hemorrhage of liver and gall, subcutaneous fluid collection, WBC abnormality, CPR abnormality, oxygen partial pressure, carbon dioxide partial pressure, white blood cells, red blood cells, prostate specific antigen, and the like.
S2, historical data set construction step: and establishing a historical data set according to the historical patient case data collected by the indexes in the index system.
Specifically, the step of constructing the historical data set further comprises:
s21, index standardization step: standardizing indexes in an index system through construction of an alias system;
s22, data acquisition step: collecting historical patient case data according to indexes in an index system;
s23, data set construction: a historical data set is constructed from the patient historical case data.
The collected historical patient case data of the patient is subjected to index standardization, and the sample data is more comprehensive and balanced when a risk prediction model is constructed later, so that the accuracy and the reliability of the risk prediction model are higher.
Specifically, the patient historical case data is collected by means of patient clinical data derived in a hospital system or directly collected, or patient feedback data output by the risk prediction model. And three modes are combined for data accumulation, and the feedback information of the patient after risk evaluation of the risk prediction model is used as historical patient case data for iterative optimization of the risk prediction model, so that the accuracy of the risk prediction model is higher, and the reliability of the preoperative direction evaluation of the surgery is further improved.
Specifically, the patient history case data that the surgery needs to collect includes: age, sex, name of the hospital admission, hospital admission diagnostic code, BMI, Glasgow coma score, muscle strength, headache, emesis, optic papillary edema, degree of hypertension, whether hypertension requires medication, history of coronary heart disease, stenting, fasting blood glucose levels, glycated hemoglobin, history of cerebral hemorrhage, history of cerebral thrombosis, history of rheumatic immune system disease, hormonal use, asthma, bronchitis, dialysis, acute renal failure, smoking age, smoking duration, smoking cessation age, drinking alcohol cessation age, anticoagulant, hormone-like medication, chemotherapy, mobility assistance, cognitive status at check-in, state at home, palliative therapy at hospital admission, drop history, hospital admission independent processing ability, ascites within 30 days before surgery, Systemic sepsis occurring 48 hours before surgery, congestive heart failure 30 days before surgery, severe COPD history, dyspnea, admission to hospital due to malignant tumor, invasion of adjacent organs (tissues), diffuse cancer, degree of tumor differentiation, type of surgery, surgical procedure code, surgical name, surgical indication, whether it is an acute surgery, whether it is shock, whether there is a history of life support, anesthesia, whether it is chemoradiotherapy, type of surgical incision, acute myocardial infarction, Killip grading, NYHA grading, functional status, ASA grading, NRS2002 (nutritional risk screening score), days of hospitalization, arrhythmia, atrial fibrillation, premature beats, conduction block, ST ischemic manifestation, ejection fraction, pulmonary artery pressure, valve regurgitation, segmental dyskinesia of the ventricular wall, breast molybdenum target diagnosis whether lesion, breast magnetic resonance diagnosis whether lesion, degree of vascular stenosis, degree of stenosis, etc Thrombosis, low density or brain softening focus, normality of craniocerebral CT, fracture site, degree of fracture, nerve damage associated with fracture, soft tissue damage associated with fracture, thyroid lesion, thyroid nodule grade, emphysema, bullous bullae, leukocytes, hemoglobin, platelet count, urine leukocytes, urine erythrocytes, PT, APTT, fibrinogen, antithrombin III, D-dimer, prostate specific antigen, alpha-fetoprotein, albumin, prealbumin, ALT, AST, Cr, urea nitrogen, oxygen partial pressure, carbon dioxide partial pressure, pH, bicarbonate, base residual, oxygen saturation, triglycerides, total cholesterol, low density lipoprotein, parathyroid hormone, thyroxine, free triiodothyronine, thyroid stimulating hormone, potassium, indocyanine green excretion test results, B-type brain natriuretic peptide, total cholesterol, low density lipoprotein, parathyroid hormone, thyroxine, free triiodothyroxine, thyroid stimulating hormone, potassium, indocyanine green excretion test results, brain-type B-type brain natriuretic peptide, and/or a combination thereof, High sensitivity troponin-I index.
It should be noted that, because different operation types need to satisfy the requirement of collecting balanced sample data when a risk prediction model is constructed and modeled later, in the process of collecting data, the operation types are uniformly coded, and in this embodiment, the operation types are uniformly coded by using "universal medical procedure coding" which is mainly compiled by the american medical association AMA.
S3, data preprocessing: data in the historical dataset is preprocessed.
Specifically, the method for preprocessing the data in the historical data set comprises the following steps: the method comprises the steps of carrying out data structuring processing, missing value processing and error value processing on data in a historical data set, and then carrying out standardization processing, wherein the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of the qualitative characteristics into the quantitative characteristics by means of dummy coding and data transformation processing.
The data in the historical data set is subjected to structuring processing, missing value processing, error value processing and standardization processing, so that the sample data is more comprehensively balanced when a risk prediction model is constructed later, and the accuracy and the reliability of the risk prediction model are higher.
S4, characteristic engineering step: and extracting indexes meeting a set threshold value through a feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set.
Specifically, the method for extracting the index in the historical data set comprises the following steps:
s41, feature selection: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
s42, feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
It should be noted that, after the indexes selected by the features are fused with the new indexes generated by the features, the new indexes are fused with other data in the historical data set to form a new historical data set, and when a risk prediction model is constructed later, the fused indexes are more comprehensive and balanced, so that the accuracy and reliability of the constructed risk prediction model are further improved.
S5, constructing a risk prediction model: and establishing a risk prediction model by taking the data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a base model.
S6, a case data set construction step: and establishing a case data set according to preoperative information of a patient to be evaluated.
Specifically, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information, and a patient medical record home page.
S7, assessment of preoperative risk of patients: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
The method of the invention determines the main indexes of the surgical complication risk assessment according to the relevant guidelines of the surgical operation and the surgical case data, forms an index system according to the main indexes, collects the historical case data of the patient according to the indexes in the index system, and further establishes a historical data set; and extracting by combining with characteristic engineering, selecting final index characteristics to obtain a new history data set, constructing a risk assessment model by combining with an integrated supervised learning method model according to data of the new history data set, assessing preoperative risk of a patient to be operated by the risk assessment model, improving the reliability of preoperative risk assessment of the surgical operation, and providing a reference basis for doctors to control the operation process and communicate preoperative doctors and patients before the operation.
