CN116682552B - Strong interpretation characteristic hemodialysis hypotension prediction method for multi-time span data - Google Patents
Strong interpretation characteristic hemodialysis hypotension prediction method for multi-time span data Download PDFInfo
- Publication number
- CN116682552B CN116682552B CN202310956821.1A CN202310956821A CN116682552B CN 116682552 B CN116682552 B CN 116682552B CN 202310956821 A CN202310956821 A CN 202310956821A CN 116682552 B CN116682552 B CN 116682552B
- Authority
- CN
- China
- Prior art keywords
- hypotension
- feature
- hemodialysis
- data
- dialysis
- 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.)
- Active
Links
- 208000001953 Hypotension Diseases 0.000 title claims abstract description 107
- 230000036543 hypotension Effects 0.000 title claims abstract description 105
- 238000001631 haemodialysis Methods 0.000 title claims abstract description 68
- 230000000322 hemodialysis Effects 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000000502 dialysis Methods 0.000 claims description 64
- 230000006870 function Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000010187 selection method Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 10
- 208000025174 PANDAS Diseases 0.000 claims description 7
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 claims description 7
- 240000004718 Panda Species 0.000 claims description 7
- 235000016496 Panda oleosa Nutrition 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 230000004931 aggregating effect Effects 0.000 claims description 6
- 230000004872 arterial blood pressure Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000010339 medical test Methods 0.000 claims description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 7
- 201000010099 disease Diseases 0.000 description 6
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000035515 penetration Effects 0.000 description 5
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 4
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 4
- 208000020372 Infective dermatitis associated with HTLV-1 Diseases 0.000 description 4
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 239000008280 blood Substances 0.000 description 4
- 230000037396 body weight Effects 0.000 description 4
- 239000011575 calcium Substances 0.000 description 4
- 229910052791 calcium Inorganic materials 0.000 description 4
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 4
- 210000003743 erythrocyte Anatomy 0.000 description 4
- 239000011780 sodium chloride Substances 0.000 description 4
- 102000001554 Hemoglobins Human genes 0.000 description 3
- 108010054147 Hemoglobins Proteins 0.000 description 3
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 3
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 3
- LEHOTFFKMJEONL-UHFFFAOYSA-N Uric Acid Chemical compound N1C(=O)NC(=O)C2=C1NC(=O)N2 LEHOTFFKMJEONL-UHFFFAOYSA-N 0.000 description 3
- TVWHNULVHGKJHS-UHFFFAOYSA-N Uric acid Natural products N1C(=O)NC(=O)C2NC(=O)NC21 TVWHNULVHGKJHS-UHFFFAOYSA-N 0.000 description 3
- 210000003651 basophil Anatomy 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 3
- 230000015271 coagulation Effects 0.000 description 3
- 238000005345 coagulation Methods 0.000 description 3
- 238000006297 dehydration reaction Methods 0.000 description 3
- 230000035487 diastolic blood pressure Effects 0.000 description 3
- 238000005534 hematocrit Methods 0.000 description 3
- 208000015181 infectious disease Diseases 0.000 description 3
- 150000002500 ions Chemical class 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000011574 phosphorus Substances 0.000 description 3
- 229910052698 phosphorus Inorganic materials 0.000 description 3
- 239000011591 potassium Substances 0.000 description 3
- 229910052700 potassium Inorganic materials 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000011734 sodium Substances 0.000 description 3
- 229910052708 sodium Inorganic materials 0.000 description 3
- 230000035488 systolic blood pressure Effects 0.000 description 3
- 238000011282 treatment Methods 0.000 description 3
- 229940116269 uric acid Drugs 0.000 description 3
- 108010088751 Albumins Proteins 0.000 description 2
- 102000009027 Albumins Human genes 0.000 description 2
- BPYKTIZUTYGOLE-IFADSCNNSA-N Bilirubin Chemical compound N1C(=O)C(C)=C(C=C)\C1=C\C1=C(C)C(CCC(O)=O)=C(CC2=C(C(C)=C(\C=C/3C(=C(C=C)C(=O)N\3)C)N2)CCC(O)=O)N1 BPYKTIZUTYGOLE-IFADSCNNSA-N 0.000 description 2
- 241001631457 Cannula Species 0.000 description 2
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 2
- 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 2
- 206010018852 Haematoma Diseases 0.000 description 2
- JVTAAEKCZFNVCJ-UHFFFAOYSA-M Lactate Chemical compound CC(O)C([O-])=O JVTAAEKCZFNVCJ-UHFFFAOYSA-M 0.000 description 2
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 description 2
- 102000003982 Parathyroid hormone Human genes 0.000 description 2
- 108090000445 Parathyroid hormone Proteins 0.000 description 2
- 102000004338 Transferrin Human genes 0.000 description 2
- 108090000901 Transferrin Proteins 0.000 description 2
- XSQUKJJJFZCRTK-UHFFFAOYSA-N Urea Chemical compound NC(N)=O XSQUKJJJFZCRTK-UHFFFAOYSA-N 0.000 description 2
- PNNCWTXUWKENPE-UHFFFAOYSA-N [N].NC(N)=O Chemical compound [N].NC(N)=O PNNCWTXUWKENPE-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 102000015736 beta 2-Microglobulin Human genes 0.000 description 2
- 108010081355 beta 2-Microglobulin Proteins 0.000 description 2
- 238000004820 blood count Methods 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 239000004202 carbamide Substances 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 2