Referring to fig. 2, an embodiment of the present invention provides a preoperative risk assessment system, including:
the system comprises an information input module 1, a clinical reference information and pre-operation information of a patient to be evaluated, wherein the clinical reference information comprises a surgical operation related guide, a knowledge text and surgical case data, and the pre-operation information of the patient to be evaluated comprises patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information and a patient case first page;
the data acquisition module 2 is used for acquiring historical case data of a patient;
the data storage module 3 is used for storing the clinical reference information and the preoperative information of the patient to be evaluated which are input by the information input module and the historical case data of the patient which are acquired by the data acquisition module; forming an index system according to the clinical reference information, forming a historical data set according to historical patient case data collected by indexes in the index system, and forming a case data set according to preoperative information of a patient to be evaluated;
the characteristic engineering module 4 is used for extracting a historical data set from the data storage module and performing characteristic engineering extraction on the historical data set to obtain a new historical data set;
the risk prediction model generation module 5 is used for extracting a new historical data set from the characteristic engineering module, taking data in the new historical data set as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a basic model to generate a risk prediction model;
a judgment module 6; the risk prediction model is used for storing the risk prediction model, extracting preoperative information of a patient to be evaluated, evaluating preoperative risk of the patient to be evaluated through the risk prediction model, predicting the occurrence probability of each complication of the patient, and comparing the probability with the occurrence probability of the complication in a clinical surgical operation to form a risk evaluation report for reference of doctors and the patient;
and the output module 7 is used for outputting and feeding back the risk assessment report formed by the judgment module to the user.
The system also comprises an information feedback module 8 which is used for collecting the case information of the user after risk assessment is carried out, sending the information to the data storage module 3 as the historical case data of the patient and updating the historical data set.
The system further comprises a PC (personal computer) end 9, a mobile end APP10 and a server 11, wherein the information entry module 1, the data acquisition module 2, the output module 7 and the information feedback module 8 are installed in the PC end 9 and the mobile end APP10, and the data storage module 3, the characteristic engineering module 4, the risk prediction model generation module 5 and the judgment module 6 are installed in the server 11.
In the system, the risk prediction model is used for evaluating the preoperative risk of a case data set to be evaluated, predicting the occurrence probability of each complication of a patient, comparing the probability with the occurrence probability of the complication in a clinical surgical operation, outputting a generated risk evaluation report to the output module, and finally outputting the risk evaluation report by the output module to provide a reference basis for the doctor to control the operation process and communicate the preoperative doctor and patient before the operation.
The above system is used for evaluating the complications possibly caused by the operation of a patient before the surgical operation, and doctors input basic information of preoperative information of the patient, personal history, previous diseases, imaging examination and blood examination to evaluate the death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, breathing machine dependence, postoperative low cardiac output, sternal opening, postoperative thrombus, intracranial infection, intracranial pressure increase, cerebral hernia, pulmonary embolism, lower limb deep vein thrombus, anastomotic fistula, operation site infection, superficial incision infection, deep incision infection, infection around organs in body cavity, incision opening, systemic septicemia, urinary system infection, renal failure, hemorrhage in operation area, nonprescheduled reoperation, postoperative delirium, functional decline and incapability of walking, and the need to use action assistance, pressure ulcer progression, Poor healing, paraplegia, tissue infection at the operation site, air leakage, atelectasis, urethral stricture, ureteral stricture, dyspnea, asphyxia, recurrent laryngeal nerve injury, thyroid crisis, vascular surgical hemorrhage, pulmonary cerebral embolism, intestinal adhesion, intestinal obstruction, intestinal necrosis, biliary leakage, pancreatic leakage, hepatobiliary surgical hemorrhage, subcutaneous fluid collection, WBC abnormality, CPR abnormality, oxygen partial pressure, carbon dioxide partial pressure, white blood cells, red blood cells, prostate specific antigen and other complications, and outputting the operation risk of the patient, and finally forming a report which can be provided for the patient and family members.
According to the system, main indexes of surgical operation complication risk assessment are determined according to the relevant guidelines of the surgical operation and the surgical case data, an index system is formed according to the main indexes, historical case data of a patient are collected according to the indexes in the index system, and a historical data set is further established; and extracting by combining with characteristic engineering, selecting final index characteristics to obtain a new history data set, constructing a risk assessment model by combining with an integrated supervised learning method model according to data of the new history data set, assessing preoperative risk of a patient to be operated by the risk assessment model, having high accuracy of risk assessment, improving reliability of preoperative risk assessment of the surgery, providing reference basis for doctors to control the operation process and communication between preoperative doctors and patients before the operation, avoiding the occurrence of inconsistent suggestions of possibly occurring complications of doctors at different levels to the same patient in clinic, and preventing the doctors from easily missing part of indexes when judging postoperative complications due to more clinical indexes of the patient.
The above method and system are further described in the following with specific embodiments.
Example 1: a preoperative risk assessment method for orthopedic surgery comprises the following steps:
s1, forming an index system: determining main indexes for evaluating complications of the orthopedic surgery according to relevant guidelines of the orthopedic surgery and orthopedic case data, and forming an index system according to the main indexes; the main indexes comprise indexes related to the complications of the orthopedic surgery and the names of the complications.
Specifically, the guidelines related to the orthopedic operation adopt Chinese guidelines for prevention of venous thrombosis in major orthopedic operations, prevention and treatment of complications in orthopedic operations (version 3), general guidelines for diagnosis and treatment of surgical diseases (version 3), and guidelines for prevention of infection at a surgical site (2017).
Specifically, the corresponding complication index of the orthopedic surgery comprises a universality index and an orthopedic surgery specificity index. Wherein, the universality index comprises: death, cardiovascular accidents, cerebrovascular accidents, respiratory failure, pulmonary embolism, pneumonia, limb thrombotic complications, anastomotic fistulas, incision infections, incision dehiscence, organ space infections, systemic sepsis, urinary system infections, renal failure, intraoperative hemorrhage, unplanned reoperation, postoperative delirium, functional decline, use of traffic aids, pressure ulcer progression. The orthopedic surgery specific indexes comprise: poor healing, paraplegia, WBC abnormalities, CPR abnormalities, and the like.
S2, historical data set construction step: and establishing a historical data set according to the historical patient case data collected by the indexes in the index system.
Specifically, the step of constructing the historical data set further comprises:
s21, index standardization step: standardizing indexes in an index system through construction of an alias system;
s22, data acquisition step: collecting historical patient case data according to indexes in an index system;
s23, data set construction: a historical data set is constructed from the patient historical case data.