- 239000001569 carbon dioxide Substances 0.000 description 2
- 239000000460 chlorine Substances 0.000 description 2
- 229910052801 chlorine Inorganic materials 0.000 description 2
- 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 2
- 229940109239 creatinine Drugs 0.000 description 2
- 230000018044 dehydration Effects 0.000 description 2
- 230000003205 diastolic effect Effects 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000003979 eosinophil Anatomy 0.000 description 2
- OVBPIULPVIDEAO-LBPRGKRZSA-N folic acid Chemical compound C=1N=C2NC(N)=NC(=O)C2=NC=1CNC1=CC=C(C(=O)N[C@@H](CCC(O)=O)C(O)=O)C=C1 OVBPIULPVIDEAO-LBPRGKRZSA-N 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 208000021822 hypotensive Diseases 0.000 description 2
- 230000001077 hypotensive effect Effects 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 210000004698 lymphocyte Anatomy 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000011777 magnesium Substances 0.000 description 2
- 229910052749 magnesium Inorganic materials 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 210000001616 monocyte Anatomy 0.000 description 2
- 210000000440 neutrophil Anatomy 0.000 description 2
- 239000000199 parathyroid hormone Substances 0.000 description 2
- 229960001319 parathyroid hormone Drugs 0.000 description 2
- 230000037361 pathway Effects 0.000 description 2
- 230000008823 permeabilization Effects 0.000 description 2
- 210000001995 reticulocyte Anatomy 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 210000002966 serum Anatomy 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000012581 transferrin Substances 0.000 description 2
- HSINOMROUCMIEA-FGVHQWLLSA-N (2s,4r)-4-[(3r,5s,6r,7r,8s,9s,10s,13r,14s,17r)-6-ethyl-3,7-dihydroxy-10,13-dimethyl-2,3,4,5,6,7,8,9,11,12,14,15,16,17-tetradecahydro-1h-cyclopenta[a]phenanthren-17-yl]-2-methylpentanoic acid Chemical compound C([C@@]12C)C[C@@H](O)C[C@H]1[C@@H](CC)[C@@H](O)[C@@H]1[C@@H]2CC[C@]2(C)[C@@H]([C@H](C)C[C@H](C)C(O)=O)CC[C@H]21 HSINOMROUCMIEA-FGVHQWLLSA-N 0.000 description 1
- 102000034279 3-hydroxybutyrate dehydrogenases Human genes 0.000 description 1
- 108090000124 3-hydroxybutyrate dehydrogenases Proteins 0.000 description 1
- 102000006267 AMP Deaminase Human genes 0.000 description 1
- 108700016228 AMP deaminases Proteins 0.000 description 1
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 description 1
- 108010082126 Alanine transaminase Proteins 0.000 description 1
- 102000002260 Alkaline Phosphatase Human genes 0.000 description 1
- 108020004774 Alkaline Phosphatase Proteins 0.000 description 1
- BVKZGUZCCUSVTD-UHFFFAOYSA-M Bicarbonate Chemical compound OC([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-M 0.000 description 1
- 108010074051 C-Reactive Protein Proteins 0.000 description 1
- 102100032752 C-reactive protein Human genes 0.000 description 1
- 102000055006 Calcitonin Human genes 0.000 description 1
- 108060001064 Calcitonin Proteins 0.000 description 1
- 102000003914 Cholinesterases Human genes 0.000 description 1
- 108090000322 Cholinesterases Proteins 0.000 description 1
- 238000008789 Direct Bilirubin Methods 0.000 description 1
- 102000008857 Ferritin Human genes 0.000 description 1
- 108050000784 Ferritin Proteins 0.000 description 1
- 238000008416 Ferritin Methods 0.000 description 1
- 206010016717 Fistula Diseases 0.000 description 1
- 108020004206 Gamma-glutamyltransferase Proteins 0.000 description 1
- 102000006395 Globulins Human genes 0.000 description 1
- 108010044091 Globulins Proteins 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- HTTJABKRGRZYRN-UHFFFAOYSA-N Heparin Chemical compound OC1C(NC(=O)C)C(O)OC(COS(O)(=O)=O)C1OC1C(OS(O)(=O)=O)C(O)C(OC2C(C(OS(O)(=O)=O)C(OC3C(C(O)C(O)C(O3)C(O)=O)OS(O)(=O)=O)C(CO)O2)NS(O)(=O)=O)C(C(O)=O)O1 HTTJABKRGRZYRN-UHFFFAOYSA-N 0.000 description 1
- 102000008133 Iron-Binding Proteins Human genes 0.000 description 1
- 108010035210 Iron-Binding Proteins Proteins 0.000 description 1
- OVBPIULPVIDEAO-UHFFFAOYSA-N N-Pteroyl-L-glutaminsaeure Natural products C=1N=C2NC(N)=NC(=O)C2=NC=1CNC1=CC=C(C(=O)NC(CCC(O)=O)C(O)=O)C=C1 OVBPIULPVIDEAO-UHFFFAOYSA-N 0.000 description 1
- 108020001621 Natriuretic Peptide Proteins 0.000 description 1
- 102000004571 Natriuretic peptide Human genes 0.000 description 1
- 102000007584 Prealbumin Human genes 0.000 description 1
- 108010071690 Prealbumin Proteins 0.000 description 1
- 208000007536 Thrombosis Diseases 0.000 description 1
- 238000008050 Total Bilirubin Reagent Methods 0.000 description 1
- 206010048629 Wound secretion Diseases 0.000 description 1
- 239000003146 anticoagulant agent Substances 0.000 description 1
- 229940127219 anticoagulant drug Drugs 0.000 description 1
- 239000003613 bile acid Substances 0.000 description 1
- 239000011230 binding agent Substances 0.000 description 1
- BBBFJLBPOGFECG-VJVYQDLKSA-N calcitonin Chemical compound N([C@H](C(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CO)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CCC(O)=O)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CC=1NC=NC=1)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CC=1C=CC(O)=CC=1)C(=O)N1[C@@H](CCC1)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)NCC(=O)N[C@@H](CO)C(=O)NCC(=O)N[C@@H]([C@@H](C)O)C(=O)N1[C@@H](CCC1)C(N)=O)C(C)C)C(=O)[C@@H]1CSSC[C@H](N)C(=O)N[C@@H](CO)C(=O)N[C@@H](CC(N)=O)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CO)C(=O)N[C@@H]([C@@H](C)O)C(=O)N1 BBBFJLBPOGFECG-VJVYQDLKSA-N 0.000 description 1
- 229960004015 calcitonin Drugs 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 229940048961 cholinesterase Drugs 0.000 description 1