Specifically, the patient history case data collected by the orthopedic surgery includes two parts of a surgical universality index and an orthopedic surgery specificity index. Wherein the surgical commonality indicators include: age, sex, BMI, white blood cells, hemoglobin, platelet count, PT, APTT, D-dimer, albumin, prealbumin, ALT, AST, Cr, BUN, PO2、PCO2pH, HCO3-BE, oxygen saturation, triglyceride, total cholesterol, low density lipoprotein, potassium, BNP, hypersensitive troponin-I, arrhythmia, atrial fibrillation, premature beat, and conduction blockST ischemic manifestation, EF, pulmonary arterial pressure, valve regurgitation, segmental wall motion abnormalities, fracture site, degree of fracture, nerve damage associated with fracture, soft tissue damage associated with fracture, low density or brain softening foci, emphysema, bullous lung, hypertension, whether hypertension requires drug therapy, whether stenting, fasting plasma glucose, glycated hemoglobin, cerebral hemorrhage, cerebral thrombosis, the rheumatic immune system, hormone use, asthma, bronchitis, dialysis or not, acute renal failure, smoking age, smoking cessation age, drinking age, alcohol withdrawal age, anticoagulant, hormone, chemotherapeutic agent, use of mobility assistance, cognitive status at enrollment, status at home, palliative therapy at admission, drop history, functional status, ASA grading, NRS2002 (nutritional risk screening score), admission capacity, hospitalization capacity, weight loss, Ascites within 30 days before operation, systemic sepsis occurring 48 hours before operation, congestive heart failure 30 days before operation, severe COPD history, dyspnea, whether hospitalization was due to a malignant tumor, whether an adjacent organ (tissue) was invaded, degree of tumor differentiation, diffuse cancer, type of operation, name of operation, surgical indication, whether emergency surgery was performed, whether shock was experienced, whether a life support history was used, anesthesia pattern, whether radiochemotherapy was performed, type of surgical incision, acute myocardial infarction, Killip classification, NYHA classification, days of hospitalization, death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, pulmonary embolism, lower limb deep vein thrombosis, anastomotic fistula, renal failure, bleeding in operative areas, postoperative delirium, unplanned reoperation, progression of compressive ulcer, and the like. The specific indexes of the orthopedic surgery comprise X-ray plain films, CT, magnetic resonance and the like.
S3, data preprocessing: data in the historical dataset is preprocessed.
Specifically, the method for preprocessing the data in the historical data set comprises the following steps: the method comprises the steps of carrying out data structuring processing, missing value processing and error value processing on data in a historical data set, and then carrying out standardization processing, wherein the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of the qualitative characteristics into the quantitative characteristics by means of dummy coding and data transformation processing.
S4, characteristic engineering step: and extracting indexes meeting a set threshold value through a feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set.
Specifically, the method for extracting the index in the historical data set comprises the following steps:
s41, feature selection: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
s42, feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
S5, constructing a risk prediction model: and establishing a risk prediction model by taking the data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a base model.
S6, a case data set construction step: and establishing a case data set according to preoperative information of a patient to be evaluated.
Specifically, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information, and a patient medical record home page.
S7, assessment of preoperative risk of patients: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
Example 2: a pre-operative risk assessment method for cardiovascular surgery comprises the following steps:
s1, forming an index system: determining main indexes for evaluating the cardiovascular surgical complications according to relevant guidelines of the cardiovascular surgical operations and cardiovascular surgical case data, and forming an index system according to the main indexes; the primary indicators include indicators related to cardiovascular surgical complications and complication designations.
Specifically, the guidelines related to cardiovascular surgery include cardiovascular surgery diagnosis and treatment guidelines (3 rd edition), chinese first-class cardiovascular disease prevention guidelines, general surgery diagnosis and treatment guidelines (3 rd edition), and surgical site infection prevention guidelines (2017).
Specifically, the cardiovascular surgery-corresponding complication index includes a general index and a cardiovascular surgery-specific index. Wherein, the universality index comprises: death, cardiovascular accidents, cerebrovascular accidents, respiratory failure, pulmonary embolism, pneumonia, limb thrombotic complications, anastomotic fistulas, incision infections, incision dehiscence, organ space infections, systemic sepsis, urinary system infections, renal failure, intraoperative hemorrhage, unplanned reoperation, postoperative delirium, functional decline, use of traffic aids, pressure ulcer progression. Cardiovascular surgery specific indices include: low cardiac output after operation, sternal opening, thrombus after operation, etc.
S2, historical data set construction step: and establishing a historical data set according to the historical patient case data collected by the indexes in the index system.
Specifically, the step of constructing the historical data set further comprises:
s21, index standardization step: standardizing indexes in an index system through construction of an alias system;
s22, data acquisition step: collecting historical patient case data according to indexes in an index system;
s23, data set construction: a historical data set is constructed from the patient historical case data.
Specifically, the patient historical case data that needs to be collected for cardiovascular surgery includes both surgical commonality indicators and cardiovascular surgery-specific indicators. Wherein the surgical commonality indicators include: age, sex, BMI, white blood cells, hemoglobin, platelet count, PT, APTT, D-dimer, albumin, prealbumin, ALT, AST, Cr, BUN, PO2、PCO2pH, HCO3-BE, oxygen saturation, triglycerides, total cholesterol, low density lipoprotein, potassium, BNP, hypersensitive troponin-I, arrhythmia, atrial fibrillation, premature beats, conduction block, ST ischemic manifestations, EF, pulmonary arterial pressure, valve regurgitation, segmental dyskinesia of the ventricular wall, hypodense or softened foci of the brain, emphysema, bullous lung, hypertension, whether hypertension requires drug therapy, coronary heart disease, whether stents, fasting plasma glucose, glycated hemoglobin, cerebral hemorrhage, cerebral thrombosis, the rheumatic immune system, hormonal use, asthma, bronchitis, whether dialysis, acute renal failure, smoking duration, whether smoking cessation, smoking duration, alcohol consumption duration, alcohol withdrawal, alcohol consumption duration, anticoagulant, hormone, chemotherapeutic agent, use of mobility assistance, cognitive state at enrollment, state at home, palliative therapy at admission, state at home, and the like, Drop history, functional status, ASA grade, NRS2002 (nutritional risk screening score), admission capacity, ascites within 30 days prior to surgery, systemic sepsis occurring 48 hours prior to surgery, congestive heart failure within 30 days prior to surgery, severe COPD history, dyspnea, admission to hospital due to a malignant tumor, invasion of adjacent organs (tissues), degree of tumor differentiation, diffuse cancer, type of surgery, name of surgery, surgical indication, whether emergency surgery, shock, history of use of life support, anesthesia modality, chemotherapy, type of surgical incision, acute myocardial infarction, Killip grade, NYHA grade, days of hospitalization, death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, pulmonary embolism, lower limb deep vein thrombosis, anastomotic fistula, renal failure, bleeding in the surgical area, postoperative delirium, postoperative, Non-planned reoperation, progression of compressive ulcer, etc.Cardiovascular surgery specific indices include elective coronary angiography, past history of cerebral infarction, and the like.