- 208000020832 chronic kidney disease Diseases 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 208000028208 end stage renal disease Diseases 0.000 description 1
- 201000000523 end stage renal failure Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000003890 fistula Effects 0.000 description 1
- 229960000304 folic acid Drugs 0.000 description 1
- 235000019152 folic acid Nutrition 0.000 description 1
- 239000011724 folic acid Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 102000006640 gamma-Glutamyltransferase Human genes 0.000 description 1
- -1 hbA1C Substances 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 229960002897 heparin Drugs 0.000 description 1
- 229920000669 heparin Polymers 0.000 description 1
- 238000011221 initial treatment Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000003908 liver function Effects 0.000 description 1
- 239000003055 low molecular weight heparin Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000000692 natriuretic peptide Substances 0.000 description 1
- 208000001297 phlebitis Diseases 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000028327 secretion Effects 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 150000003626 triacylglycerols Chemical class 0.000 description 1
- 238000000108 ultra-filtration Methods 0.000 description 1
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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- External Artificial Organs (AREA)
Abstract
The invention provides a strong interpretation characteristic hemodialysis hypotension prediction method of multi-time span data, which comprises the steps of obtaining hemodialysis hypotension data, preprocessing the hemodialysis hypotension data, and obtaining a first characteristic set; constructing a second feature set with clinical significance; performing feature selection on the first feature set and the second feature set by utilizing a pre-constructed GS-RFE-XGBoost model; and carrying out characteristic interpretable analysis on the result of characteristic selection by using a xilipendability interpretation method, and predicting the range of the hypotension related factor reference interval by using a percentile. By the method provided by the invention, the strong interpretation prediction of hemodialysis hypotension can be realized.
Description
Technical Field
The invention belongs to the field of machine learning.
Background
Maintenance hemodialysis is the primary treatment for end stage renal patients, and currently 60 tens of thousands are receiving this treatment. Patients with end stage renal disease typically undergo three treatments per week, which is a significant challenge to the blood circulation system. There are various complications during the treatment, among which hypotension in hemodialysis (Intradialytic hypotension, IDH) is the most common and serious, affecting the long-term prognosis of uremic patients. Hypotension is often associated with long-term negative consequences, including increased incidence of heart disease and total cause mortality. The prevalence of IDH varies from 8% to 40% in different studies.
Since the standard of hemodialysis hypotension is not uniformly defined at present, the difficulty in predicting the relevant factors of hypotension is high. Furthermore, the cardiovascular and uremic mechanisms of IDH are complex and there are other causes that can also lead to hypotension, and thus it is difficult to predict the interactions of factors related to hemodialysis hypotension. In addition, the model for predicting hypotension has weak interpretability and has weak clinical substantial assistance to doctors.
The existing methods for predicting hemodialysis hypotension by using machine learning technology mainly comprise the following two methods: 1) A hypotension prediction method with single prediction model features. 2) Hypotension related characteristic prediction method only with correlation research
The method for predicting the hypotension in the scheme 1) can not comprehensively grasp the disease action principle of hemodialysis hypotension due to single selected characteristics, so that misjudgment on factors related to the action mechanism of the hypotension disease is caused, and the accuracy of a hypotension prediction result is low. The method of the scheme 2) has weak clinical interpretability and has little practical significance to clinic due to the fact that the method only has relevant factor analysis. In the clinic of doctors, a reference interval for medical examination is required to be used as an important guarantee for guiding the doctors to diagnose and take medicines.
In summary, in the present stage of the scenario of predicting hemodialysis hypotension, most of the research works only perform feature analysis of single feature-related factors, which cannot achieve the purpose of predicting hemodialysis hypotension by using analysis of factors related to the actual disease mechanism of hypotension, and have little effect on the actual medical clinical scenario. In the research using the analysis of the related factors, most of the work does not explore the specific numerical relationship between the related factors and the diseases, such as the reference interval between the related factors and the diseases, which can achieve better effect on clinical significance.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, the invention aims to provide a method for predicting hemodialysis hypotension with strong interpretation characteristics of multi-time span data, which is used for realizing the strong interpretation prediction of the hemodialysis hypotension.