S3, data preprocessing: data in the historical dataset is preprocessed.
Specifically, the method for preprocessing the data in the historical data set comprises the following steps: the method comprises the steps of carrying out data structuring processing, missing value processing and error value processing on data in a historical data set, and then carrying out standardization processing, wherein the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of the qualitative characteristics into the quantitative characteristics by means of dummy coding and data transformation processing.
S4, characteristic engineering step: and extracting indexes meeting a set threshold value through a feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set.
Specifically, the method for extracting the index in the historical data set comprises the following steps:
s41, feature selection: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
s42, feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
S5, constructing a risk prediction model: and establishing a risk prediction model by taking the data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a base model.
S6, a case data set construction step: and establishing a case data set according to preoperative information of a patient to be evaluated.
Specifically, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information, and a patient medical record home page.
S7, assessment of preoperative risk of patients: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
Example 3: a preoperative risk assessment method for thoracic surgery comprises the following steps:
s1, forming an index system: determining main indexes for evaluating complications of the thoracic surgery according to relevant guidelines of the thoracic surgery and thoracic surgery case data, and forming an index system according to the main indexes; the primary indices include indices related to complications of thoracic surgery and complication names.
Specifically, the guidelines related to thoracic surgery employ prevention and treatment of cardiothoracic surgical complications, chinese thoracic surgery perioperative airway management guidelines (2020 version), general surgical disease diagnosis guidelines (3 rd version), and surgical site infection prevention guidelines (2017).
Specifically, the complications index corresponding to the thoracic surgery includes a general index and a thoracic surgery specificity index. Wherein, the universality index comprises: death, cardiovascular accidents, cerebrovascular accidents, respiratory failure, pulmonary embolism, pneumonia, limb thrombotic complications, anastomotic fistulas, incision infections, incision dehiscence, organ space infections, systemic sepsis, urinary system infections, renal failure, intraoperative hemorrhage, unplanned reoperation, postoperative delirium, functional decline, use of traffic aids, pressure ulcer progression. Thoracic surgery specific indices include: leakage of qi, atelectasis of the lung, etc.
S2, historical data set construction step: and establishing a historical data set according to the historical patient case data collected by the indexes in the index system.
Specifically, the step of constructing the historical data set further comprises:
s21, index standardization step: standardizing indexes in an index system through construction of an alias system;
s22, data acquisition step: collecting historical patient case data according to indexes in an index system;
s23, data set construction: a historical data set is constructed from the patient historical case data.
Specifically, the patient history case data collected by the thoracic surgery includes two parts of a general surgical index and a specific thoracic surgery index. Wherein the surgical commonality indicators include: age, sex, BMI, white blood cells, hemoglobin, platelet count, PT, APTT, D-dimer, albumin, prealbumin, ALT, AST, Cr, BUN, PO2、PCO2pH, HCO3-BE, oxygen saturation, triglycerides, total cholesterol, low density lipoprotein, potassium, BNP, hypersensitive troponin-I, arrhythmia, atrial fibrillation, premature beats, conduction block, ST ischemic manifestations, EF, pulmonary arterial pressure, valve regurgitation, segmental dyskinesia of the ventricular wall, hypodense or softened brain foci, emphysema, bullous lung, hypertension, whether hypertension requires drug therapy, whether stents, fasting plasma glucose, glycated hemoglobin, cerebral hemorrhage, cerebral thrombosis, the rheumatic immune system, hormonal use, asthma, bronchitis, whether dialysis, acute renal failure, smoking duration, whether smoking cessation, smoking duration, alcohol consumption duration, alcohol withdrawal duration, anticoagulant, hormone, chemotherapeutic agent, use of mobility assistance, cognitive state at check-in, state at home, palliative therapy at admission, history of dropping, and the like, Functional status, ASA grade, NRS2002 (nutritional risk screening score), admission capacity, ascites within 30 days before surgery, systemic sepsis occurring 48 hours before surgery, congestive heart failure 30 days before surgery, severe COPD history, dyspnea, admission to hospital due to malignant tumors, invasion of adjacent organs (tissues), degree of tumor differentiation, diffuse cancer, hand cancer, liver cancerThe type of operation, the name of the operation, the indication of the operation, whether or not an emergency operation is performed, whether or not shock is caused, whether or not a history of life support is used, the anesthesia mode, whether or not radiotherapy and chemotherapy are performed, the type of the operation incision, acute myocardial infarction, Killip grading, the number of hospitalization days, death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, pulmonary embolism, lower limb deep vein thrombosis, anastomotic fistula, renal failure, bleeding in the operation area, postoperative delirium, unplanned reoperation and other indexes. Thoracic surgery specific indicators include WBC abnormalities, CPR abnormalities, and the like.
S3, data preprocessing: data in the historical dataset is preprocessed.
Specifically, the method for preprocessing the data in the historical data set comprises the following steps: the method comprises the steps of carrying out data structuring processing, missing value processing and error value processing on data in a historical data set, and then carrying out standardization processing, wherein the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of the qualitative characteristics into the quantitative characteristics by means of dummy coding and data transformation processing.
S4, characteristic engineering step: and extracting indexes meeting a set threshold value through a feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set.
Specifically, the method for extracting the index in the historical data set comprises the following steps:
s41, feature selection: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
s42, feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
S5, constructing a risk prediction model: and establishing a risk prediction model by taking the data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a base model.
S6, a case data set construction step: and establishing a case data set according to preoperative information of a patient to be evaluated.
Specifically, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information, and a patient medical record home page.
S7, assessment of preoperative risk of patients: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
Example 4: a preoperative risk assessment method for general surgery comprises the following steps:
s1, forming an index system: determining main indexes for evaluating complications of general surgery according to relevant guidelines of general surgery and general surgery case data, and forming an index system according to the main indexes; the main indicators include indicators related to the complications of general surgery and the names of the complications.
Specifically, general surgical guidelines include general surgical diagnosis and treatment guidelines (3 rd edition) and surgical site infection prevention guidelines (2017).
Specifically, the indexes of the complications corresponding to the general surgery comprise a general index and a general surgery operation specificity index. Wherein, the universality index comprises: death, cardiovascular accidents, cerebrovascular accidents, respiratory failure, pulmonary embolism, pneumonia, limb thrombotic complications, anastomotic fistulas, incision infections, incision dehiscence, organ space infections, systemic sepsis, urinary system infections, renal failure, intraoperative hemorrhage, unplanned reoperation, postoperative delirium, functional decline, use of traffic aids, pressure ulcer progression. General surgery specific indices include: hemorrhage, pulmonary embolism, anastomotic leakage, intestinal adhesion, intestinal obstruction, intestinal necrosis, biliary leakage, pancreatic leakage, dyspnea, asphyxia, recurrent laryngeal nerve injury, thyroid gland crisis, subcutaneous effusion, etc.
S2, historical data set construction step: and establishing a historical data set according to the historical patient case data collected by the indexes in the index system.
Specifically, the step of constructing the historical data set further comprises:
s21, index standardization step: standardizing indexes in an index system through construction of an alias system;
s22, data acquisition step: collecting historical patient case data according to indexes in an index system;
s23, data set construction: a historical data set is constructed from the patient historical case data.
In particular, the patient historical case data that the general surgery needs to collect includes two parts, surgical general purpose indicators and general surgery specific indicators. Wherein the surgical commonality indicators include: age, sex, BMI, white blood cells, hemoglobin, platelet count, PT, APTT, D-dimer, albumin, prealbumin, ALT, AST, Cr, BUN, PO2、PCO2pH, HCO3-BE, oxygen saturation, triglycerides, total cholesterol, low density lipoprotein, thyroxine, potassium, BNP, hypersensitive troponin-I, arrhythmia, atrial fibrillation, premature beats, conduction block, ST ischemic manifestations, EF, pulmonary arterial pressure, valve regurgitation, segmental dyskinesia of the ventricular wall, low density or brain softening foci, emphysema, bullous bullae, hypertension, whether hypertension requires drug therapy, coronary heart disease, whether stenting, fasting plasma glucose, glycated hemoglobin, cerebral hemorrhage, cerebral thrombosis, rheumatic immune system, hormonal use, asthma, bronchitis, whether dialysis is performed, acute renal failure, smoking duration, whether smoking cessation, smoking duration, alcohol consumption duration, alcohol withdrawal, abstinence from alcoholAge, anticoagulant, hormone, chemotherapeutic agent, use of mobility assistance, cognitive status at registration, status at home, palliative treatment at admission, history of falls, functional status, ASA classification, NRS2002 (nutritional risk screening score), admission capacity, ascites within 30 days prior to surgery, systemic sepsis occurring 48 hours prior to surgery, congestive heart failure 30 days prior to surgery, severe COPD history, dyspnea, admission to hospital due to malignant tumor, whether there is an invasion of adjacent organs (tissues), degree of tumor differentiation, diffuse cancer, type of surgery, name of surgery, surgical indication, whether or not there is an emergency surgery, whether or not there is shock, whether or not there is a history of use of life support, mode of anesthesia, whether or not radiochemotherapy is performed, type of surgical incision, acute myocardial infarction, Killip classification, number of days of hospitalization, death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, cerebral hemorrhage, cerebral, Respiratory failure, pneumonia, lower limb deep vein thrombosis, anastomotic fistula, renal failure, postoperative delirium, unplanned reoperation, etc. The specific indexes of general surgery include CT angiography, ultrasound, fibrinogen, antithrombin III, rectal MR, abdominal enhanced CT, indocyanine green excretion test, alpha-fetoprotein, thyroid ultrasound, parathyroid hormone, Jiagong, mammary gland ultrasound molybdenum target, mammary gland magnetic resonance and the like.
S3, data preprocessing: data in the historical dataset is preprocessed.
Specifically, the method for preprocessing the data in the historical data set comprises the following steps: the method comprises the steps of carrying out data structuring processing, missing value processing and error value processing on data in a historical data set, and then carrying out standardization processing, wherein the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of the qualitative characteristics into the quantitative characteristics by means of dummy coding and data transformation processing.
S4, characteristic engineering step: and extracting indexes meeting a set threshold value through a feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set.
Specifically, the method for extracting the index in the historical data set comprises the following steps:
s41, feature selection: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
s42, feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
S5, constructing a risk prediction model: and establishing a risk prediction model by taking the data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a base model.
S6, a case data set construction step: and establishing a case data set according to preoperative information of a patient to be evaluated.
Specifically, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information, and a patient medical record home page.
S7, assessment of preoperative risk of patients: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
Example 5: a preoperative risk assessment method for urology surgery comprises the following steps:
s1, forming an index system: determining main indexes of urological operation complication evaluation according to the urological operation relevant guidelines and urological case data, and forming an index system according to the main indexes; the main indicators include indicators related to complications of urology surgery and the name of the complications.
Specifically, the urological surgery-related guidelines employ prevention and treatment of urological complications (seminal), urological complications-diagnosis, prevention and treatment, general surgical disease diagnosis and treatment guidelines (3 rd edition), prevention guidelines for surgical site infections (2017).
Specifically, the corresponding complication index of the urological operation comprises a general index and a urological operation specific index. Wherein, the universality index comprises: death, cardiovascular accidents, cerebrovascular accidents, respiratory failure, pulmonary embolism, pneumonia, limb thrombotic complications, anastomotic fistulas, incision infections, incision dehiscence, organ space infections, systemic sepsis, urinary system infections, renal failure, intraoperative hemorrhage, unplanned reoperation, postoperative delirium, functional decline, use of traffic aids, pressure ulcer progression. Urological procedure specific indicators include: urethral stricture, ureteral stricture, urinary tract infection, etc.
S2, historical data set construction step: and establishing a historical data set according to the historical patient case data collected by the indexes in the index system.
Specifically, the step of constructing the historical data set further comprises:
s21, index standardization step: standardizing indexes in an index system through construction of an alias system;
s22, data acquisition step: collecting historical patient case data according to indexes in an index system;
s23, data set construction: a historical data set is constructed from the patient historical case data.