To achieve the above object, an embodiment of the first aspect of the present invention provides a method for predicting hemodialysis hypotension with strong interpretation characteristics of multi-time span data, including:
obtaining hemodialysis hypotension data, preprocessing the hemodialysis hypotension data, and obtaining a first characteristic set;
constructing a second feature set with clinical significance;
performing feature selection on the first feature set and the second feature set by utilizing a pre-constructed GS-RFE-XGBoost model;
and carrying out interpretable analysis on the characteristics by using a xilipendability method on the result of the characteristic selection, and predicting the range of the hypotension related factor reference interval by using a percentile.
In addition, a method for predicting hemodialysis hypotension with strong interpretation of multi-time span data according to the above embodiment of the present invention may further have the following additional technical features:
further, in one embodiment of the present invention, before feature selection of the first feature set and the second feature set using a pre-constructed GS-RFE-XGBoost model, the method includes:
and carrying out feature screening on the first feature set by using a feature selection method, and inputting the screened features into a pre-constructed GS-RFE-XGBoost model.
Further, in an embodiment of the present invention, before the feature selection method is used to perform feature screening on the first feature set, the method further includes:
aggregating the hemodialysis hypotension data using a pandas inclusion complex function of Python;
converting the classification value to a numerical value using a mapping function, including converting the classification feature to a digital attribute;
the definition of the hypotension tag is performed according to the guidance of hypotension specialists and the search of documents.
Further, in an embodiment of the present invention, the predicting the range of the hypotension related factor reference interval using the percentile includes:
performing strong interpretation on the obtained important features by using a medical examination reference interval; the obtaining mode of the reference interval comprises the following steps:
normal distribution, including obtaining a reference interval by means of obtaining an average value and a standard deviation; and
the deviant distribution comprises the step of obtaining a reference interval by using the percentile point to obtain intervals of the percentile 2.5 and the percentile 97.5.
To achieve the above object, a second aspect of the present invention provides a hemodialysis hypotension prediction apparatus with strong interpretation characteristics of multi-time span data, comprising:
the acquisition module is used for acquiring hemodialysis hypotension data, preprocessing the hemodialysis hypotension data and acquiring a first characteristic set;
the construction module is used for constructing a second feature set with clinical significance;
the prediction module is used for carrying out feature selection on the first feature set and the second feature set by utilizing a pre-constructed GS-RFE-XGBoost model;
and the analysis module is used for carrying out the interpretable analysis of the characteristics on the result of the characteristic selection by using a xilipendability method and predicting the range of the hypotension related factor reference interval by using the percentile.
Further, in an embodiment of the present invention, the preprocessing module is further configured to:
and carrying out feature screening on the first feature set by using a feature selection method, and inputting the screened features into a pre-constructed GS-RFE-XGBoost model.
Further, in an embodiment of the present invention, the preprocessing module is further configured to:
aggregating the hemodialysis hypotension data using a pandas inclusion complex function of Python;
converting the classification value to a numerical value using a mapping function, including converting the classification feature to a digital attribute;
the definition of the hypotension tag is performed according to the guidance of hypotension specialists and the search of documents.
Further, in an embodiment of the present invention, the analysis module is further configured to:
performing strong interpretation on the obtained important features by using a medical examination reference interval; the obtaining mode of the reference interval comprises the following steps:
normal distribution, including obtaining a reference interval by means of obtaining an average value and a standard deviation; and
the deviant distribution comprises the step of obtaining a reference interval by using the percentile point to obtain intervals of the percentile 2.5 and the percentile 97.5.
To achieve the above object, an embodiment of the third aspect of the present invention provides a computer device, which is characterized by comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a method for predicting hemodialysis hypotension with strong interpretation of multi-time span data as described above when the processor executes the computer program.
To achieve the above object, a fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method for predicting hemodialysis hypotension with strong interpretation of multi-time span data as described above.
According to the strong interpretation feature hemodialysis hypotension prediction method for multi-time span data, provided by the embodiment of the invention, 211 features and 21 constructed features are used for predicting relevant factors, 20 important relevant factors are subjected to relevant analysis by using a Xiali common value method, and a reference interval of the important features is obtained by using percentiles of 2.5 and 97.5, so that the strong interpretation prediction for hemodialysis hypotension can be realized.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic flow chart of a hemodialysis hypotension prediction method with strong interpretation characteristics of multi-time span data according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of data preprocessing according to an embodiment of the present invention.
Fig. 3 is a frequency diagram of different IDH standards according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of data feature processing according to an embodiment of the present invention.
Fig. 5 is a system flowchart corresponding to a method for predicting hemodialysis hypotension with strong interpretation of multi-span features according to an embodiment of the present invention.
Fig. 6 is a schematic flow chart of a hemodialysis hypotension prediction apparatus with multiple time span data strong interpretation features according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The following describes a method for predicting hemodialysis hypotension with a strong interpretation of multi-time span data according to an embodiment of the present invention with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a hemodialysis hypotension prediction method with strong interpretation characteristics of multi-time span data according to an embodiment of the present invention.