Specifically, the patient historical case data that the urological procedure requires to collect includes both surgical commonality indicators and urological procedure-specific indicators. Wherein the surgical commonality indicators include: age, sex, BMI, white blood cells, hemoglobin, platelet count, PT, APTT, D-dimer, albumin, prealbumin, ALT, AST, Cr, BUN, PO2、PCO2pH, HCO3-BE, oxygen saturation, triglycerides, total cholesterol, low density lipoprotein, potassium, BNP, hypersensitive troponin-I, arrhythmia, atrial fibrillation, premature beats, conduction block, ST ischemic manifestations, EF, pulmonary arterial pressure, valve regurgitation, segmental dyskinesia of the ventricular wall, hypodense or softened foci of the brain, emphysema, bullous lung, hypertension, whether hypertension requires drug therapy, coronary heart disease, whether stents, fasting plasma glucose, glycated hemoglobin, cerebral hemorrhage, cerebral thrombosis, the rheumatic immune system, hormonal use, asthma, bronchitis, whether dialysis, acute renal failure, smoking duration, whether smoking cessation, smoking duration, alcohol consumption duration, alcohol withdrawal, alcohol consumption duration, anticoagulant, hormone, chemotherapeutic agent, use of mobility assistance, cognitive state at enrollment, state at home, palliative therapy at admission, state at home, and the like, Drop history, functional status, ASA grade, NRS2002 (nutritional risk screening score), admission capacity, ascites within 30 days prior to surgery, systemic sepsis occurring 48 hours prior to surgery, congestive heart failure 30 days prior to surgery, severe COPD history, dyspnea, whether admitted to the hospital due to a malignant tumor, whether there is an invasion of adjacent organs (tissues), degree of tumor differentiation, diffuse cancer, type of surgery, name of surgery, surgical indication, whether emergency surgery, whether shock, whether there is a history of using life support, anesthesia modality, the indications of chemotherapy, type of operative incision, acute myocardial infarction, Killip grading, days of hospitalization, death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, pulmonary embolism, lower limb deep vein thrombosis, anastomotic fistula, renal failure, bleeding in operative area, postoperative delirium, unplanned reoperation, etc. The specific indexes of the urinary surgery include leucocytes, erythrocytes, prostate specific antigen and the like.
S3, data preprocessing: data in the historical dataset is preprocessed.
Specifically, the method for preprocessing the data in the historical data set comprises the following steps: the method comprises the steps of carrying out data structuring processing, missing value processing and error value processing on data in a historical data set, and then carrying out standardization processing, wherein the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of the qualitative characteristics into the quantitative characteristics by means of dummy coding and data transformation processing.
S4, characteristic engineering step: and extracting indexes meeting a set threshold value through a feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set.
Specifically, the method for extracting the index in the historical data set comprises the following steps:
s41, feature selection: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
s42, feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
S5, constructing a risk prediction model: and establishing a risk prediction model by taking the data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a base model.
S6, a case data set construction step: and establishing a case data set according to preoperative information of a patient to be evaluated.
Specifically, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information, and a patient medical record home page.
S7, assessment of preoperative risk of patients: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
Example 6: a preoperative risk assessment method for neurosurgery comprises the following steps:
s1, forming an index system: determining main indexes of neurosurgical operation complication evaluation according to the neurosurgical operation related guidelines and neurosurgical case data, and forming an index system according to the main indexes; the primary indicators include indicators related to neurosurgical complications and complication names.
Specifically, the guidance related to neurosurgery adopts the consensus of neurosurgical perioperative bleeding prevention and treatment experts (2018), the consensus of Chinese neurosurgical intensive care management experts (2020 edition), the diagnosis and treatment guidance of common surgical diseases (3 rd edition), and the prevention guidance of surgical site infection (2017).
Specifically, the neurosurgical corresponding complication index includes a general index and a neurosurgical specific index. Wherein, the universality index comprises: death, cardiovascular accidents, cerebrovascular accidents, respiratory failure, pulmonary embolism, pneumonia, limb thrombotic complications, anastomotic fistulas, incision infections, incision dehiscence, organ space infections, systemic sepsis, urinary system infections, renal failure, intraoperative hemorrhage, unplanned reoperation, postoperative delirium, functional decline, use of traffic aids, pressure ulcer progression. Neurosurgical specific indices include: abnormalities in C-reactive protein (CRP) and white blood cell count (WBC), increased intracranial pressure, cerebral hernia, and the like.
S2, historical data set construction step: and establishing a historical data set according to the historical patient case data collected by the indexes in the index system.
Specifically, the step of constructing the historical data set further comprises:
s21, index standardization step: standardizing indexes in an index system through construction of an alias system;
s22, data acquisition step: collecting historical patient case data according to indexes in an index system;
s23, data set construction: a historical data set is constructed from the patient historical case data.
Specifically, the patient history case data collected by neurosurgery includes two parts of a general surgical index and a neurosurgical specific index. Wherein the surgical commonality indicators include: age, sex, BMI, white blood cells, hemoglobin, platelet count, PT, APTT, D-dimer, albumin, prealbumin, ALT, AST, Cr, BUN, PO2、PCO2pH, HCO3-BE, oxygen saturation, triglycerides, total cholesterol, low density lipoprotein, potassium, BNP, hypersensitive troponin-I, arrhythmia, atrial fibrillation, premature beats, conduction block, ST ischemic manifestations, EF, pulmonary arterial pressure, valve regurgitation, segmental dyskinesia of the ventricular wall, hypodense or softened foci of the brain, emphysema, bullous lung, hypertension, whether hypertension requires drug therapy, coronary heart disease, whether stents, fasting plasma glucose, glycated hemoglobin, cerebral hemorrhage, cerebral thrombosis, the rheumatic immune system, hormonal use, asthma, bronchitis, whether dialysis, acute renal failure, smoking duration, whether smoking cessation, smoking duration, alcohol consumption duration, alcohol withdrawal, alcohol consumption duration, anticoagulant, hormone, chemotherapeutic agent, use of mobility assistance, cognitive state at enrollment, state at home, palliative therapy at admission, state at home, and the like, Droping history, functional status, ASA grade, NRS2002 (nutritional risk screening score), admission capacity, ascites within 30 days before surgery, systemic sepsis occurring 48 hours before surgery, congestive heart failure within 30 days before surgery, severe COPD history, dyspnea, admission to hospital due to malignant tumor, whether neighboring organ (tissue) invasion, degree of tumor differentiation, diffuse cancer, type of surgery, name of surgery, surgical indication, whether emergency surgery, whether shock, whether life support history is used, anesthesia pattern, whether chemoradiotherapy is performed, type of surgical incision, acute myocardial infarction, Killip grade, number of hospitalization days, death, cardiac arrest, myocardial infarction, cerebral hemorrhage, cerebral embolism, cerebral infarction, respiratory failure, pneumonia, pulmonary embolism, deep vein thrombosis of lower extremities, kissFistula, renal failure, hemorrhage in operative area, delirium after operation, and unplanned reoperation. Neurosurgical specific indices include glasgow coma score, craniocerebral CT, muscle strength, headache, vomiting, optic nerve head edema, and the like.
S3, data preprocessing: data in the historical dataset is preprocessed.
Specifically, the method for preprocessing the data in the historical data set comprises the following steps: the method comprises the steps of carrying out data structuring processing, missing value processing and error value processing on data in a historical data set, and then carrying out standardization processing, wherein the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of the qualitative characteristics into the quantitative characteristics by means of dummy coding and data transformation processing.
S4, characteristic engineering step: and extracting indexes meeting a set threshold value through a feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set.
Specifically, the method for extracting the index in the historical data set comprises the following steps:
s41, feature selection: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
s42, feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
S5, constructing a risk prediction model: and establishing a risk prediction model by taking the data in the new history data set obtained in the characteristic engineering step as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a base model.
S6, a case data set construction step: and establishing a case data set according to preoperative information of a patient to be evaluated.
Specifically, the preoperative information includes patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information, and a patient medical record home page.
S7, assessment of preoperative risk of patients: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
The above-described embodiments are intended to illustrate rather than to limit the invention, and any modifications and variations of the present invention are possible within the spirit and scope of the claims.
Claims (9)
1. A preoperative risk assessment method, comprising the steps of:
forming an index system: determining main indexes of the surgical complication evaluation according to the relevant surgical guide and the surgical case data, and forming an index system according to the main indexes; the primary indicators include indicators related to surgical complications and complication names;
and (3) constructing a historical data set: establishing a historical data set according to historical patient case data collected by indexes in an index system;
a data preprocessing step: preprocessing data in the historical data set;
characteristic engineering steps: extracting indexes meeting a set threshold value through feature engineering according to the preprocessed historical data set, and forming a new historical data set according to the extracted indexes and other data in the historical data set; constructing a risk prediction model: establishing a risk prediction model by taking data in the new history data set obtained in the characteristic engineering step as input, taking various complications in an index system as output and taking an integrated supervised learning algorithm model as a base model;
and (3) constructing a case data set: establishing a case data set according to preoperative information of a patient to be evaluated;
a patient preoperative risk assessment step: and inputting preoperative information in the case data set into the risk prediction model, judging the probability of occurrence of each complication of the patient through the risk prediction model, and comparing the probability with the probability of occurrence of the complication in the clinical surgical operation to form a risk assessment report for reference of doctors and patients.
2. The method of pre-surgical risk assessment according to claim 1, wherein the step of constructing a historical data set further comprises:
and (3) index standardization step: standardizing indexes in an index system through construction of an alias system;
a data acquisition step: collecting historical patient case data according to indexes in an index system;
a data set construction step: a historical data set is constructed from the patient historical case data.
3. The method of risk assessment before surgery according to claim 1 or 2, wherein in the step of constructing the historical data set, the patient historical case data is collected in a manner of patient clinical data derived in a hospital system or directly collected, or patient feedback data output by the risk prediction model.
4. The method of pre-surgical risk assessment according to claim 1, wherein in the step of pre-processing the data, the pre-processing the data in the historical dataset comprises: carrying out data structuring processing, missing value processing and error value processing on data in the historical data set, and then carrying out standardization processing; the standardization processing comprises characteristic dimensionless processing, redundant information processing, binarization processing for dividing effective information sections contained in quantitative characteristics, polynomial processing for quantitative variables, conversion of qualitative characteristics into quantitative characteristics by using a dummy code mode, and data conversion processing.
5. The preoperative risk assessment method of claim 1, wherein in the feature engineering step, the method of extracting indicators in the historical data set is:
a characteristic selection step: removing relatively unimportant features from a plurality of features of an index system by adopting an Embedded method, thereby retaining the important features; under the condition of selecting an integrated model, performing feature selection by using an L1 regular term base model with a penalty term to obtain a weight coefficient of each feature, eliminating an index term with a coefficient of 0, and screening out other nonzero indexes;
a feature generation step: and performing cross assignment on the indexes in the historical data set by a characteristic combination method to generate new characteristics to obtain new indexes and express information which cannot be expressed by the original characteristics, wherein if the importance of the patient complications corresponding to the new indexes is higher than the importance of the patient complications corresponding to any one of the indexes screened in the characteristic selection step, the new indexes are reserved.
6. The method of risk assessment prior to surgery of claim 1, wherein in the step of constructing a case data set, the pre-operative information comprises patient hospitalization information, patient case information, patient exam information, patient diagnosis information, patient ward visit information, patient medical record home page.
7. A preoperative risk assessment system, comprising:
the system comprises an information input module, a clinical reference information and pre-operation information of a patient to be evaluated, wherein the clinical reference information comprises a surgical operation related guide, a knowledge text and surgical case data, and the pre-operation information of the patient to be evaluated comprises patient hospitalization information, patient case information, patient examination information, patient diagnosis information, patient ward-round information and a patient case first page;
the data acquisition module is used for acquiring historical case data of a patient;
the data storage module is used for storing the clinical reference information and the preoperative information of the patient to be evaluated which are input by the information input module and the historical case data of the patient which are acquired by the data acquisition module; forming an index system according to the clinical reference information, forming a historical data set according to historical patient case data collected by indexes in the index system, and forming a case data set according to preoperative information of a patient to be evaluated;
the characteristic engineering module is used for extracting a historical data set from the data storage module and performing characteristic engineering extraction on the historical data set to obtain a new historical data set;
the risk prediction model generation module is used for extracting a new historical data set from the characteristic engineering module, taking data in the new historical data set as input, taking whether complications occur as output and taking the integrated supervised learning algorithm model as a basic model to generate a risk prediction model;
a judgment module; the risk prediction model is used for storing the risk prediction model, extracting preoperative information of a patient to be evaluated, evaluating preoperative risk of the patient to be evaluated through the risk prediction model, predicting the occurrence probability of each complication of the patient, comparing the probability with the occurrence probability of the complication in a clinical surgical operation, and generating a risk evaluation report for reference of doctors and the patient;
and the output module is used for outputting and feeding back the judgment result of the judgment module to the user.
8. The preoperative risk assessment system of claim 7, further comprising an information feedback module for gathering case information of a user after risk assessment has been performed and sending this information to the data storage module as patient historical case data, updating the historical data set.