As shown in fig. 1, the method for predicting hemodialysis hypotension with strong interpretation characteristics of multi-time span data comprises the following steps:
s101: obtaining hemodialysis hypotension data, preprocessing the hemodialysis hypotension data, and obtaining a first characteristic set;
the medical test was run month by month as time span, the dialysis record was run day by day, the dialysis machine monitoring record was run hour by hour as time span, and the data set was taken as 1173783 dialysis records (including basic information spanning month, day, hour and patient) from 211 features of 837 patients, and finally summarized into the dialysis machine monitoring record for real-time blood pressure monitoring. The specific process is shown in fig. 2.
These 211 features include:
basic information: patient ID, gender, ethnicity, date of birth, height, weight, date of admission, time of first dialysis, home address, work unit, pay-per-view, marital status, occupation, smoking, drinking, vision impairment, age of penetration, primary morbidity;
checking: patient identification, follow-up date, white blood count, red blood cell count, hemoglobin, hematocrit, mean red blood cell volume, mean hemoglobin amount, mean hemoglobin concentration, platelet count, reticulocyte (%), lymphocyte (%), monocyte (%), neutrophil (%), eosinophil (%), basophil (%), reticulocyte, lymphocyte, monocyte, neutrophil, eosinophil, basophil, red blood cell distribution width, platelet distribution width, mean platelet volume, large platelet ratio, platelet hematocrit, erythrocyte sedimentation rate, total protein, albumin, globulin, albumin ratio, glutamic pyruvic transaminase, alkaline phosphatase, cholinesterase, total bile acid Total bilirubin, direct bilirubin, indirect bilirubin, glutamyl transpeptidase, adenylate deaminase, lactate dehydrogenase_02 liver function, hydroxybutyrate dehydrogenase, pre-dialysis creatinine, post-dialysis creatinine, pre-dialysis urea nitrogen, post-dialysis urea nitrogen, pre-dialysis uric acid, post-dialysis uric acid, pre-dialysis potassium, pre-dialysis calcium, pre-dialysis phosphorus, post-dialysis chlorine, pre-dialysis sodium, post-dialysis sodium, pre-dialysis chlorine, post-dialysis phosphorus, post-dialysis potassium, post-dialysis calcium, pre-dialysis magnesium, post-dialysis magnesium, ca P, pre-dialysis carbon dioxide, post-dialysis carbon dioxide, triglycerides, total cholesterol, high density lipoprotein-C, low density lipoprotein-C, very low density lipoprotein-C, blood glucose, 2 hours post-meal blood glucose, hbA1C, parathyroid hormone, serum iron, serum ferritin, total iron binding force, transferrin saturation, transferrin, folic acid, vitB12, pre-permeabilization urea, post-permeabilization urea, dialysis time, urr, dehydration, body weight, KT/V, pre-albumin, C-reactive protein, pre-calcitonin, pre-permeabilization blood beta 2 microglobulin, post-permeabilization blood beta 2 microglobulin, rate of decrease of beta 2-MG, natriuretic peptide precursor, lactate dehydrogenase_26ldh;
dialysis recording: patient ID, dialysis date, bed number, dialyzer, dialysis machine model, dialysis mode, access type, blood flow rate, substitution pattern, total substitution, dialysate temperature, dialysate flow rate, anticoagulant, initial dose, maintenance amount, potassium, calcium, sodium, bicarbonate, saline flush time, saline flush dose, total saline flush, dialysis time, dry body weight, pre-dialysis weight, clothing weight, pre-dialysis net weight, quasi-dehydration, body temperature, pre-dialysis systolic pressure, pre-dialysis diastolic pressure, pre-dialysis pulse, pre-dialysis heart rate, post-dialysis weight, single supermode, dialyzer coagulation level, arterial vessel coagulation level, venous vessel coagulation level, policy, arterial kettle, venous kettle, blood pressure internal fistula true tremolo, skin integrity, skin description, arterial end cause, venous end cause, insufficient flow, hematoma condition, infection, arterial puncture needle, arterial puncture direction, venous puncture needle, venous puncture direction, catheter connection mode, tunnel portal infection cause, secretion, and method of treating a wound secretion description, hematoma condition, thrombus, phlebitis, suture shedding, external medicine, dressing replacement, dressing infection, catheter shedding, shedding reasons, lower machine tube sealing, tube sealing liquid, catheter cavity capacity a, catheter cavity capacity v, distance between catheters and cuff, body weight after penetration, actual dehydration, systolic pressure after penetration, diastolic pressure after penetration and heart rate after penetration;
dialysis machine monitoring information: patient ID, jc_time, dialysis date, monitoring time, body temperature, pulse, systolic pressure, diastolic pressure, blood flow, heparin amount, ultrafiltration amount, conductivity, low molecular heparin, care record, venous pressure, arterial pressure, machine temperature, transmembrane pressure, heparin-free, sodium chloride;
moon knot: patient id, year, month, hypotensor, epo, iron, phosphorus binder, vitd formulation, others, evaluation.
S102: constructing a second feature set with clinical significance;
the index of 18 changes of the medical test ions before and after dialysis and the index of 21 indexes of the average arterial pressure of the weight increase during dialysis are constructed.
S103: performing feature selection on the first feature set and the second feature set by utilizing a pre-constructed GS-RFE-XGBoost model;
further, in one embodiment of the present invention, before feature selection of the first feature set and the second feature set using a pre-constructed GS-RFE-XGBoost model, the method includes:
and carrying out feature screening on the first feature set by using a feature selection method, and inputting the screened features into a pre-constructed GS-RFE-XGBoost model.
Further, in an embodiment of the present invention, before the feature selection method is used to perform feature screening on the first feature set, the method further includes:
aggregating the hemodialysis hypotension data using a pandas inclusion complex function of Python;
converting the classification value to a numerical value using a mapping function, including converting the classification feature to a digital attribute;
the definition of the hypotension tag is performed according to the guidance of hypotension specialists and the search of documents.
Specifically, the present invention uses the pandas inclusion function of Python to aggregate all data, yielding 1173783 dialysis records and 211 features. The dataset contains information of the initial and hemodialysis time during hemodialysis.
The present invention converts the classification value into a numerical value by using a mapping function. For example, the pathway type categories include temporary cannulas, grafted phytovascular fistulae, long term cannulas, direct punctures, and autologous arteriovenous fistulae, which the present invention converts to 1, 2, 3, 4, and 5, respectively. The invention converts 29 classification features in total into digital attributes.
The definition of 8 kinds of hypotensive labels was performed based on the guidance of hypotensive specialists and the search of literature, and only the standard 8 (KDOQI) was paid attention to in consideration of the occurrence frequency of different standards as shown in fig. 3.
And (3) carrying out feature screening on the 211 features by using 4 feature selection methods to obtain 89 features, and training and testing the 89 features. As shown in FIG. 4, the feature selection method performed by the GS-RFE-XGBoost model constructed by the invention performs best.
And selecting the reconstructed features according to a pre-constructed model GS-RFE-XGBoost to obtain 20 features. These 20 features include:
pre-systolic, pre-diastolic, systolic, diastolic, platelet count, pathway type, net pre-dialysis body weight, dialysis machine model, hematocrit, basophils, platelet distribution width, pre-dialysis uric acid, KT/V, parathyroid hormone, pre-dialysis mid-systolic, pre-dialysis mid-diastolic, pre-dialysis post-dialysis systolic, post-dialysis calcium, age of dialysis
S104: and carrying out interpretable analysis on the characteristics by using a xilipendability method on the result of the characteristic selection, and predicting the range of the hypotension related factor reference interval by using a percentile.
Further, in an embodiment of the present invention, the predicting the range of the hypotension related factor reference interval using the percentile includes:
performing strong interpretation on the obtained important features by using a medical examination reference interval; the obtaining mode of the reference interval comprises the following steps:
normal distribution, including obtaining a reference interval by means of obtaining an average value and a standard deviation; and
the deviant distribution comprises the step of obtaining a reference interval by using the percentile point to obtain intervals of the percentile 2.5 and the percentile 97.5.
Fig. 5 is a system flow diagram corresponding to a strongly-explained hemodialysis hypotension prediction method of multi-span features.
According to the strong interpretation feature hemodialysis hypotension prediction method for multi-time span data, provided by the embodiment of the invention, 211 features and 21 constructed features are used for predicting relevant factors, 20 important relevant factors are subjected to relevant analysis by using a Xiali common value method, and a reference interval of the important features is obtained by using percentiles of 2.5 and 97.5, so that the strong interpretation prediction for hemodialysis hypotension can be realized.
Compared with the prior art, the invention has the advantages that:
1) According to the invention, the dialysis record taking the day as the time span, the medical examination record taking the month as the time span are used, and finally the hypotension real-time monitoring is carried out by fusing the dialysis machine monitoring information taking the hour as the time span, so that the comprehensive real-time disease prediction for hypotension by utilizing the data of different time spans is realized for the first time.
2) The invention has 21 constructed features, which are all related to the change of ions before and after hemodialysis, to improve the accuracy of hypotension prediction by 40 percent, and the disease prediction of hypotension is realized for the first time by utilizing the data features of the change of ions before and after hemodialysis.
3) The invention uses the method of the sharp interpretable feature to perform the interpretable analysis of the characteristics aiming at the hypotension prediction model, and uses the percentile to predict the range of the hypotension related factor reference interval, and the obtained hypotension prediction model can be applied to the strong interpretation model prediction of hemodialysis hypotension.
In order to realize the embodiment, the invention also provides a hemodialysis hypotension prediction device with strong interpretation characteristics of multi-time span data.
Fig. 6 is a schematic structural diagram of a hemodialysis hypotension prediction apparatus with multiple time span data strong interpretation features according to an embodiment of the present invention.
As shown in fig. 6, the hemodialysis hypotension prediction apparatus of the strong interpretation feature of the multi-time span data includes: a preprocessing module 100, a construction module 200, a prediction module 300, an analysis module 400, wherein,
the pretreatment module is used for acquiring hemodialysis hypotension data, and carrying out pretreatment on the hemodialysis hypotension data to acquire a first characteristic set;
the construction module is used for constructing a second feature set with clinical significance;
the prediction module is used for carrying out feature selection on the first feature set and the second feature set by utilizing a pre-constructed GS-RFE-XGBoost model;
and the analysis module is used for carrying out the interpretable analysis of the characteristics on the result of the characteristic selection by using a xilipendability method and predicting the range of the hypotension related factor reference interval by using the percentile.
Further, in an embodiment of the present invention, the preprocessing module is further configured to:
and carrying out feature screening on the first feature set by using a feature selection method, and inputting the screened features into a pre-constructed GS-RFE-XGBoost model.
Further, in an embodiment of the present invention, the preprocessing module is further configured to:
aggregating the hemodialysis hypotension data using a pandas inclusion complex function of Python;
converting the classification value to a numerical value using a mapping function, including converting the classification feature to a digital attribute;
the definition of the hypotension tag is performed according to the guidance of hypotension specialists and the search of documents.