9. The preoperative risk assessment system of claim 8, further comprising a PC terminal, a mobile terminal APP and a server, wherein the information input module, the data acquisition module, the output module and the information feedback module are installed on the PC terminal and the mobile terminal APP, and the data storage module, the feature engineering module, the risk prediction model generation module and the judgment module are installed in the server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110467774.5A CN113178258A (en) | 2021-04-28 | 2021-04-28 | Preoperative risk assessment method and system for surgical operation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110467774.5A CN113178258A (en) | 2021-04-28 | 2021-04-28 | Preoperative risk assessment method and system for surgical operation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113178258A true CN113178258A (en) | 2021-07-27 |
Family
ID=76926892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110467774.5A Pending CN113178258A (en) | 2021-04-28 | 2021-04-28 | Preoperative risk assessment method and system for surgical operation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113178258A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639478A (en) * | 2022-03-09 | 2022-06-17 | 曜立科技(北京)有限公司 | Ultrasonic monitoring system based on valvular heart disease |
| CN114783607A (en) * | 2022-05-10 | 2022-07-22 | 中南大学湘雅医院 | Surgical blood transfusion risk prediction model and construction method of network calculator thereof |
| CN114913982A (en) * | 2022-07-18 | 2022-08-16 | 之江实验室 | End-stage renal disease complication risk prediction system based on contrast learning |
| CN116665910A (en) * | 2023-06-01 | 2023-08-29 | 曜立科技(北京)有限公司 | Neural intervention operation risk assessment system based on big data analysis |
| CN116825356A (en) * | 2023-07-12 | 2023-09-29 | 中国医学科学院基础医学研究所 | Multi-association surgery complication risk assessment method, system and computing equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109285024A (en) * | 2018-07-23 | 2019-01-29 | 北京三快在线科技有限公司 | Online feature determines method, apparatus, electronic equipment and storage medium |
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN111524598A (en) * | 2020-04-21 | 2020-08-11 | 赵述武 | Perioperative complication prediction method and system |
| CN111899866A (en) * | 2020-07-28 | 2020-11-06 | 四川大学华西医院 | Surgical operation complication evaluation system based on deep learning |
| CN111931809A (en) * | 2020-06-29 | 2020-11-13 | 北京大米科技有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN112017783A (en) * | 2020-09-14 | 2020-12-01 | 华中科技大学同济医学院附属协和医院 | Prediction model for pulmonary infection after heart operation and construction method thereof |
-
2021
- 2021-04-28 CN CN202110467774.5A patent/CN113178258A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109285024A (en) * | 2018-07-23 | 2019-01-29 | 北京三快在线科技有限公司 | Online feature determines method, apparatus, electronic equipment and storage medium |
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN111524598A (en) * | 2020-04-21 | 2020-08-11 | 赵述武 | Perioperative complication prediction method and system |
| CN111931809A (en) * | 2020-06-29 | 2020-11-13 | 北京大米科技有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN111899866A (en) * | 2020-07-28 | 2020-11-06 | 四川大学华西医院 | Surgical operation complication evaluation system based on deep learning |
| CN112017783A (en) * | 2020-09-14 | 2020-12-01 | 华中科技大学同济医学院附属协和医院 | Prediction model for pulmonary infection after heart operation and construction method thereof |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639478A (en) * | 2022-03-09 | 2022-06-17 | 曜立科技(北京)有限公司 | Ultrasonic monitoring system based on valvular heart disease |
| CN114639478B (en) * | 2022-03-09 | 2023-01-10 | 曜立科技(北京)有限公司 | Ultrasonic monitoring system based on valvular heart disease |
| CN114783607A (en) * | 2022-05-10 | 2022-07-22 | 中南大学湘雅医院 | Surgical blood transfusion risk prediction model and construction method of network calculator thereof |
| CN114913982A (en) * | 2022-07-18 | 2022-08-16 | 之江实验室 | End-stage renal disease complication risk prediction system based on contrast learning |
| US11875882B1 (en) | 2022-07-18 | 2024-01-16 | Zhejiang Lab | System for predicting end-stage renal disease complication risk based on contrastive learning |
| CN116665910A (en) * | 2023-06-01 | 2023-08-29 | 曜立科技(北京)有限公司 | Neural intervention operation risk assessment system based on big data analysis |
| CN116825356A (en) * | 2023-07-12 | 2023-09-29 | 中国医学科学院基础医学研究所 | Multi-association surgery complication risk assessment method, system and computing equipment |
| CN116825356B (en) * | 2023-07-12 | 2024-02-06 | 中国医学科学院基础医学研究所 | Multi-association surgery complication risk assessment method, system and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113178258A (en) | Preoperative risk assessment method and system for surgical operation | |
| Fernandez et al. | The Society of Thoracic Surgeons and the European Society of Thoracic Surgeons general thoracic surgery databases: joint standardization of variable definitions and terminology | |
| US20050043614A1 (en) | Automated methods and systems for vascular plaque detection and analysis | |
| Whitson et al. | Increasing numbers of rib fractures do not worsen outcome: an analysis of the national trauma data bank | |
| CN114121278A (en) | Prediction model of AKI risk after heart valve replacement based on age and clinical index | |
| Vawter et al. | Complications and failure-to-rescue after pancreatectomy and hospital participation in the targeted American College of Surgeons National Surgical Quality Improvement Program registry | |
| Detrano et al. | Computer probability estimates of angiographic coronary artery disease: Transportability and comparison with cardiologists' estimates | |
| Xie et al. | A simple nomogram for predicting early complications in patients after primary knee arthroplasty | |
| CN115479934A (en) | Aortic dissection joint prognosis evaluation system based on marker and imaging | |
| CN113053534A (en) | Predictive analysis method for complicated pulmonary embolism of lower limb deep venous thrombosis patient | |
| Lake | Assessment of the emergency surgical patient | |
| Lopez et al. | Using machine learning methods to predict prolonged operative time in elective total shoulder arthroplasty | |
| Fu et al. | Analysis of the occurrence of acute pulmonary embolism in the icu ward and related risk factors predicting its severity | |
| Pinto et al. | Preoperative evaluation of the patient with cardiorespiratory diseases | |
| Xu et al. | Machine learning for predicting hemodynamic deterioration of patients with intermediate-risk pulmonary embolism in intensive care unit | |
| RU2735996C1 (en) | Method for predicting development of pulmonary hypertension at the end of subacute myocardial infarction in men younger than 60 years old | |
| RU2788285C1 (en) | Method for determination of probability of lethal outcome at hospital stage after coronary bypass surgery | |
| Wood et al. | Additive value of invasive haemodynamic assessment for predicting post-operative outcomes after Fontan | |
| Tracy et al. | Calcium phosphate content does not affect stone-free rate after percutaneous nephrolithotomy | |
| Qu | Engineering a Large Matched MIMIC-III ICU Waveform Dataset with Clinical Covariates to Determine the Association Between Hemodynamic Variables and Acute Kidney Injury | |
| Craig et al. | Perioperative risk models: a narrative review | |
| Pinto et al. | Preoperative evaluation of the patient with cardiorespiratory diseases | |
| Saric | The prognostic capabilities of a preoperative six-minute walk test to inform cardiovascular risk after noncardiac surgery: a pragmatic prospective cohort study. | |
| Mercer et al. | P-OGC89 Peri-operative blood use in Upper GI surgery | |
| CN114334064A (en) | Patient access model construction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210727 |