Further, in an embodiment of the present invention, the analysis module is further configured to:
performing strong interpretation on the obtained important features by using a medical examination reference interval; the obtaining mode of the reference interval comprises the following steps:
normal distribution, including obtaining a reference interval by means of obtaining an average value and a standard deviation; and
the deviant distribution comprises the step of obtaining a reference interval by using the percentile point to obtain intervals of the percentile 2.5 and the percentile 97.5.
To achieve the above object, an embodiment of the third aspect of the present invention provides a computer device, which is characterized by comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for predicting hemodialysis hypotension with strong interpretation of multi-time span data as described above when executing the computer program.
To achieve the above object, a fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, implements a method for predicting hemodialysis hypotension with strong interpretation of multi-time span data as described above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. A method for predicting hemodialysis hypotension with strong interpretation of multi-time span data, comprising the steps of:
obtaining hemodialysis hypotension data, preprocessing the hemodialysis hypotension data, and obtaining a first characteristic set; the method comprises the steps of obtaining hemodialysis hypotension data, wherein the hemodialysis hypotension data comprises the steps of utilizing a dialysis record with a day as a time span, utilizing a medical examination record with a month as a time span, and carrying out hypotension real-time monitoring by fusing the medical examination record with dialysis machine monitoring information with an hour as the time span;
constructing a second feature set with clinical significance; wherein the constructing of the second feature set with clinical significance comprises constructing indexes of medical test ion change before and after dialysis, and dialysis age, weight increase during dialysis and mean arterial pressure;
performing feature selection on the first feature set and the second feature set by utilizing a pre-constructed GS-RFE-XGBoost model;
and carrying out interpretable analysis on the characteristics by using a xilipendability method on the result of the characteristic selection, and predicting the range of the hypotension related factor reference interval by using a percentile.
2. The method of claim 1, comprising, prior to feature selection of the first feature set and the second feature set using a pre-constructed GS-RFE-XGBoost model:
and carrying out feature screening on the first feature set by using a feature selection method, and inputting the screened features into a pre-constructed GS-RFE-XGBoost model.
3. The method of claim 2, further comprising, prior to feature screening the first feature set using a feature selection method:
aggregating the hemodialysis hypotension data using a pandas inclusion complex function of Python;
converting the classification value to a numerical value using a mapping function, including converting the classification feature to a digital attribute;
the definition of the hypotension tag is performed according to the guidance of hypotension specialists and the search of documents.
4. The method of claim 1, wherein predicting the range of the hypotension related factor reference interval using the percentile comprises:
performing strong interpretation on the obtained important features by using a medical examination reference interval; the obtaining mode of the reference interval comprises the following steps:
normal distribution, including obtaining a reference interval by means of obtaining an average value and a standard deviation; and
the deviant distribution comprises the step of obtaining a reference interval by using the percentile point to obtain intervals of the percentile 2.5 and the percentile 97.5.
5. A multi-time span data strong interpretation feature hemodialysis hypotension prediction apparatus, comprising the following modules:
the pretreatment module is used for acquiring hemodialysis hypotension data, and carrying out pretreatment on the hemodialysis hypotension data to acquire a first characteristic set; the method comprises the steps of obtaining hemodialysis hypotension data, wherein the hemodialysis hypotension data comprises the steps of utilizing a dialysis record with a day as a time span, utilizing a medical examination record with a month as a time span, and carrying out hypotension real-time monitoring by fusing the medical examination record with dialysis machine monitoring information with an hour as the time span;
the construction module is used for constructing a second feature set with clinical significance; wherein the constructing of the second feature set with clinical significance comprises constructing indexes of medical test ion change before and after dialysis, and dialysis age, weight increase during dialysis and mean arterial pressure;
the prediction module is used for carrying out feature selection on the first feature set and the second feature set by utilizing a pre-constructed GS-RFE-XGBoost model;
and the analysis module is used for carrying out the interpretable analysis of the characteristics on the result of the characteristic selection by using a xilipendability method and predicting the range of the hypotension related factor reference interval by using the percentile.
6. The apparatus of claim 5, wherein the preprocessing module is further configured to:
and carrying out feature screening on the first feature set by using a feature selection method, and inputting the screened features into a pre-constructed GS-RFE-XGBoost model.
7. The apparatus of claim 5, wherein the preprocessing module is further configured to:
aggregating the hemodialysis hypotension data using a pandas inclusion complex function of Python;
converting the classification value to a numerical value using a mapping function, including converting the classification feature to a digital attribute;
the definition of the hypotension tag is performed according to the guidance of hypotension specialists and the search of documents.
8. The apparatus of claim 5, wherein the analysis module is further configured to:
performing strong interpretation on the obtained important features by using a medical examination reference interval; the obtaining mode of the reference interval comprises the following steps:
normal distribution, including obtaining a reference interval by means of obtaining an average value and a standard deviation; and
the deviant distribution comprises the step of obtaining a reference interval by using the percentile point to obtain intervals of the percentile 2.5 and the percentile 97.5.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the multi-time span data strong interpretation feature hemodialysis hypotension prediction method of any one of claims 1-4 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements a method for strongly-interpreted characteristic hemodialysis hypotension prediction of multi-time span data according to any one of claims 1-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310956821.1A CN116682552B (en) | 2023-08-01 | 2023-08-01 | Strong interpretation characteristic hemodialysis hypotension prediction method for multi-time span data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310956821.1A CN116682552B (en) | 2023-08-01 | 2023-08-01 | Strong interpretation characteristic hemodialysis hypotension prediction method for multi-time span data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116682552A CN116682552A (en) | 2023-09-01 |
CN116682552B true CN116682552B (en) | 2023-10-24 |
Family
ID=87784034
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310956821.1A Active CN116682552B (en) | 2023-08-01 | 2023-08-01 | Strong interpretation characteristic hemodialysis hypotension prediction method for multi-time span data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116682552B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114550913A (en) * | 2022-02-22 | 2022-05-27 | 深圳市裕辰医疗科技有限公司 | Auxiliary diagnosis method for hemodialysis hypotension complication |
CN114845631A (en) * | 2019-12-20 | 2022-08-02 | 弗雷塞尼斯医疗保健控股公司 | Real-time intradialytic hypotension prediction |
KR20220149093A (en) * | 2021-04-30 | 2022-11-08 | 서울대학교산학협력단 | Apparatus for predicting intradialytic hypotension using AI and method thereof |
CN115547489A (en) * | 2022-11-02 | 2022-12-30 | 复旦大学附属华山医院 | Method for predicting death risk of maintenance hemodialysis patient |
CN115796312A (en) * | 2022-12-09 | 2023-03-14 | 北京数洋智慧科技有限公司 | Multivariable time series prediction method and system |
-
2023
- 2023-08-01 CN CN202310956821.1A patent/CN116682552B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114845631A (en) * | 2019-12-20 | 2022-08-02 | 弗雷塞尼斯医疗保健控股公司 | Real-time intradialytic hypotension prediction |
KR20220149093A (en) * | 2021-04-30 | 2022-11-08 | 서울대학교산학협력단 | Apparatus for predicting intradialytic hypotension using AI and method thereof |
CN114550913A (en) * | 2022-02-22 | 2022-05-27 | 深圳市裕辰医疗科技有限公司 | Auxiliary diagnosis method for hemodialysis hypotension complication |
CN115547489A (en) * | 2022-11-02 | 2022-12-30 | 复旦大学附属华山医院 | Method for predicting death risk of maintenance hemodialysis patient |
CN115796312A (en) * | 2022-12-09 | 2023-03-14 | 北京数洋智慧科技有限公司 | Multivariable time series prediction method and system |
Non-Patent Citations (1)
Title |
---|
基于机器学习算法探讨糖尿病视网膜病变的风险因素;宋亚男 等;解放军医学院学报;第42卷(第9期);第906-912页 * |
Also Published As
Publication number | Publication date |
---|---|
CN116682552A (en) | 2023-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20190378619A1 (en) | Using machine learning to predict health conditions | |
CN111724910B (en) | Detection and evaluation method suitable for blood management of perioperative patients | |
US8303532B2 (en) | Pertioneal membrane function test method, peritoneal membrane function test apparatus and peritoneal membrane function test program | |
Vest et al. | Outcomes for patients with diabetes after continuous-flow left ventricular assist device implantation | |
US20220047789A1 (en) | Adequacy assessment method and system | |
CN109585011A (en) | The Illnesses Diagnoses method and machine readable storage medium of chest pain patients | |
CN114121278A (en) | Prediction model of AKI risk after heart valve replacement based on age and clinical index | |
Connors Jr et al. | Assessing hemodynamic status in critically ill patients: do physicians use clinical information optimally? | |
O’Halloran et al. | RBC exposure in pediatric extracorporeal membrane oxygenation: epidemiology and factors associated with large blood transfusion volume | |
Saylor et al. | Predicting plasma free hemoglobin levels in patients due to medical device–related hemolysis | |
CN113744832B (en) | Intelligent decision-making and quality control system for continuous kidney substitution therapy | |
CN116682552B (en) | Strong interpretation characteristic hemodialysis hypotension prediction method for multi-time span data | |
Walker et al. | Calculating mixed venous saturation during veno-venous extracorporeal membrane oxygenation | |
Depner et al. | Refinements and application of urea modeling | |
CN114141359A (en) | Liquid treatment early warning system for general anesthesia abdominal operation patient | |
Kost et al. | Indications for measurement of total carbon dioxide in arterial blood. | |
CN111630610B (en) | Improved method for estimating arterial blood values | |
RU2154499C2 (en) | Method for treating the cases of renal insufficiency | |
Zhao et al. | Accuracy and stability evaluation of different blood sampling methods in blood gas analysis in emergency patients: A retrospective study | |
CN112730849B (en) | Application of endogenous orphan enkephalin as serum biomarker for diabetes mellitus combined with asymptomatic myocardial ischemia | |
Beto et al. | The effect of blood draw methodology on selected nutritional parameters in chronic renal failure | |
Xiong et al. | Association of intraoperative hyperglycemia with postoperative composite infection after cardiac surgery with cardiopulmonary bypass: A retrospective cohort study | |
CN115775633A (en) | Mortality real-time prediction method and system based on multidimensional data and electronic equipment | |
Cui et al. | Predicting ICU Pressure Injuries with Historical Data: A Multivariate Time Series Approach | |
CN116313076A (en) | Information processing method based on intelligent main examination program of physical examination 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |