WO2023241012A1 - Method for establishing deep learning-based model for predicting functions after post-cerebral stroke early rehabilitation - Google Patents
Method for establishing deep learning-based model for predicting functions after post-cerebral stroke early rehabilitation Download PDFInfo
- Publication number
- WO2023241012A1 WO2023241012A1 PCT/CN2022/143730 CN2022143730W WO2023241012A1 WO 2023241012 A1 WO2023241012 A1 WO 2023241012A1 CN 2022143730 W CN2022143730 W CN 2022143730W WO 2023241012 A1 WO2023241012 A1 WO 2023241012A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- model
- information
- mrs
- stroke
- feature
- Prior art date
Links
- 208000006011 Stroke Diseases 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000006870 function Effects 0.000 title claims abstract description 24
- 238000013135 deep learning Methods 0.000 title claims abstract description 11
- 208000032382 Ischaemic stroke Diseases 0.000 claims abstract description 31
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 22
- 238000010801 machine learning Methods 0.000 claims abstract description 16
- 238000004393 prognosis Methods 0.000 claims abstract description 14
- 238000013528 artificial neural network Methods 0.000 claims abstract description 6
- 230000006403 short-term memory Effects 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 5
- 239000000463 material Substances 0.000 claims abstract description 4
- 238000011282 treatment Methods 0.000 claims description 33
- 238000011084 recovery Methods 0.000 claims description 32
- 238000003066 decision tree Methods 0.000 claims description 18
- 229940079593 drug Drugs 0.000 claims description 18
- 239000003814 drug Substances 0.000 claims description 18
- 206010063648 Cerebral artery stenosis Diseases 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 16
- 208000031481 Pathologic Constriction Diseases 0.000 claims description 15
- 230000036262 stenosis Effects 0.000 claims description 15
- 208000037804 stenosis Diseases 0.000 claims description 15
- 238000000554 physical therapy Methods 0.000 claims description 14
- 238000011161 development Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 239000003146 anticoagulant agent Substances 0.000 claims description 10
- 230000000391 smoking effect Effects 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 206010020772 Hypertension Diseases 0.000 claims description 8
- 208000026106 cerebrovascular disease Diseases 0.000 claims description 8
- 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 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000002630 speech therapy Methods 0.000 claims description 8
- 210000004004 carotid artery internal Anatomy 0.000 claims description 7
- 208000006170 carotid stenosis Diseases 0.000 claims description 7
- 206010012601 diabetes mellitus Diseases 0.000 claims description 7
- 201000010099 disease Diseases 0.000 claims description 7
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 7
- 230000035622 drinking Effects 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 claims description 7
- 238000007917 intracranial administration Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 206010047330 Vertebral artery stenosis Diseases 0.000 claims description 6
- 201000006559 Vertebrobasilar insufficiency Diseases 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 6
- 230000002537 thrombolytic effect Effects 0.000 claims description 6
- 238000000585 Mann–Whitney U test Methods 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 230000000702 anti-platelet effect Effects 0.000 claims description 5
- 229940127219 anticoagulant drug Drugs 0.000 claims description 5
- 239000003472 antidiabetic agent Substances 0.000 claims description 5
- 239000002220 antihypertensive agent Substances 0.000 claims description 5
- 229940127088 antihypertensive drug Drugs 0.000 claims description 5
- 210000001367 artery Anatomy 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 claims description 5
- PGOHTUIFYSHAQG-LJSDBVFPSA-N (2S)-6-amino-2-[[(2S)-5-amino-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-4-amino-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-5-amino-2-[[(2S)-5-amino-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S,3R)-2-[[(2S)-5-amino-2-[[(2S)-2-[[(2S)-2-[[(2S,3R)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-5-amino-2-[[(2S)-1-[(2S,3R)-2-[[(2S)-2-[[(2S)-2-[[(2R)-2-[[(2S)-2-[[(2S)-2-[[2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-1-[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-amino-4-methylsulfanylbutanoyl]amino]-3-(1H-indol-3-yl)propanoyl]amino]-5-carbamimidamidopentanoyl]amino]propanoyl]pyrrolidine-2-carbonyl]amino]-3-methylbutanoyl]amino]-4-methylpentanoyl]amino]-4-methylpentanoyl]amino]acetyl]amino]-3-hydroxypropanoyl]amino]-4-methylpentanoyl]amino]-3-sulfanylpropanoyl]amino]-4-methylsulfanylbutanoyl]amino]-5-carbamimidamidopentanoyl]amino]-3-hydroxybutanoyl]pyrrolidine-2-carbonyl]amino]-5-oxopentanoyl]amino]-3-hydroxypropanoyl]amino]-3-hydroxypropanoyl]amino]-3-(1H-imidazol-5-yl)propanoyl]amino]-4-methylpentanoyl]amino]-3-hydroxybutanoyl]amino]-3-(1H-indol-3-yl)propanoyl]amino]-5-carbamimidamidopentanoyl]amino]-5-oxopentanoyl]amino]-3-hydroxybutanoyl]amino]-3-hydroxypropanoyl]amino]-3-carboxypropanoyl]amino]-3-hydroxypropanoyl]amino]-5-oxopentanoyl]amino]-5-oxopentanoyl]amino]-3-phenylpropanoyl]amino]-5-carbamimidamidopentanoyl]amino]-3-methylbutanoyl]amino]-4-methylpentanoyl]amino]-4-oxobutanoyl]amino]-5-carbamimidamidopentanoyl]amino]-3-(1H-indol-3-yl)propanoyl]amino]-4-carboxybutanoyl]amino]-5-oxopentanoyl]amino]hexanoic acid Chemical compound CSCC[C@H](N)C(=O)N[C@@H](Cc1c[nH]c2ccccc12)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](C)C(=O)N1CCC[C@H]1C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)N[C@@H](CO)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CS)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H]([C@@H](C)O)C(=O)N1CCC[C@H]1C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](Cc1cnc[nH]1)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](Cc1c[nH]c2ccccc12)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CO)C(=O)N[C@@H](CC(O)=O)C(=O)N[C@@H](CO)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](Cc1ccccc1)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CC(N)=O)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](Cc1c[nH]c2ccccc12)C(=O)N[C@@H](CCC(O)=O)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CCCCN)C(O)=O PGOHTUIFYSHAQG-LJSDBVFPSA-N 0.000 claims description 4
- 206010008190 Cerebrovascular accident Diseases 0.000 claims description 4
- 102000017011 Glycated Hemoglobin A Human genes 0.000 claims description 4
- 108010014663 Glycated Hemoglobin A Proteins 0.000 claims description 4
- 108010023302 HDL Cholesterol Proteins 0.000 claims description 4
- FFFHZYDWPBMWHY-VKHMYHEASA-N L-homocysteine Chemical compound OC(=O)[C@@H](N)CCS FFFHZYDWPBMWHY-VKHMYHEASA-N 0.000 claims description 4
- 108010028554 LDL Cholesterol Proteins 0.000 claims description 4
- 108010033266 Lipoprotein(a) Proteins 0.000 claims description 4
- 102000057248 Lipoprotein(a) Human genes 0.000 claims description 4
- 108010000499 Thromboplastin Proteins 0.000 claims description 4
- 102000002262 Thromboplastin Human genes 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 4
- 230000008901 benefit Effects 0.000 claims description 4
- 235000012000 cholesterol Nutrition 0.000 claims description 4
- 235000019504 cigarettes Nutrition 0.000 claims description 4
- 230000035487 diastolic blood pressure Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 4
- 208000019073 internal carotid artery stenosis Diseases 0.000 claims description 4
- 238000001990 intravenous administration Methods 0.000 claims description 4
- 238000001584 occupational therapy Methods 0.000 claims description 4
- 230000009747 swallowing Effects 0.000 claims description 4
- 230000035488 systolic blood pressure Effects 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 4
- 150000003626 triacylglycerols Chemical class 0.000 claims description 4
- 101000759879 Homo sapiens Tetraspanin-10 Proteins 0.000 claims description 3
- 201000006561 Subclavian Steal Syndrome Diseases 0.000 claims description 3
- 206010050180 Subclavian artery stenosis Diseases 0.000 claims description 3
- 102100024990 Tetraspanin-10 Human genes 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000005094 computer simulation Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 230000002349 favourable effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000007417 hierarchical cluster analysis Methods 0.000 claims description 3
- 210000004972 left anterior cerebral artery Anatomy 0.000 claims description 3
- 210000004973 left posterior cerebral artery Anatomy 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000002483 medication Methods 0.000 claims description 3
- 230000037081 physical activity Effects 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000012276 Endovascular treatment Methods 0.000 claims description 2
- 208000016988 Hemorrhagic Stroke Diseases 0.000 claims description 2
- 102100027378 Prothrombin Human genes 0.000 claims description 2
- 108010094028 Prothrombin Proteins 0.000 claims description 2
- 208000020658 intracerebral hemorrhage Diseases 0.000 claims description 2
- 229940039716 prothrombin Drugs 0.000 claims description 2
- 238000007637 random forest analysis Methods 0.000 claims 2
- 210000004556 brain Anatomy 0.000 claims 1
- 238000004364 calculation method Methods 0.000 claims 1
- 238000007477 logistic regression Methods 0.000 claims 1
- 230000007774 longterm Effects 0.000 abstract description 3
- 238000013136 deep learning model Methods 0.000 abstract description 2
- 238000009472 formulation Methods 0.000 abstract description 2
- 239000000203 mixture Substances 0.000 abstract description 2
- 230000036962 time dependent Effects 0.000 abstract description 2
- 206010008118 cerebral infarction Diseases 0.000 description 6
- 238000000556 factor analysis Methods 0.000 description 4
- 208000029078 coronary artery disease Diseases 0.000 description 3
- 239000005541 ACE inhibitor Substances 0.000 description 2
- 206010003658 Atrial Fibrillation Diseases 0.000 description 2
- 229940123208 Biguanide Drugs 0.000 description 2
- 208000032928 Dyslipidaemia Diseases 0.000 description 2
- 108090000790 Enzymes Proteins 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 2
- 208000017170 Lipid metabolism disease Diseases 0.000 description 2
- 229940044094 angiotensin-converting-enzyme inhibitor Drugs 0.000 description 2
- 150000004283 biguanides Chemical class 0.000 description 2
- 230000015271 coagulation Effects 0.000 description 2
- 238000005345 coagulation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- NOESYZHRGYRDHS-UHFFFAOYSA-N insulin Chemical compound N1C(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(NC(=O)CN)C(C)CC)CSSCC(C(NC(CO)C(=O)NC(CC(C)C)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CCC(N)=O)C(=O)NC(CC(C)C)C(=O)NC(CCC(O)=O)C(=O)NC(CC(N)=O)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CSSCC(NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2C=CC(O)=CC=2)NC(=O)C(CC(C)C)NC(=O)C(C)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2NC=NC=2)NC(=O)C(CO)NC(=O)CNC2=O)C(=O)NCC(=O)NC(CCC(O)=O)C(=O)NC(CCCNC(N)=N)C(=O)NCC(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC(O)=CC=3)C(=O)NC(C(C)O)C(=O)N3C(CCC3)C(=O)NC(CCCCN)C(=O)NC(C)C(O)=O)C(=O)NC(CC(N)=O)C(O)=O)=O)NC(=O)C(C(C)CC)NC(=O)C(CO)NC(=O)C(C(C)O)NC(=O)C1CSSCC2NC(=O)C(CC(C)C)NC(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CC(N)=O)NC(=O)C(NC(=O)C(N)CC=1C=CC=CC=1)C(C)C)CC1=CN=CN1 NOESYZHRGYRDHS-UHFFFAOYSA-N 0.000 description 2
- 230000000302 ischemic effect Effects 0.000 description 2
- 238000013151 thrombectomy Methods 0.000 description 2
- 102100021870 ATP synthase subunit O, mitochondrial Human genes 0.000 description 1
- BSYNRYMUTXBXSQ-UHFFFAOYSA-N Aspirin Chemical compound CC(=O)OC1=CC=CC=C1C(O)=O BSYNRYMUTXBXSQ-UHFFFAOYSA-N 0.000 description 1
- 206010003662 Atrial flutter Diseases 0.000 description 1
- 239000005552 B01AC04 - Clopidogrel Substances 0.000 description 1
- 239000005528 B01AC05 - Ticlopidine Substances 0.000 description 1
- 108090000312 Calcium Channels Proteins 0.000 description 1
- 102000003922 Calcium Channels Human genes 0.000 description 1
- 208000002330 Congenital Heart Defects Diseases 0.000 description 1
- HGVDHZBSSITLCT-JLJPHGGASA-N Edoxaban Chemical compound N([C@H]1CC[C@@H](C[C@H]1NC(=O)C=1SC=2CN(C)CCC=2N=1)C(=O)N(C)C)C(=O)C(=O)NC1=CC=C(Cl)C=N1 HGVDHZBSSITLCT-JLJPHGGASA-N 0.000 description 1
- 229940121710 HMGCoA reductase inhibitor Drugs 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
- 102000004877 Insulin Human genes 0.000 description 1
- 108090001061 Insulin Proteins 0.000 description 1
- 229940122355 Insulin sensitizer Drugs 0.000 description 1
- 201000008450 Intracranial aneurysm Diseases 0.000 description 1
- 208000007177 Left Ventricular Hypertrophy Diseases 0.000 description 1
- PVNIIMVLHYAWGP-UHFFFAOYSA-N Niacin Chemical compound OC(=O)C1=CC=CN=C1 PVNIIMVLHYAWGP-UHFFFAOYSA-N 0.000 description 1
- 208000005764 Peripheral Arterial Disease Diseases 0.000 description 1
- 208000030831 Peripheral arterial occlusive disease Diseases 0.000 description 1
- 208000032851 Subarachnoid Hemorrhage Diseases 0.000 description 1
- 229940100389 Sulfonylurea Drugs 0.000 description 1
- 208000007536 Thrombosis Diseases 0.000 description 1
- 208000002564 X-linked cardiac valvular dysplasia Diseases 0.000 description 1
- 229960001138 acetylsalicylic acid Drugs 0.000 description 1
- 206010000891 acute myocardial infarction Diseases 0.000 description 1
- 238000013103 analytical ultracentrifugation Methods 0.000 description 1
- 238000002399 angioplasty Methods 0.000 description 1
- 239000002333 angiotensin II receptor antagonist Substances 0.000 description 1
- 229940125364 angiotensin receptor blocker Drugs 0.000 description 1
- 229940127003 anti-diabetic drug Drugs 0.000 description 1
- 230000010100 anticoagulation Effects 0.000 description 1
- -1 apidogrel Saban Chemical compound 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002876 beta blocker Substances 0.000 description 1
- 229940097320 beta blocking agent Drugs 0.000 description 1
- 210000001715 carotid artery Anatomy 0.000 description 1
- 230000001906 cholesterol absorption Effects 0.000 description 1
- 229960004588 cilostazol Drugs 0.000 description 1
- RRGUKTPIGVIEKM-UHFFFAOYSA-N cilostazol Chemical compound C=1C=C2NC(=O)CCC2=CC=1OCCCCC1=NN=NN1C1CCCCC1 RRGUKTPIGVIEKM-UHFFFAOYSA-N 0.000 description 1
- 229960003009 clopidogrel Drugs 0.000 description 1
- GKTWGGQPFAXNFI-HNNXBMFYSA-N clopidogrel Chemical compound C1([C@H](N2CC=3C=CSC=3CC2)C(=O)OC)=CC=CC=C1Cl GKTWGGQPFAXNFI-HNNXBMFYSA-N 0.000 description 1
- 208000028831 congenital heart disease Diseases 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229960003850 dabigatran Drugs 0.000 description 1
- YBSJFWOBGCMAKL-UHFFFAOYSA-N dabigatran Chemical compound N=1C2=CC(C(=O)N(CCC(O)=O)C=3N=CC=CC=3)=CC=C2N(C)C=1CNC1=CC=C(C(N)=N)C=C1 YBSJFWOBGCMAKL-UHFFFAOYSA-N 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229960002768 dipyridamole Drugs 0.000 description 1
- IZEKFCXSFNUWAM-UHFFFAOYSA-N dipyridamole Chemical compound C=12N=C(N(CCO)CCO)N=C(N3CCCCC3)C2=NC(N(CCO)CCO)=NC=1N1CCCCC1 IZEKFCXSFNUWAM-UHFFFAOYSA-N 0.000 description 1
- 239000002934 diuretic Substances 0.000 description 1
- 229940030606 diuretics Drugs 0.000 description 1
- 229960000622 edoxaban Drugs 0.000 description 1
- 229940125753 fibrate Drugs 0.000 description 1
- 239000003316 glycosidase inhibitor Substances 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 230000002008 hemorrhagic effect Effects 0.000 description 1
- 229920000669 heparin Polymers 0.000 description 1
- 239000002471 hydroxymethylglutaryl coenzyme A reductase inhibitor Substances 0.000 description 1
- 239000003112 inhibitor Substances 0.000 description 1
- 229940125396 insulin Drugs 0.000 description 1
- 230000003914 insulin secretion Effects 0.000 description 1
- 238000001361 intraarterial administration Methods 0.000 description 1
- 239000003055 low molecular weight heparin Substances 0.000 description 1
- 229940127215 low-molecular weight heparin Drugs 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 208000031225 myocardial ischemia Diseases 0.000 description 1
- 229960003512 nicotinic acid Drugs 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 108010007425 oligomycin sensitivity conferring protein Proteins 0.000 description 1
- 229950003837 ozagrel Drugs 0.000 description 1
- SHZKQBHERIJWAO-AATRIKPKSA-N ozagrel Chemical compound C1=CC(/C=C/C(=O)O)=CC=C1CN1C=NC=C1 SHZKQBHERIJWAO-AATRIKPKSA-N 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229960001148 rivaroxaban Drugs 0.000 description 1
- KGFYHTZWPPHNLQ-AWEZNQCLSA-N rivaroxaban Chemical compound S1C(Cl)=CC=C1C(=O)NC[C@@H]1OC(=O)N(C=2C=CC(=CC=2)N2C(COCC2)=O)C1 KGFYHTZWPPHNLQ-AWEZNQCLSA-N 0.000 description 1
- 229960005001 ticlopidine Drugs 0.000 description 1
- PHWBOXQYWZNQIN-UHFFFAOYSA-N ticlopidine Chemical compound ClC1=CC=CC=C1CN1CC(C=CS2)=C2CC1 PHWBOXQYWZNQIN-UHFFFAOYSA-N 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
- 229960005080 warfarin Drugs 0.000 description 1
- PJVWKTKQMONHTI-UHFFFAOYSA-N warfarin Chemical compound OC=1C2=CC=CC=C2OC(=O)C=1C(CC(=O)C)C1=CC=CC=C1 PJVWKTKQMONHTI-UHFFFAOYSA-N 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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
Definitions
- the invention relates to a method for establishing a functional prognosis prediction model after early recovery from stroke, and specifically relates to a method for establishing a functional prediction model after early recovery from stroke based on deep learning.
- Stroke has the characteristics of high incidence, high mortality and high recurrence rate. According to the Global Burden of Disease Report 2010, stroke has become the second leading cause of death in the world and is also the disease with the highest disability rate among single diseases. Over the past two decades, tremendous advances have been made in the treatment of patients with acute ischemic stroke, resulting in significant reductions in mortality. However, as mortality rates decrease, the disability burden among stroke survivors increases.
- Treatment after acute ischemic stroke includes intravenous thrombolysis, device thrombectomy, etc.
- the difficulty lies in how to assess the patient's risk and how to obtain benefits from treatment, thereby helping to make early treatment decisions.
- Early rehabilitation is currently proposed as a means to promote functional recovery and reduce mortality and disability rates in stroke patients.
- there are currently no studies that predict the level of functional prognosis after acute ischemic stroke and there are no studies that predict the level of function and disability after early recovery.
- early and accurate prediction of functional prognosis is of great reference for family decision-making.
- the prognosis of ischemic stroke is highly heterogeneous and difficult to predict.
- Deep neural network analysis methods are adept at handling complex inputs and have been used to predict long-term prognosis.
- the present invention constructs a hybrid deep learning model composed of a convolutional neural network and a long-short-term memory artificial neural network, and combines clinical data and early rehabilitation-related data to make early and accurate predictions of the functional prognosis after early rehabilitation of ischemic stroke. Combined with the time-dependent modified Rankin Scale (mRS), long-term functional prediction is performed, while guiding the development of individualized early rehabilitation strategies.
- mRS time-dependent modified Rankin Scale
- the purpose of the present invention is to propose a method for establishing a functional prediction model after early rehabilitation of stroke based on deep learning in order to solve the shortcomings existing in the existing technology.
- the model establishment method includes the following steps:
- Prepare medical record data collect patient electronic medical records from the hospital electronic medical record platform, and collect electronic medical records of ischemic stroke patients undergoing early rehabilitation; use the medical record data of the first case diagnosed with ischemic stroke as qualified electronic medical record data. ;
- the medical characteristic values are specific values of each medical characteristic among demographics, laboratory and clinical examinations, drugs and invasive treatment and rehabilitation intervention characteristics;
- the demographic information includes: gender, age, occupation, marital status, education, height, weight, BMI, systolic blood pressure, diastolic blood pressure, heart rate, whether it is the first cerebrovascular accident, TOAST classification, OCSP classification, past history, Duration of hypertension, duration of diabetes, smoking status, smoking age, number of cigarettes smoked per day, smoking index, drinking history, regular physical activities, family history;
- the laboratory and clinical examination-related information includes: glycosylated hemoglobin, triglycerides, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, lipoprotein A, homocysteine, partial thromboplastin time, coagulation Enzyme time - international normalized ratio, electrocardiogram, structural imaging examination results, common carotid artery stenosis, carotid bulb stenosis, internal carotid artery stenosis, subclavian artery stenosis, left internal carotid artery intracranial stenosis, left anterior cerebral artery stenosis , left middle cerebral artery stenosis, left posterior cerebral artery stenosis, left vertebral artery stenosis, right internal carotid artery intracranial stenosis, right anterior cerebral artery stenosis, right middle cerebral artery stenosis, right posterior cerebral artery stenosis, right
- the information related to the drugs and invasive treatments includes: intravenous thrombolysis, endovascular treatment, antiplatelet treatment within 48 hours, anticoagulant treatment within 48 hours, antihypertensive drugs, lipid-lowering drugs, and hypoglycemic drugs;
- the information related to rehabilitation intervention includes: the duration from onset to the first rehabilitation intervention, the duration from onset to the first mobilization, the benefit of early mobilization in the first rehabilitation intervention, the duration of early mobilization in the first rehabilitation intervention, 14 days Total duration of early mobilization, average duration of 14 days of early mobilization, duration of physical therapy, duration of occupational therapy, duration of speech therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy Continuous Speech Therapy;
- Extract post-stroke scores at different time steps mainly include the day of admission, 15 days after stroke, 30 days after stroke, 90 days after stroke, and 180 days after stroke; extract the post-stroke time score used to predict the target ;
- the dichotomous results of time after stroke are: favorable outcome is time after stroke score 0-2, unfavorable outcome is time after stroke score 3-6, which may be moderate or severe disability, or death;
- the XGBoost includes an XGBoost decision tree and the relationship between the XGBoost decision trees; the XGBoost decision tree includes multiple nodes; the nodes are medical features and thresholds; the relationship between the XGBoost decision trees is a gradient descent optimization algorithm, The latter decision tree is obtained from the previous decision tree according to the gradient descent optimization algorithm;
- Feature screening in the XGBoost model Use XGBoost to automatically find the most relevant features for mRS90 binary classification of target results; use the initial features on the development set to train the estimator, and perform parameter adjustment through grid search technology or three-fold cross-validation for hyperparameter optimization, the trained model generates ranked key features, quantifying its relative importance by assigning a weight to each variable; said "weight" represents the use of that feature to split the data in all trees The total number of times to measure the feature importance in XGBoost;
- Feature analysis in the XGBoost model Calculate standard data samples, and the statistical methods for screening relevant features are T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance; among which T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance is a commonly used method in statistics; the present invention uses the above statistical method and related software to calculate and obtain the probability value P.
- Ward s method is implemented using the open source tool library seaborn
- the modeling test refers to using four machine learning algorithms:
- the grid search method systematically performs automated hyperparameter tuning.
- F1score is used as the model evaluation criterion, and 5-fold cross-validation is used to select the optimal model;
- the convolutional neural network - CNN is used as the backbone network and the long short-term memory network model with forgetting gate - LSTM is combined to conduct time series modeling focusing on the patient's recovery at each time step and the development of mRS recovery.
- the information used by the model includes demographic feature information and clinical feature information screened out by Intervention-related feature information is non-sequential information, and mRS scores are temporal information; the mRS scores include mRS-0, mRS-15, mRS-30, mRS-90, and mRS-180 scores;
- the network structure of the cascaded convolutional neural network and the recurrent neural network is constructed.
- the convolutional neural network performs feature aggregation and extraction on the non-sequential state information, and finally uses the sigmoid activation function as the score of the non-sequential state information;
- the attention mechanism is used to perform weighted fusion of features across time steps, so that the mRS prediction at each time step is closer to the mRS at all time steps before the current time step;
- the CNN time series model refers to the simulation modeling of the rehabilitation progress by focusing on the patient's recovery situation at each time step through learning and development, and changing the input of the model to obtain the rehabilitation progress under different circumstances;
- mRS-180 is used to represent the patient's final recovery status
- mRS-15, mRS-30, and mRS-90 are used to represent the patient's final recovery status.
- the present invention uses a machine learning CNN-LSTM integrated algorithm to establish a prediction model for functional prognosis after early recovery from ischemic stroke, based on demographic information, laboratory and clinical examination-related information, drug and invasive treatment-related information, rehabilitation Intervention-related information accurately predicts mRS-90 outcomes in patients with ischemic stroke.
- the CNN-LSTM model performed well in predicting the functional prognosis of early recovered ischemic stroke patients and showed better prediction performance than four traditional algorithms.
- the AUCs of the CNN-LSTM model in the test set are 0.829 (mRS-15), 0.706 (mRS-30), 0.809 (mRS-90) and 0.730 (mRS-180) respectively.
- the information of mRS-15 and mRS-30 is a key feature for the CNN-LSTM model to improve the prediction performance of mRS-180.
- the machine learning-based prediction model of functional prognosis after early rehabilitation of ischemic stroke constructed by this invention - CNN-LSTM, can perform functional prediction in the early stage of stroke and provide accurate guidance for the formulation of subsequent rehabilitation training programs. , to better restore the functions of stroke patients, while saving medical resources and reducing unnecessary consumption of manpower and material resources.
- Figure 1 is a flow chart of the method of model construction in the present invention.
- the present invention provides a method for establishing a functional prediction model after early recovery from stroke based on deep learning, which includes the following steps:
- Prepare medical record data collect patient electronic medical records from the hospital electronic medical record platform, and collect electronic medical records of ischemic stroke patients undergoing early rehabilitation.
- the ischemic stroke features include demographic information, laboratory and clinical examination-related information, and medications. and information related to invasive treatments, information related to rehabilitation interventions;
- the medical characteristic values are specific values of each medical characteristic among demographics, laboratory and clinical examinations, drugs and invasive treatment and rehabilitation intervention characteristics;
- the demographic information includes: gender, age, occupation, marital status, education, height, weight, BMI, systolic blood pressure, diastolic blood pressure, heart rate, whether it is the first cerebrovascular accident, TOAST classification, OCSP classification, past history, Duration of hypertension, duration of diabetes, smoking status, smoking age, number of cigarettes smoked per day, smoking index, drinking history, regular physical activities, family history;
- the past medical history also includes ischemic stroke, hemorrhagic stroke, subarachnoid hemorrhage, unclassified stroke, hypertension, diabetes, dyslipidemia, atrial fibrillation, coronary heart disease, myocardial infarction, congenital heart disease, and valvular heart disease.
- disease other types of heart disease, and peripheral arterial disease; the family history includes stroke, coronary heart disease, hypertension, diabetes, dyslipidemia, and intracranial aneurysm.
- the laboratory and clinical examination-related information includes: glycosylated hemoglobin, triglycerides, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, lipoprotein A, homocysteine, partial thromboplastin time, coagulation Enzyme time - international normalized ratio, electrocardiogram, structural imaging examination results, common carotid artery stenosis, carotid bulb stenosis, internal carotid artery stenosis, subclavian artery stenosis, left internal carotid artery intracranial stenosis, left anterior cerebral artery stenosis , left middle cerebral artery stenosis, left posterior cerebral artery stenosis, left vertebral artery stenosis, right internal carotid artery intracranial stenosis, right anterior cerebral artery stenosis, right middle cerebral artery stenosis, right posterior cerebral artery stenosis, right
- the electrocardiogram detection includes atrial fibrillation, atrial flutter, left ventricular hypertrophy, Q wave, acute myocardial infarction, myocardial ischemia and others; the structural imaging examination results include hemorrhagic transformation after cerebral infarction, new cerebral infarction, old cerebral infarction and so on. Cerebral infarction and others.
- the information related to the drugs and invasive treatments includes: intravenous thrombolysis, intravascular treatment, antiplatelet treatment within 48 hours, anticoagulant treatment within 48 hours, antihypertensive drugs, lipid-lowering drugs, and hypoglycemic drugs;
- the intravascular treatment includes stent thrombectomy, direct thrombus aspiration, balloon dilatation, intravascular stent-assisted angioplasty, intra-arterial thrombolysis and mechanical thrombolysis;
- the antiplatelet treatment within 48 hours includes the use of aspirin, Clopidogrel, ozagrel, dipyridamole, ticlopidine, cilostazol and others;
- the anticoagulant treatment within 48 hours includes warfarin, rivaroxaban, dabigatran, apidogrel Saban, edoxaban, low molecular weight heparin, unfractionated heparin and others;
- the antihypertensive drugs include angiotensin-converting enzyme inhibitors, angiotensin receptor blockers, diuretics, beta-blockers, Calcium ion channel blockers and others;
- the lipid-lowering drugs include statins, niacin and its derivatives, fibrates, cholesterol absorption inhibitors and others;
- the information related to rehabilitation intervention includes: the duration from onset to the first rehabilitation intervention, the duration from onset to the first mobilization, the benefit of early mobilization in the first rehabilitation intervention, the duration of early mobilization in the first rehabilitation intervention, 14 days Total duration of early mobilization, average duration of 14 days of early mobilization, duration of physical therapy, duration of occupational therapy, duration of speech therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy Continuous Speech Therapy.
- the extracted time steps mainly include mRS-0 (baseline is the day of admission), mRS-15 (15 days after stroke), mRS-30 ( 30 days after stroke), mRS-90 (90 days after stroke), mRS-180 (180 days after stroke);
- the dichotomous outcomes of time after stroke include: favorable outcome, time after stroke score of 0-2, indicating no or minimal disability; unfavorable outcome, time after stroke score of 3-6, indicating moderate or severe disability, or death.
- steps S1 to S3 big data on the clinical manifestations of ischemic stroke can be obtained.
- the remaining missing feature data will be filled in under the mode of existing data for the same feature.
- the missing values of continuous variables are filled with the mean
- the missing values of the categorical variables are filled with the mode; all data are standardized so that their mean and unit variance are zero.
- the XGBoost includes an XGBoost decision tree and the relationship between the XGBoost decision trees; the XGBoost decision tree includes multiple nodes; the nodes are medical features and thresholds; the relationship between the XGBoost decision trees is a gradient descent optimization algorithm, The latter decision tree is obtained from the previous decision tree according to the gradient descent optimization algorithm;
- Feature screening in the XGBoost model Use XGBoost to automatically find the most relevant features for mRS90 binary classification of target results; use the initial features on the development set to train the estimator, and perform parameter adjustment through grid search technology or three-fold cross-validation for hyperparameter optimization, the trained model generates ranked key features, quantifying its relative importance by assigning a weight to each variable; said "weight" represents the use of that feature to split the data in all trees The total number of times to measure the feature importance in XGBoost;
- Feature analysis in the XGBoost model Calculate standard data samples, and the statistical methods for screening relevant features are T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance; among which T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance is a commonly used method in statistics; the present invention uses the above statistical method and related software to calculate and obtain the probability value P.
- the modeling test refers to using four machine learning algorithms:
- the grid search method systematically performs automated hyperparameter tuning.
- F1score is used as the model evaluation criterion, and 5-fold cross-validation is used to select the optimal model;
- Demographic and clinical information smoking age, antidiabetic drugs (biguanides), number of cigarettes smoked per day, past medical history (diabetes), antiplatelet treatment within 48 hours, anticoagulant treatment within 48 hours (other), drinking history, family History (stroke), carotid artery vascular examination (carotid bulbar artery stenosis), family history (hypertension), occupation, duration of diabetes (years), family history (coronary heart disease), systolic blood pressure, whether it is the first cerebrovascular accident, imaging (new cerebral infarction), education, swallowing function assessment, anticoagulation treatment within 48 hours, resultant imaging examination results (old cerebral infarction), lipoprotein (a), resultant imaging examination results (other), past history ( Hypertension), duration of hypertension (years), antihypertensive drugs (angiotensin-converting enzyme inhibitors), heart rate, gender, lipid-lowering drugs, age, triglycerides, OSCP classification, partial thromboplastin time, total cholesterol , weight, prothro
- Rehabilitation intervention related information length of time from onset to first rehabilitation treatment (hours), time from onset to first out of bed (hours), whether out of bed was completed during the first rehabilitation treatment, time to maintain out of bed state during first out of bed rehabilitation treatment (minutes) , Total time out of bed in 14 days, Average time out of bed in 14 days (minutes), Physical therapy duration (days), Occupational therapy duration (days), Speech therapy duration (days), 14 days of continuous physical therapy, 14 days of continuous Physical therapy, continuous speech therapy for 14 days;
- Time step information (days): The value is ⁇ 0, 15, 30, 90, 180 ⁇ .
- the information used by the model includes demographic feature information and clinical feature information screened out by Intervention-related feature information is non-sequential information, and mRS scores are temporal information; the mRS scores include mRS-0, mRS-15, mRS-30, mRS-90, and mRS-180 scores;
- the network structure of the cascaded convolutional neural network and the recurrent neural network is constructed.
- the convolutional neural network performs feature aggregation and extraction on the non-sequential state information, and finally uses the sigmoid activation function as the score of the non-sequential state information;
- the attention mechanism is used to perform weighted fusion of features across time steps, so that the mRS prediction at each time step is closer to the mRS at all time steps before the current time step;
- L total represents the overall loss
- Lmse represents the weighted mean square error loss function
- L fn represents the weighted focal loss loss function (focal loss can effectively alleviate the complex category imbalance problem between multiple time steps and perform difficult sample mining )
- mse represents the mean square error loss function (which can make the prediction performance at different time steps more balanced)
- W mask represents the weighting coefficient
- ⁇ represents the weighting factor
- the value range is [0,1]
- the value of this model is 0.25
- P represents the prediction result
- p' represents the label
- N represents the number of samples
- ⁇ is the weighting factor
- the value range is [0,1]
- this model takes the value 1
- ⁇ represents the focusing parameter
- the value range is generally [0, 5], the value of this model is 2.
- the time series model refers to the simulation modeling of the rehabilitation progress by focusing on the patient's recovery situation at each time step through learning and development, and changing the input of the model to obtain the rehabilitation progress under different circumstances;
- mRS-180 is used to represent the patient's final recovery status
- mRS-15, mRS-30, and mRS-90 are used to represent the patient's final recovery status.
- the impact of missing mRS scores was explored and analyzed in time steps.
Abstract
A method for establishing a deep learning-based model for predicting functions after post-cerebral stroke early rehabilitation. By constructing a hybrid deep learning model consisting of a convolutional neural network (CNN) and a long short-term memory (LSTM) artificial neural network, and combining clinical data and early rehabilitation related data, the early and accurate prediction of function prognosis after post-cerebral ischemic stroke early rehabilitation is performed; long-term function prediction is performed in combination with a time-dependent modified Rankin scale (mRS), and at the same time, an individualized early rehabilitation strategy is formulated under guidance; function prediction can be performed in the early stage of cerebral stroke by means of the constructed machine learning-based prediction model for function prognosis after post-cerebral ischemic stroke early rehabilitation, i.e., a CNN-LSTM model, so that accurate guidance is provided for the formulation of a subsequent rehabilitation training plan, and the functions of a stroke patient are better recovered; moreover, medical resources can be conserved, and unnecessary consumption of labor and material resources is reduced.
Description
发明涉及脑卒中早期康复后功能预后预测模型的建立方法,具体涉及一种基于深度学习的脑卒中早期康复后功能预测模型建立方法。The invention relates to a method for establishing a functional prognosis prediction model after early recovery from stroke, and specifically relates to a method for establishing a functional prediction model after early recovery from stroke based on deep learning.
脑卒中具有高发病率、高死亡率和高复发率等特点,据全球疾病负担报告2010显示,脑卒中已成为世界上第二大致死原因,同时也是单病种致残率最高的疾病。在过去的二十年中,急性缺血性脑卒中患者的治疗取得了巨大的进展,死亡率显著降低。然而,随着死亡率的下降,脑卒中幸存者的残疾负担增加。Stroke has the characteristics of high incidence, high mortality and high recurrence rate. According to the Global Burden of Disease Report 2010, stroke has become the second leading cause of death in the world and is also the disease with the highest disability rate among single diseases. Over the past two decades, tremendous advances have been made in the treatment of patients with acute ischemic stroke, resulting in significant reductions in mortality. However, as mortality rates decrease, the disability burden among stroke survivors increases.
急性缺血性卒中后的治疗有静脉溶栓、器械取栓等,难点在于如何评估患者的风险以及如何从治疗中获得益处,从而帮助早期治疗的决策。早期康复是目前提出的作为一种促进脑卒中患者功能恢复,降低死亡率和致残率的手段。然而目前尚未由研究对急性缺血性卒中功能预后水平进行预测,同时也无研究对早期康复后的功能和残疾水平进行预测。然而对于患者和家属而言,早期和准确地预测功能预后对于家庭决策具有重要参考意义。缺血性脑卒中的预后具有高度异质性,预测难度大。近年来,人们对逐渐增加了对深度学习的研究,这可能为解决这些具有挑战性的问题提供方法。深度神经网络分析方法擅长处理复杂的输入,并已被用于预测长期预后。Treatment after acute ischemic stroke includes intravenous thrombolysis, device thrombectomy, etc. The difficulty lies in how to assess the patient's risk and how to obtain benefits from treatment, thereby helping to make early treatment decisions. Early rehabilitation is currently proposed as a means to promote functional recovery and reduce mortality and disability rates in stroke patients. However, there are currently no studies that predict the level of functional prognosis after acute ischemic stroke, and there are no studies that predict the level of function and disability after early recovery. However, for patients and families, early and accurate prediction of functional prognosis is of great reference for family decision-making. The prognosis of ischemic stroke is highly heterogeneous and difficult to predict. In recent years, there has been a gradual increase in research into deep learning, which may provide methods for solving these challenging problems. Deep neural network analysis methods are adept at handling complex inputs and have been used to predict long-term prognosis.
本发明构建一个由卷积神经网络和长短期记忆人工神经网络组成的混合深度学习模型,结合临床数据及早期康复相关数据为缺血性 脑卒中早期康复后的功能预后进行早期、精准地预测,结合时间依耐性的改良Rankin量表(mRS)进行远期功能预测,同时指导制定个体化的早期康复策略。The present invention constructs a hybrid deep learning model composed of a convolutional neural network and a long-short-term memory artificial neural network, and combines clinical data and early rehabilitation-related data to make early and accurate predictions of the functional prognosis after early rehabilitation of ischemic stroke. Combined with the time-dependent modified Rankin Scale (mRS), long-term functional prediction is performed, while guiding the development of individualized early rehabilitation strategies.
发明内容Contents of the invention
本发明的目的是为了解决现有技术中存在的缺点,而提出的一种基于深度学习的脑卒中早期康复后功能预测模型建立方法。The purpose of the present invention is to propose a method for establishing a functional prediction model after early rehabilitation of stroke based on deep learning in order to solve the shortcomings existing in the existing technology.
为实现上述目的,本发明采用了如下技术方案:一种基于深度学习的脑卒中早期康复后功能预测模型建立方法,所述模型建立方法包括以下步骤:In order to achieve the above purpose, the present invention adopts the following technical solution: a method for establishing a functional prediction model after early recovery from stroke based on deep learning. The model establishment method includes the following steps:
S1:建立数据病库;S1: Establish a data disease database;
准备病历数据,从医院电子病历平台采集患者电子病历,搜集进行早期康复的缺血性脑卒中患者的电子病历;以第一诊断为缺血性脑卒中的病例的病历数据为合格的电子病历数据;Prepare medical record data, collect patient electronic medical records from the hospital electronic medical record platform, and collect electronic medical records of ischemic stroke patients undergoing early rehabilitation; use the medical record data of the first case diagnosed with ischemic stroke as qualified electronic medical record data. ;
S2:提取病患医学特征数据;S2: Extract patient medical characteristic data;
对S1中得到的合格的电子病历数据进行缺血性脑卒中医学特征提取,提取医学特征及医学特征值;所述缺血性脑卒中特征包括人口统计信息、实验室和临床检查相关信息、药物和侵入性治疗相关信息、康复干预相关信息;用于作为预测的素材;Extract ischemic stroke medical features from the qualified electronic medical record data obtained in S1, and extract medical features and medical feature values; the ischemic stroke features include demographic information, laboratory and clinical examination-related information, and medications. Information related to invasive treatment and rehabilitation intervention; used as material for prediction;
所述医学特征值为人口统计、实验室和临床检查、药物和侵入性治疗和康复干预特征中各个医学特征的具体数值;The medical characteristic values are specific values of each medical characteristic among demographics, laboratory and clinical examinations, drugs and invasive treatment and rehabilitation intervention characteristics;
所述人口统计信息包括:性别、年龄、职业、婚姻状态、教育、身高、体重、BMI、收缩压、舒张压、心率、是否为首次脑血管意外、 TOAST分型、OCSP分型、既往史、高血压病程、糖尿病病程、吸烟状态、烟龄、每日吸烟支数、吸烟指数、饮酒史、常规体育活动、家族史;The demographic information includes: gender, age, occupation, marital status, education, height, weight, BMI, systolic blood pressure, diastolic blood pressure, heart rate, whether it is the first cerebrovascular accident, TOAST classification, OCSP classification, past history, Duration of hypertension, duration of diabetes, smoking status, smoking age, number of cigarettes smoked per day, smoking index, drinking history, regular physical activities, family history;
所述实验室和临床检查相关信息包括:糖化血红蛋白、甘油三脂、总胆固醇、低密度脂蛋白胆固醇、高密度脂蛋白胆固醇、脂蛋白a、同型半胱氨酸、部分凝血活酶时间、凝血酶原时间-国际标准化比值、心电图、结构影像学检查结果、颈总动脉狭窄、颈动脉球狭窄、颈内动脉狭窄、锁骨下动脉狭窄、左颈内动脉颅内狭窄、左侧大脑前动脉狭窄、左侧大脑中动脉狭窄、左脑后动脉狭窄、左椎动脉狭窄、右颈内动脉颅内狭窄、右大脑前动脉狭窄、右大脑中动脉狭窄、右大脑后动脉狭窄、右椎动脉狭窄、椎基底动脉狭窄、吞咽功能评估、洼田饮水试验;The laboratory and clinical examination-related information includes: glycosylated hemoglobin, triglycerides, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, lipoprotein A, homocysteine, partial thromboplastin time, coagulation Enzyme time - international normalized ratio, electrocardiogram, structural imaging examination results, common carotid artery stenosis, carotid bulb stenosis, internal carotid artery stenosis, subclavian artery stenosis, left internal carotid artery intracranial stenosis, left anterior cerebral artery stenosis , left middle cerebral artery stenosis, left posterior cerebral artery stenosis, left vertebral artery stenosis, right internal carotid artery intracranial stenosis, right anterior cerebral artery stenosis, right middle cerebral artery stenosis, right posterior cerebral artery stenosis, right vertebral artery stenosis, Vertebrobasilar artery stenosis, swallowing function assessment, Kubota drinking test;
所述药物和侵入性治疗相关信息包括:静脉溶栓、血管内治疗、48小时内抗血小板治疗、48小时内抗凝治疗、降压药、调脂药、降糖药;The information related to the drugs and invasive treatments includes: intravenous thrombolysis, endovascular treatment, antiplatelet treatment within 48 hours, anticoagulant treatment within 48 hours, antihypertensive drugs, lipid-lowering drugs, and hypoglycemic drugs;
所述康复干预相关信息包括:从发病至第一次康复干预时长、从发病至第一次动员时长、第一次康复干预中早期动员的效益、第一次康复干预中早期动员时长、14天早期动员总时长、14天早期动员平均时长、物理治疗时长、作业治疗时长、言语治疗时长、第一次14天进行连续物理治疗、第一次14天进行连续物理治疗、第一次14天进行连续言语治疗;The information related to rehabilitation intervention includes: the duration from onset to the first rehabilitation intervention, the duration from onset to the first mobilization, the benefit of early mobilization in the first rehabilitation intervention, the duration of early mobilization in the first rehabilitation intervention, 14 days Total duration of early mobilization, average duration of 14 days of early mobilization, duration of physical therapy, duration of occupational therapy, duration of speech therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy Continuous Speech Therapy;
S3:目标结果特征数据提取;S3: Target result feature data extraction;
在不同时间步点提取卒中后评分,提取的时间步点主要包括入院当天、卒中后15天、卒中后30天、卒中后90天、卒中后180天;提取用于预测目标的卒中后时间评分;卒中后时间二分类结果有:有利结果为卒中后时间评分0-2,不利结果卒中后时间评分3-6,情况可能是中度或重度失能,或死亡;Extract post-stroke scores at different time steps. The extracted time steps mainly include the day of admission, 15 days after stroke, 30 days after stroke, 90 days after stroke, and 180 days after stroke; extract the post-stroke time score used to predict the target ; The dichotomous results of time after stroke are: favorable outcome is time after stroke score 0-2, unfavorable outcome is time after stroke score 3-6, which may be moderate or severe disability, or death;
通过S1到步骤S3可以得到缺血性卒中临床表现的大数据资料Big data on the clinical manifestations of ischemic stroke can be obtained through steps S1 to S3.
S4:特征数据标准化及对数据清洗;S4: Feature data standardization and data cleaning;
对S3得到的缺血性卒中临床表现的大数据资料进行特征数据标准化,采用缺失数据策略,排除特征变量缺失超过50%的患者,剩余特征缺失的数据在同一特征已有数据的模式下进行填充,连续变量的缺失值使用均值填充,分类变量的缺失值使用众数填充;所有数据经过标准化,使其均值和单位方差为零;Standardize the feature data on the big data on the clinical manifestations of ischemic stroke obtained in S3, and adopt a missing data strategy to exclude patients with more than 50% missing feature variables. The remaining missing feature data will be filled in under the mode of existing data for the same feature. , the missing values of continuous variables are filled with the mean, and the missing values of the categorical variables are filled with the mode; all data are standardized so that their mean and unit variance are zero;
S5:建立机器学习模型1——XGBoost;S5: Establish machine learning model 1—XGBoost;
将步骤S2中提取到的人口统计信息、实验室和临床检查相关信息、药物和侵入性治疗相关信息以及康复干预相关信息输入XGBoost模型中进行mRS90二分类预测;Input the demographic information, laboratory and clinical examination-related information, drug and invasive treatment-related information, and rehabilitation intervention-related information extracted in step S2 into the XGBoost model for mRS90 binary prediction;
所述XGBoost包括XGBoost决策树以及XGBoost决策树之间的关系;所述XGBoost决策树包括多个结点;结点为医学特征及阈值;所述XGBoost决策树之间的关系为梯度下降优化算法,后一棵决策树由前一棵树决策树按照梯度下降优化算法得到;The XGBoost includes an XGBoost decision tree and the relationship between the XGBoost decision trees; the XGBoost decision tree includes multiple nodes; the nodes are medical features and thresholds; the relationship between the XGBoost decision trees is a gradient descent optimization algorithm, The latter decision tree is obtained from the previous decision tree according to the gradient descent optimization algorithm;
所述XGBoost模型中特征筛选:使用XGBoost自动找出最相关的特征,用于目标结果的mRS90二元分类;利用开发集上的初始特 征对估计器进行训练,并通过网格搜索技术进行参数调整或超参数优化的三折交叉验证,训练后的模型生成排序的关键特征,通过为每个变量分配一个权重来量化其相对重要性;所述“权重”表示使用该特性在所有树中分割数据的总次数,以度量XGBoost中的特征重要性;Feature screening in the XGBoost model: Use XGBoost to automatically find the most relevant features for mRS90 binary classification of target results; use the initial features on the development set to train the estimator, and perform parameter adjustment through grid search technology or three-fold cross-validation for hyperparameter optimization, the trained model generates ranked key features, quantifying its relative importance by assigning a weight to each variable; said "weight" represents the use of that feature to split the data in all trees The total number of times to measure the feature importance in XGBoost;
所述XGBoost模型中特征分析:对标准数据样本进行计算,筛选相关特征的统计学方法为T检验、Mann-Whitney U检验、Kruskal-Wallis单因素方差分析;其中T检验、Mann-Whitney U检验、Kruskal-Wallis单因素方差分析是统计学中常用的一种方法;本发明用上述统计学方法及相关软件进行计算,得到概率值P,我们设定P值小于0.05的,可以认为选取的特征与缺血性mRS90二分类目标存在极其显著的相关关系,选取这些特征建立模型是合理的;其次对筛选出的特征变量以及所有康复干预相关信息进行层次聚类分析;所述层次聚类使用的评价标准为‘enclidean’,方法选择Feature analysis in the XGBoost model: Calculate standard data samples, and the statistical methods for screening relevant features are T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance; among which T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance is a commonly used method in statistics; the present invention uses the above statistical method and related software to calculate and obtain the probability value P. We set the P value less than 0.05, and it can be considered that the selected features are consistent with There is an extremely significant correlation between the ischemic mRS90 two-category targets, and it is reasonable to select these features to build a model; secondly, hierarchical clustering analysis was performed on the selected feature variables and all rehabilitation intervention-related information; evaluation of the use of hierarchical clustering Standard is 'enclidean', method selection
Ward’s method,具体实现采用开源工具库seaborn;Ward’s method is implemented using the open source tool library seaborn;
使用选择出来的人口学特征信息和临床特征信息、所有康复干预相关的特征信息和mRS首次作为输入信息进行建模实验;Use the selected demographic and clinical characteristic information, all rehabilitation intervention-related characteristic information and mRS as input information for the first time to conduct a modeling experiment;
所述建模试验是指使用XGBoost、SVM、random forest(RF)、Logistic Regression(LR)四种机器学习算法在开发集Develop Set进行建模,在建模过程中,每种机器学习方法都使用网格搜索方法系统的进行自动化超参数调优,网格搜索过程中使用F1score作为模型评价标准,采用5折交叉验证选择最优模型;The modeling test refers to using four machine learning algorithms: The grid search method systematically performs automated hyperparameter tuning. During the grid search process, F1score is used as the model evaluation criterion, and 5-fold cross-validation is used to select the optimal model;
S6:建立机器学习模型2——CNN-LSTM;S6: Establish machine learning model 2—CNN-LSTM;
利用卷积神经网络--CNN作为主干网络与带有遗忘门的长短期记忆网络模型--LSTM结合,以患者在每个时间步的康复为重点,以及mRS康复发展情况进行时序建模。The convolutional neural network - CNN is used as the backbone network and the long short-term memory network model with forgetting gate - LSTM is combined to conduct time series modeling focusing on the patient's recovery at each time step and the development of mRS recovery.
所述模型采用的信息包括由XGBoost筛选出的人口学特征信息和临床特征信息、所有康复干预相关的特征信息、mRS评分和对应的时间步信息;其中人口学特征信息和临床特征信息、所有康复干预相关的特征信息属于非时序信息,mRS评分属于时序信息;所述mRS评分包括mRS-0、mRS-15、mRS-30、mRS-90、mRS-180的评分;The information used by the model includes demographic feature information and clinical feature information screened out by Intervention-related feature information is non-sequential information, and mRS scores are temporal information; the mRS scores include mRS-0, mRS-15, mRS-30, mRS-90, and mRS-180 scores;
采用上述所述信息作为输入信息,构建级联卷积神经网络和循环神经网络的网络结构,为了让每一时间步都能获取到病人的非时序状态信息,首先使用堆叠多层全连接层的卷积神经网络对非时序状态信息进行特征聚合、提取,最终经过sigmoid激活函数作为非时序状态信息的得分;Using the above information as input information, the network structure of the cascaded convolutional neural network and the recurrent neural network is constructed. In order to obtain the patient's non-sequential status information at each time step, first use stacked multiple layers of fully connected layers. The convolutional neural network performs feature aggregation and extraction on the non-sequential state information, and finally uses the sigmoid activation function as the score of the non-sequential state information;
随后应用CNN堆叠多个完整的连接层聚合,提取特征非连续的状态信息,其次采用上述所述函数生成非时序的状态信息;Then apply CNN to stack multiple complete connection layer aggregation to extract feature discontinuous state information, and then use the above function to generate non-sequential state information;
将生成的分数与时序信息和相应的时间步信息结合,融合到LSTM网络中;Combine the generated scores with timing information and corresponding time step information and integrate them into the LSTM network;
采用LSTM模型训练学习每个患者的mRS康复发展变化;Use LSTM model training to learn the mRS rehabilitation development changes of each patient;
最后,利用注意机制进行跨时间步的特征加权融合,使每个时间步的mRS预测更接近当前时间步之前所有时间步的mRS;Finally, the attention mechanism is used to perform weighted fusion of features across time steps, so that the mRS prediction at each time step is closer to the mRS at all time steps before the current time step;
S7:建立机器学习模型3——刺激观察-关键点选择;S7: Establish machine learning model 3 - stimulus observation - key point selection;
利用已经训练好的CNN时序模型在不同的mRS缺失情况下进行 测试评估,以便更好地探究随访过程每一时间步mRS评分对病人康复情况的影响;Use the trained CNN time series model to conduct testing and evaluation under different mRS loss conditions to better explore the impact of mRS scores at each time step of the follow-up process on the patient's recovery;
所述CNN时序模型是指通过学习开发集中病人每个时间步的康复情况进而对康复进展进行了仿真建模,改变模型的输入得到不同情况下的康复进展;The CNN time series model refers to the simulation modeling of the rehabilitation progress by focusing on the patient's recovery situation at each time step through learning and development, and changing the input of the model to obtain the rehabilitation progress under different circumstances;
通过上述模型输入的改变,对比不同时间步下mRS评分的影响程度;在该模型中,利用mRS-180代表病人最终的康复状态,然后使用mRS-15、mRS-30、mRS-90这三个时间步中探索分析mRS评分的缺失的影响;Through the changes in the input of the above model, the impact of mRS scores at different time steps is compared; in this model, mRS-180 is used to represent the patient's final recovery status, and then mRS-15, mRS-30, and mRS-90 are used to represent the patient's final recovery status. Explore and analyze the impact of missing mRS scores in the time step;
S8:结果对比,选择模型;S8: Compare results and select model;
经过S5、S6以及S7的结果对比后得到特异性和敏感性最好的是CNN-LSTM模型,判定其为缺血性脑卒中早期康复后功能预后的预测模型。After comparing the results of S5, S6 and S7, it was found that the CNN-LSTM model had the best specificity and sensitivity, and was judged to be a predictive model for functional prognosis after early recovery from ischemic stroke.
与现有技术相比,本发明的有益效果为:Compared with the prior art, the beneficial effects of the present invention are:
(1)本发明采用机器学习CNN-LSTM集成算法建立缺血性脑卒中早期康复后功能预后的预测模型,根据人口统计信息、实验室和临床检查相关信息、药物和侵入性治疗相关信息、康复干预相关信息精准预测缺血性脑卒中患者mRS-90结局。CNN-LSTM模型在预测早期康复的缺血性脑卒中患者的功能预后方面表现良好,并显示出优于四种传统算法的预测效果。CNN-LSTM模型在测试集的AUC分别为0.829(mRS-15)、0.706(mRS-30)、0.809(mRS-90)和0.730(mRS-180)。此外,mRS-15和mRS-30的信息是CNN-LSTM模型对mRS-180预 测性能改善的关键特征。(1) The present invention uses a machine learning CNN-LSTM integrated algorithm to establish a prediction model for functional prognosis after early recovery from ischemic stroke, based on demographic information, laboratory and clinical examination-related information, drug and invasive treatment-related information, rehabilitation Intervention-related information accurately predicts mRS-90 outcomes in patients with ischemic stroke. The CNN-LSTM model performed well in predicting the functional prognosis of early recovered ischemic stroke patients and showed better prediction performance than four traditional algorithms. The AUCs of the CNN-LSTM model in the test set are 0.829 (mRS-15), 0.706 (mRS-30), 0.809 (mRS-90) and 0.730 (mRS-180) respectively. In addition, the information of mRS-15 and mRS-30 is a key feature for the CNN-LSTM model to improve the prediction performance of mRS-180.
(2)本发明构建的基于机器学习的缺血性脑卒中早期康复后功能预后的预测模型——CNN-LSTM,可在脑卒中早期进行功能预测,为后续的康复训练方案的制定提供精确指导,更好地恢复卒中患者的功能,同时可节省医疗资源,减少不必要的人力及物力的消耗。(2) The machine learning-based prediction model of functional prognosis after early rehabilitation of ischemic stroke constructed by this invention - CNN-LSTM, can perform functional prediction in the early stage of stroke and provide accurate guidance for the formulation of subsequent rehabilitation training programs. , to better restore the functions of stroke patients, while saving medical resources and reducing unnecessary consumption of manpower and material resources.
图1为本发明模型构建的方法流程图。Figure 1 is a flow chart of the method of model construction in the present invention.
为使对本发明的目的、构造、特征、及其功能有进一步的了解,兹配合实施例详细说明如下。In order to further understand the purpose, structure, characteristics, and functions of the present invention, detailed descriptions are given below with reference to the embodiments.
1.请结合参照图1,本发明提供了一种基于深度学习的脑卒中早期康复后功能预测模型建立方法,包括以下步骤:1. Please refer to Figure 1. The present invention provides a method for establishing a functional prediction model after early recovery from stroke based on deep learning, which includes the following steps:
S1:建立数据病库;S1: Establish a data disease database;
准备病历数据,从医院电子病历平台采集患者电子病历,搜集进行早期康复的缺血性脑卒中患者的电子病历。Prepare medical record data, collect patient electronic medical records from the hospital electronic medical record platform, and collect electronic medical records of ischemic stroke patients undergoing early rehabilitation.
S2:提取病患医学特征数据;S2: Extract patient medical characteristic data;
对S1中得到的合格的电子病历数据进行缺血性脑卒中医学特征提取,提取医学特征及医学特征值;所述缺血性脑卒中特征包括人口统计信息、实验室和临床检查相关信息、药物和侵入性治疗相关信息、康复干预相关信息;Extract ischemic stroke medical features from the qualified electronic medical record data obtained in S1, and extract medical features and medical feature values; the ischemic stroke features include demographic information, laboratory and clinical examination-related information, and medications. and information related to invasive treatments, information related to rehabilitation interventions;
所述医学特征值为人口统计、实验室和临床检查、药物和侵入性治疗和康复干预特征中各个医学特征的具体数值;The medical characteristic values are specific values of each medical characteristic among demographics, laboratory and clinical examinations, drugs and invasive treatment and rehabilitation intervention characteristics;
所述人口统计信息包括:性别、年龄、职业、婚姻状态、教育、身高、体重、BMI、收缩压、舒张压、心率、是否为首次脑血管意外、TOAST分型、OCSP分型、既往史、高血压病程、糖尿病病程、吸烟状态、烟龄、每日吸烟支数、吸烟指数、饮酒史、常规体育活动、家族史;The demographic information includes: gender, age, occupation, marital status, education, height, weight, BMI, systolic blood pressure, diastolic blood pressure, heart rate, whether it is the first cerebrovascular accident, TOAST classification, OCSP classification, past history, Duration of hypertension, duration of diabetes, smoking status, smoking age, number of cigarettes smoked per day, smoking index, drinking history, regular physical activities, family history;
所述既往史又包括缺血性卒中、出血性卒中、蛛网膜下腔出血、卒中未分类、高血压、糖尿病、血脂异常、房颤、冠心病、心梗、先天性心脏病、瓣膜性心脏病、其它类型心脏病、周围动脉疾病;所述家族史包括卒中、冠心病、高血压、糖尿病、血脂异常、颅内动脉瘤。The past medical history also includes ischemic stroke, hemorrhagic stroke, subarachnoid hemorrhage, unclassified stroke, hypertension, diabetes, dyslipidemia, atrial fibrillation, coronary heart disease, myocardial infarction, congenital heart disease, and valvular heart disease. disease, other types of heart disease, and peripheral arterial disease; the family history includes stroke, coronary heart disease, hypertension, diabetes, dyslipidemia, and intracranial aneurysm.
所述实验室和临床检查相关信息包括:糖化血红蛋白、甘油三脂、总胆固醇、低密度脂蛋白胆固醇、高密度脂蛋白胆固醇、脂蛋白a、同型半胱氨酸、部分凝血活酶时间、凝血酶原时间-国际标准化比值、心电图、结构影像学检查结果、颈总动脉狭窄、颈动脉球狭窄、颈内动脉狭窄、锁骨下动脉狭窄、左颈内动脉颅内狭窄、左侧大脑前动脉狭窄、左侧大脑中动脉狭窄、左脑后动脉狭窄、左椎动脉狭窄、右颈内动脉颅内狭窄、右大脑前动脉狭窄、右大脑中动脉狭窄、右大脑后动脉狭窄、右椎动脉狭窄、椎基底动脉狭窄、吞咽功能评估、洼田饮水试验;The laboratory and clinical examination-related information includes: glycosylated hemoglobin, triglycerides, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, lipoprotein A, homocysteine, partial thromboplastin time, coagulation Enzyme time - international normalized ratio, electrocardiogram, structural imaging examination results, common carotid artery stenosis, carotid bulb stenosis, internal carotid artery stenosis, subclavian artery stenosis, left internal carotid artery intracranial stenosis, left anterior cerebral artery stenosis , left middle cerebral artery stenosis, left posterior cerebral artery stenosis, left vertebral artery stenosis, right internal carotid artery intracranial stenosis, right anterior cerebral artery stenosis, right middle cerebral artery stenosis, right posterior cerebral artery stenosis, right vertebral artery stenosis, Vertebrobasilar artery stenosis, swallowing function assessment, Kubota drinking test;
所述心电图检测包括房颤、房扑、左室肥厚、Q波、急性心梗、心肌缺血及其它;所述结构影像学检查结果包括脑梗死后出血性转化、新发脑梗死、陈旧性脑梗塞及其它。The electrocardiogram detection includes atrial fibrillation, atrial flutter, left ventricular hypertrophy, Q wave, acute myocardial infarction, myocardial ischemia and others; the structural imaging examination results include hemorrhagic transformation after cerebral infarction, new cerebral infarction, old cerebral infarction and so on. Cerebral infarction and others.
所述药物和侵入性治疗相关信息包括:静脉溶栓、血管内治疗、 48小时内抗血小板治疗、48小时内抗凝治疗、降压药、调脂药、降糖药;The information related to the drugs and invasive treatments includes: intravenous thrombolysis, intravascular treatment, antiplatelet treatment within 48 hours, anticoagulant treatment within 48 hours, antihypertensive drugs, lipid-lowering drugs, and hypoglycemic drugs;
所述血管内治疗包括支架取栓、直接血栓抽吸、球囊扩张形成术、血管内支架辅助血管成形术、动脉内溶栓及机械溶栓;所述48小时内抗血小板治疗包括使用阿司匹林、氯吡格雷、奥扎格雷、双嘧达莫、噻氯匹定、西洛他唑及其它;所述48小时内抗凝治疗包括华法林、利伐沙班、达比加群、阿哌沙班、依多沙班、低分子肝素、普通肝素及其它;所述降压药包括血管紧张素转换酶抑制剂、血管紧张素受体阻滞剂、利尿剂、β受体阻滞剂、钙离子通道阻滞剂及其它;所述调脂药包括他汀、烟酸及其衍生物、贝特类、胆固醇吸收抑制剂及其它;所述降糖药还包括胰岛素、磺酰脲类、双胍类、糖苷酶抑制剂、胰岛素致敏剂、胰岛素分泌促进剂及其它。The intravascular treatment includes stent thrombectomy, direct thrombus aspiration, balloon dilatation, intravascular stent-assisted angioplasty, intra-arterial thrombolysis and mechanical thrombolysis; the antiplatelet treatment within 48 hours includes the use of aspirin, Clopidogrel, ozagrel, dipyridamole, ticlopidine, cilostazol and others; the anticoagulant treatment within 48 hours includes warfarin, rivaroxaban, dabigatran, apidogrel Saban, edoxaban, low molecular weight heparin, unfractionated heparin and others; the antihypertensive drugs include angiotensin-converting enzyme inhibitors, angiotensin receptor blockers, diuretics, beta-blockers, Calcium ion channel blockers and others; the lipid-lowering drugs include statins, niacin and its derivatives, fibrates, cholesterol absorption inhibitors and others; the hypoglycemic drugs also include insulin, sulfonylureas, biguanides classes, glycosidase inhibitors, insulin sensitizers, insulin secretion promoters and others.
所述康复干预相关信息包括:从发病至第一次康复干预时长、从发病至第一次动员时长、第一次康复干预中早期动员的效益、第一次康复干预中早期动员时长、14天早期动员总时长、14天早期动员平均时长、物理治疗时长、作业治疗时长、言语治疗时长、第一次14天进行连续物理治疗、第一次14天进行连续物理治疗、第一次14天进行连续言语治疗。The information related to rehabilitation intervention includes: the duration from onset to the first rehabilitation intervention, the duration from onset to the first mobilization, the benefit of early mobilization in the first rehabilitation intervention, the duration of early mobilization in the first rehabilitation intervention, 14 days Total duration of early mobilization, average duration of 14 days of early mobilization, duration of physical therapy, duration of occupational therapy, duration of speech therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy Continuous Speech Therapy.
S3:目标结果特征数据提取;S3: Target result feature data extraction;
取用于预测目标的卒中后时间评分,在不同时间步点提取mRS评分,提取时间步点主要包括mRS-0(基线为入院当天)、mRS-15(卒中后15天)、mRS-30(卒中后30天)、mRS-90(卒中后90 天)、mRS-180(卒中后180天);Take the post-stroke time score used to predict the target, and extract the mRS score at different time steps. The extracted time steps mainly include mRS-0 (baseline is the day of admission), mRS-15 (15 days after stroke), mRS-30 ( 30 days after stroke), mRS-90 (90 days after stroke), mRS-180 (180 days after stroke);
卒中后时间二分类结果有:有利结果为卒中后时间评分0-2,表现为无或最低失能;不利结果卒中后时间评分3-6,情况可能是中度或重度失能,或死亡。通过步骤S1到步骤S3可以得到缺血性卒中临床表现的大数据资料。The dichotomous outcomes of time after stroke include: favorable outcome, time after stroke score of 0-2, indicating no or minimal disability; unfavorable outcome, time after stroke score of 3-6, indicating moderate or severe disability, or death. Through steps S1 to S3, big data on the clinical manifestations of ischemic stroke can be obtained.
S4:特征数据标准化及对数据清洗;S4: Feature data standardization and data cleaning;
对S4得到的缺血性卒中临床表现的大数据资料进行特征数据标准化,采用缺失数据策略,排除特征变量缺失超过50%的患者,剩余特征缺失的数据在同一特征已有数据的模式下进行填充,连续变量的缺失值使用均值填充,分类变量的缺失值使用众数填充;所有数据经过标准化,使其均值和单位方差为零。Standardize the feature data on the big data on the clinical manifestations of ischemic stroke obtained in S4, and adopt a missing data strategy to exclude patients with more than 50% missing feature variables. The remaining missing feature data will be filled in under the mode of existing data for the same feature. , the missing values of continuous variables are filled with the mean, and the missing values of the categorical variables are filled with the mode; all data are standardized so that their mean and unit variance are zero.
S5:建立机器学习模型1——XGBoost;S5: Establish machine learning model 1—XGBoost;
将人口统计信息、实验室和临床检查相关信息、药物和侵入性治疗相关信息以及康复干预相关信息输入XGBoost模型中进行mRS90二分类预测;Input demographic information, laboratory and clinical examination-related information, drug and invasive treatment-related information, and rehabilitation intervention-related information into the XGBoost model for mRS90 binary prediction;
所述XGBoost包括XGBoost决策树以及XGBoost决策树之间的关系;所述XGBoost决策树包括多个结点;结点为医学特征及阈值;所述XGBoost决策树之间的关系为梯度下降优化算法,后一棵决策树由前一棵树决策树按照梯度下降优化算法得到;The XGBoost includes an XGBoost decision tree and the relationship between the XGBoost decision trees; the XGBoost decision tree includes multiple nodes; the nodes are medical features and thresholds; the relationship between the XGBoost decision trees is a gradient descent optimization algorithm, The latter decision tree is obtained from the previous decision tree according to the gradient descent optimization algorithm;
所述XGBoost模型中特征筛选:使用XGBoost自动找出最相关的特征,用于目标结果的mRS90二元分类;利用开发集上的初始特征对估计器进行训练,并通过网格搜索技术进行参数调整或超参数优 化的三折交叉验证,训练后的模型生成排序的关键特征,通过为每个变量分配一个权重来量化其相对重要性;所述“权重”表示使用该特性在所有树中分割数据的总次数,以度量XGBoost中的特征重要性;Feature screening in the XGBoost model: Use XGBoost to automatically find the most relevant features for mRS90 binary classification of target results; use the initial features on the development set to train the estimator, and perform parameter adjustment through grid search technology or three-fold cross-validation for hyperparameter optimization, the trained model generates ranked key features, quantifying its relative importance by assigning a weight to each variable; said "weight" represents the use of that feature to split the data in all trees The total number of times to measure the feature importance in XGBoost;
所述XGBoost模型中特征分析:对标准数据样本进行计算,筛选相关特征的统计学方法为T检验、Mann-Whitney U检验、Kruskal-Wallis单因素方差分析;其中T检验、Mann-Whitney U检验、Kruskal-Wallis单因素方差分析是统计学中常用的一种方法;本发明用上述统计学方法及相关软件进行计算,得到概率值P,我们设定P值小于0.05的,可以认为选取的特征与缺血性mRS90二分类目标存在极其显著的相关关系,选取这些特征建立模型是合理的;其次对筛选出的特征变量以及所有康复干预相关信息进行层次聚类分析;所述层次聚类使用的评价标准为‘enclidean’,方法选择Ward’s method,具体实现采用开源工具库seaborn;Feature analysis in the XGBoost model: Calculate standard data samples, and the statistical methods for screening relevant features are T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance; among which T test, Mann-Whitney U test, Kruskal-Wallis one-factor analysis of variance is a commonly used method in statistics; the present invention uses the above statistical method and related software to calculate and obtain the probability value P. We set the P value less than 0.05, and it can be considered that the selected features are consistent with There is an extremely significant correlation between the ischemic mRS90 two-category targets, and it is reasonable to select these features to build a model; secondly, hierarchical clustering analysis was performed on the selected feature variables and all rehabilitation intervention-related information; evaluation of the use of hierarchical clustering The standard is 'enclidean', the method is Ward's method, and the specific implementation uses the open source tool library seaborn;
使用选择出来的人口学特征信息和临床特征信息、所有康复干预相关的特征信息和mRS首次作为输入信息进行建模实验;Use the selected demographic and clinical characteristic information, all rehabilitation intervention-related characteristic information and mRS as input information for the first time to conduct a modeling experiment;
所述建模试验是指使用XGBoost、SVM、random forest(RF)、Logistic Regression(LR)四种机器学习算法在开发集Develop Set进行建模,在建模过程中,每种机器学习方法都使用网格搜索方法系统的进行自动化超参数调优,网格搜索过程中使用F1score作为模型评价标准,采用5折交叉验证选择最优模型;The modeling test refers to using four machine learning algorithms: The grid search method systematically performs automated hyperparameter tuning. During the grid search process, F1score is used as the model evaluation criterion, and 5-fold cross-validation is used to select the optimal model;
上述步骤筛选的特征信息包括以下:The characteristic information filtered in the above steps includes the following:
人口学和临床信息:烟龄、降糖药(双胍类)、每日吸烟支数、 既往史(糖尿病)、48小时内抗血小板治疗、48小时内抗凝治疗(其它)、饮酒史、家族史(卒中)、颈动脉血管检查(颈动脉球动脉狭窄)、家族史(高血压)、职业、糖尿病病程(年)、家族史(冠心病)、收缩压、是否为首次脑血管意外、影像(新发脑梗死)、教育、吞咽功能评估、48小时内抗凝治疗、结果影像学检查结果(陈旧性脑梗塞)、脂蛋白(a)、结果影像学检查结果(其它)、既往史(高血压)、高血压病程(年)、降压药(血管紧张素转换酶抑制剂)、心率、性别、调脂药、年龄、甘油三酯、OSCP分型、部分凝血活酶时间、总胆固醇、体重、凝血酶原时间-国际标准化比值、同型半胱胺酸、高密度脂蛋白胆固醇、糖化血红蛋白、洼田饮水试验、舒张压、右颈内动脉颅内狭窄、颈内动脉狭窄、身高、TOAST分型、BMI、低密度脂蛋白胆固醇;Demographic and clinical information: smoking age, antidiabetic drugs (biguanides), number of cigarettes smoked per day, past medical history (diabetes), antiplatelet treatment within 48 hours, anticoagulant treatment within 48 hours (other), drinking history, family History (stroke), carotid artery vascular examination (carotid bulbar artery stenosis), family history (hypertension), occupation, duration of diabetes (years), family history (coronary heart disease), systolic blood pressure, whether it is the first cerebrovascular accident, imaging (new cerebral infarction), education, swallowing function assessment, anticoagulation treatment within 48 hours, resultant imaging examination results (old cerebral infarction), lipoprotein (a), resultant imaging examination results (other), past history ( Hypertension), duration of hypertension (years), antihypertensive drugs (angiotensin-converting enzyme inhibitors), heart rate, gender, lipid-lowering drugs, age, triglycerides, OSCP classification, partial thromboplastin time, total cholesterol , weight, prothrombin time-international normalized ratio, homocysteine, high-density lipoprotein cholesterol, glycosylated hemoglobin, Kubota water test, diastolic blood pressure, right internal carotid artery intracranial stenosis, internal carotid artery stenosis, height, TOAST classification, BMI, low-density lipoprotein cholesterol;
康复干预相关信息:从发病至首次康复治疗时长(小时)、从发病至首次离床时间(小时)、首次康复治疗中是否完成离床、首次离床康复治疗中离床状态维持时间(分钟)、14天离床总时长、14天离床平均时长(分钟)、物理治疗时长(天)、作业治疗时长(天)、言语治疗时长(天)、14天进行连续物理治疗、14天进行连续物理治疗、14天进行连续言语治疗;Rehabilitation intervention related information: length of time from onset to first rehabilitation treatment (hours), time from onset to first out of bed (hours), whether out of bed was completed during the first rehabilitation treatment, time to maintain out of bed state during first out of bed rehabilitation treatment (minutes) , Total time out of bed in 14 days, Average time out of bed in 14 days (minutes), Physical therapy duration (days), Occupational therapy duration (days), Speech therapy duration (days), 14 days of continuous physical therapy, 14 days of continuous Physical therapy, continuous speech therapy for 14 days;
时间步信息(天):取值为{0,15,30,90,180}。Time step information (days): The value is {0, 15, 30, 90, 180}.
S6:建立机器学习模型2——CNN-LSTM;S6: Establish machine learning model 2—CNN-LSTM;
利用卷积神经网络--CNN作为主干网络与带有遗忘门的长短期记忆网络模型--LSTM结合,以患者在每个时间步的康复为重点,以 及mRS康复发展情况进行时序建模。Using the convolutional neural network - CNN as the backbone network and the long short-term memory network model with forget gate - LSTM, we focus on the patient's recovery at each time step and conduct time series modeling on the mRS recovery development.
所述模型采用的信息包括由XGBoost筛选出的人口学特征信息和临床特征信息、所有康复干预相关的特征信息、mRS评分和对应的时间步信息;其中人口学特征信息和临床特征信息、所有康复干预相关的特征信息属于非时序信息,mRS评分属于时序信息;所述mRS评分包括mRS-0、mRS-15、mRS-30、mRS-90、mRS-180的评分;The information used by the model includes demographic feature information and clinical feature information screened out by Intervention-related feature information is non-sequential information, and mRS scores are temporal information; the mRS scores include mRS-0, mRS-15, mRS-30, mRS-90, and mRS-180 scores;
采用上述所述信息作为输入信息,构建级联卷积神经网络和循环神经网络的网络结构,为了让每一时间步都能获取到病人的非时序状态信息,首先使用堆叠多层全连接层的卷积神经网络对非时序状态信息进行特征聚合、提取,最终经过sigmoid激活函数作为非时序状态信息的得分;Using the above information as input information, the network structure of the cascaded convolutional neural network and the recurrent neural network is constructed. In order to obtain the patient's non-sequential status information at each time step, first use stacked multiple layers of fully connected layers. The convolutional neural network performs feature aggregation and extraction on the non-sequential state information, and finally uses the sigmoid activation function as the score of the non-sequential state information;
随后应用CNN堆叠多个完整的连接层聚合,提取特征非连续的状态信息,其次采用上述所述函数生成非时序的状态信息;Then apply CNN to stack multiple complete connection layer aggregation to extract feature discontinuous state information, and then use the above function to generate non-sequential state information;
将生成的分数与时序信息和相应的时间步信息结合,融合到LSTM网络中;Combine the generated scores with timing information and corresponding time step information and integrate them into the LSTM network;
采用LSTM模型训练学习每个患者的mRS康复发展变化;Use LSTM model training to learn the mRS rehabilitation development changes of each patient;
最后,利用注意机制进行跨时间步的特征加权融合,使每个时间步的mRS预测更接近当前时间步之前所有时间步的mRS;Finally, the attention mechanism is used to perform weighted fusion of features across time steps, so that the mRS prediction at each time step is closer to the mRS at all time steps before the current time step;
上述所使用的损失函数公式如下:The loss function formula used above is as follows:
L
total=θL
mse+(1-θ)L
fn
L total =θL mse +(1-θ)L fn
其中L
total表示总体的损失,Lmse表示加权的均方差损失函数,L
fn表示加权的focal loss损失函数(focal loss可以有效减轻多个时间步之间复杂的类别不平衡问题,并进行难样本挖掘),mse表示均方差损失函数(可使不同时间步的预测效能更加均衡),W
mask表示加权系数,θ表示weighting fator,取值范围为[0,1],本模型取值为0.25;P表示预测结果,p’表示标签,N表示样本个数,α为weighting fator,取值范围为[0,1],本模型取值为1;γ表示focusing parameter,取值范围一般为[0,5],本模型取值为2。
where L total represents the overall loss, Lmse represents the weighted mean square error loss function, and L fn represents the weighted focal loss loss function (focal loss can effectively alleviate the complex category imbalance problem between multiple time steps and perform difficult sample mining ), mse represents the mean square error loss function (which can make the prediction performance at different time steps more balanced), W mask represents the weighting coefficient, θ represents the weighting factor, the value range is [0,1], and the value of this model is 0.25; P represents the prediction result, p' represents the label, N represents the number of samples, α is the weighting factor, the value range is [0,1], this model takes the value 1; γ represents the focusing parameter, the value range is generally [0, 5], the value of this model is 2.
S7:建立机器学习模型3——刺激观察-关键点选择;S7: Establish machine learning model 3 - stimulus observation - key point selection;
利用已经训练好的时序模型在不同的mRS缺失情况下进行测试评估,以便更好地探究随访过程每一时间步mRS评分对病人康复情况的影响;Use the already trained time-series model to conduct testing and evaluation under different mRS loss conditions to better explore the impact of mRS scores on the patient's recovery at each time step of the follow-up process;
所述时序模型是指通过学习开发集中病人每个时间步的康复情况进而对康复进展进行了仿真建模,改变模型的输入得到不同情况下的康复进展;The time series model refers to the simulation modeling of the rehabilitation progress by focusing on the patient's recovery situation at each time step through learning and development, and changing the input of the model to obtain the rehabilitation progress under different circumstances;
通过上述模型输入的改变,对比不同时间步下mRS评分的影响程度;在该模型中,利用mRS-180代表病人最终的康复状态,然后使用mRS-15、mRS-30、mRS-90这三个时间步中探索分析mRS评分 的缺失的影响。Through the changes in the input of the above model, the impact of mRS scores at different time steps is compared; in this model, mRS-180 is used to represent the patient's final recovery status, and then mRS-15, mRS-30, and mRS-90 are used to represent the patient's final recovery status. The impact of missing mRS scores was explored and analyzed in time steps.
S8:结果对比,选择模型;S8: Compare results and select model;
经过S5、S6以及S7的结果对比后得到特异性和敏感性最好的是CNN-LSTM模型,判定其为缺血性脑卒中早期康复后功能预后的预测模型。After comparing the results of S5, S6 and S7, it was found that the CNN-LSTM model had the best specificity and sensitivity, and was judged to be a predictive model for functional prognosis after early recovery from ischemic stroke.
本发明已由上述相关实施例加以描述,然而上述实施例仅为实施本发明的范例。必需指出的是,已揭露的实施例并未限制本发明的范围。相反地,在不脱离本发明的精神和范围内所作的更动与润饰,均属本发明的专利保护范围。The present invention has been described by the above-mentioned relevant embodiments, but the above-mentioned embodiments are only examples of implementing the present invention. It must be noted that the disclosed embodiments do not limit the scope of the present invention. On the contrary, any changes and modifications made without departing from the spirit and scope of the present invention shall fall within the scope of patent protection of the present invention.
Claims (4)
- 一种基于深度学习的脑卒中早期康复后功能预测模型建立方法,其特征在于:所述模型建立方法包括以下步骤:A deep learning-based method for establishing a functional prediction model after early recovery from stroke, characterized in that: the model establishment method includes the following steps:S1:建立数据病库;S1: Establish a data disease database;准备病历数据,从医院电子病历平台采集患者电子病历,搜集进行早期康复的缺血性脑卒中患者的电子病历;以第一诊断为缺血性脑卒中的病例的病历数据为合格的电子病历数据;Prepare medical record data, collect patient electronic medical records from the hospital electronic medical record platform, and collect electronic medical records of ischemic stroke patients undergoing early rehabilitation; use the medical record data of the first case diagnosed with ischemic stroke as qualified electronic medical record data. ;S2:提取病患医学特征数据;S2: Extract patient medical characteristic data;对S1中得到的合格的电子病历数据进行缺血性脑卒中医学特征提取,提取医学特征及医学特征值;所述缺血性脑卒中特征包括人口统计信息、实验室和临床检查相关信息、药物和侵入性治疗相关信息、康复干预相关信息;用于作为预测的素材;Extract ischemic stroke medical features from the qualified electronic medical record data obtained in S1, and extract medical features and medical feature values; the ischemic stroke features include demographic information, laboratory and clinical examination-related information, and medications. Information related to invasive treatment and rehabilitation intervention; used as material for prediction;S3:目标结果特征数据提取;S3: Target result feature data extraction;在不同时间步点提取卒中后评分,提取的时间步点主要包括入院当天、卒中后15天、卒中后30天、卒中后90天、卒中后180天;提取用于预测目标的卒中后时间评分,Extract post-stroke scores at different time steps. The extracted time steps mainly include the day of admission, 15 days after stroke, 30 days after stroke, 90 days after stroke, and 180 days after stroke; extract the post-stroke time score used to predict the target ,卒中后时间二分类结果有:有利结果为卒中后时间评分0-2,不利结果卒中后时间评分3-6,情况可能是中度或重度失能,或死亡;通过S1到步骤S3可以得到缺血性卒中临床表现的大数据资料;The two-category results of time after stroke include: a favorable outcome is a time after stroke score of 0-2, an unfavorable outcome is a time after stroke score of 3-6, which may be moderate or severe disability, or death; the missing results can be obtained through steps S1 to S3. Big data on clinical manifestations of hemorrhagic stroke;S4:特征数据标准化及对数据清洗;S4: Feature data standardization and data cleaning;对S3得到的缺血性卒中临床表现的大数据资料进行特征数据标准化,采用缺失数据策略,排除特征变量缺失超过50%的患者,剩余特征缺失的数据在同一特征已有数据的模式下进行填充,连续变量的 缺失值使用均值填充,分类变量的缺失值使用众数填充;所有数据经过标准化,使其均值和单位方差为零;Standardize the feature data on the big data on the clinical manifestations of ischemic stroke obtained in S3, and adopt a missing data strategy to exclude patients with more than 50% missing feature variables. The remaining missing feature data will be filled in under the mode of existing data for the same feature. , the missing values of continuous variables are filled with the mean, and the missing values of the categorical variables are filled with the mode; all data are standardized so that their mean and unit variance are zero;S5:建立机器学习模型1——XGBoost;S5: Establish machine learning model 1—XGBoost;将步骤S2中提取到的人口统计信息、实验室和临床检查相关信息、药物和侵入性治疗相关信息以及康复干预相关信息输入XGBoost模型中进行mRS90二分类预测;Input the demographic information, laboratory and clinical examination-related information, drug and invasive treatment-related information, and rehabilitation intervention-related information extracted in step S2 into the XGBoost model for mRS90 binary prediction;所述XGBoost模型包括XGBoost决策树以及XGBoost决策树之间的关系;所述XGBoost决策树包括多个结点;结点为医学特征及阈值;所述XGBoost决策树之间的关系为梯度下降优化算法,后一棵决策树由前一棵树决策树按照梯度下降优化算法得到;对XGBoost模型进行特征筛选以及特征分析;使用XGBoost的方式筛选出了特征变量并进行了建模,最终建立了一个XGBoost预测模型;The XGBoost model includes an XGBoost decision tree and the relationship between the XGBoost decision trees; the XGBoost decision tree includes multiple nodes; the nodes are medical features and thresholds; the relationship between the XGBoost decision trees is a gradient descent optimization algorithm , the latter decision tree is obtained from the previous decision tree according to the gradient descent optimization algorithm; feature screening and feature analysis are performed on the XGBoost model; feature variables are screened out and modeled using XGBoost, and finally an XGBoost is established Predictive models;S6:建立机器学习模型2——CNN-LSTM;S6: Establish machine learning model 2—CNN-LSTM;利用卷积神经网络CNN作为主干网络与带有遗忘门的长短期记忆网络模型--LSTM结合,以患者在每个时间步的康复为重点,以及mRS康复发展情况进行时序建模。The convolutional neural network CNN is used as the backbone network and combined with the long short-term memory network model with forgetting gate - LSTM, focusing on the patient's recovery at each time step, as well as the mRS recovery development situation for time-series modeling.所述CNN-LSTM模型采用的信息包括由XGBoost筛选出的人口学特征信息和临床特征信息、所有康复干预相关的特征信息、mRS评分和对应的时间步信息;其中人口学特征信息和临床特征信息、所有康复干预相关的特征信息属于非时序信息,mRS评分属于时序信息;所述mRS评分包括mRS-0、mRS-15、mRS-30、mRS-90、mRS-180的评分;The information used by the CNN-LSTM model includes demographic feature information and clinical feature information filtered by XGBoost, all rehabilitation intervention-related feature information, mRS scores and corresponding time step information; among them, demographic feature information and clinical feature information , All the characteristic information related to rehabilitation intervention belongs to non-sequential information, and the mRS score belongs to temporal information; the mRS score includes the scores of mRS-0, mRS-15, mRS-30, mRS-90, and mRS-180;采用上述人口学特征信息和临床特征信息、所有康复干预相关的特征信息、mRS评分和对应的时间步信息作为输入信息,构建级联卷积神经网络和循环神经网络的网络结构,为了让每一时间步都能获取到病人的非时序状态信息,首先使用堆叠多层全连接层的卷积神经网络对非时序状态信息进行特征聚合、提取,最终经过sigmoid激活函数作为非时序状态信息的得分;随后应用CNN堆叠多个完整的连接层聚合,提取特征非连续的状态信息,其次采用上述所述的sigmoid激活函数生成非时序的状态信息;将生成的分数与时序信息和相应的时间步信息结合,融合到LSTM网络中;采用LSTM模型训练学习每个患者的mRS康复发展变化;最后,利用注意机制进行跨时间步的特征加权融合,使每个时间步的mRS预测更接近当前时间步之前所有时间步的mRS;Using the above demographic characteristic information and clinical characteristic information, all rehabilitation intervention-related characteristic information, mRS scores and corresponding time step information as input information, the network structure of the cascade convolutional neural network and the recurrent neural network is constructed. In order to allow each The patient's non-sequential state information can be obtained at every time step. First, a convolutional neural network stacked with multiple fully connected layers is used to aggregate and extract features of the non-sequential state information, and finally the sigmoid activation function is used as the score of the non-sequential state information; Then apply CNN to stack multiple complete connection layer aggregation to extract feature discontinuous state information. Secondly, use the sigmoid activation function mentioned above to generate non-sequential state information; combine the generated scores with temporal information and corresponding time step information. , integrated into the LSTM network; LSTM model training is used to learn the mRS rehabilitation development changes of each patient; finally, the attention mechanism is used to perform weighted fusion of features across time steps, so that the mRS prediction at each time step is closer to all the mRS predictions before the current time step. mRS at time step;步骤S6是利用步骤S5中筛选出的特征变量,用卷积神经网络--CNN作为主干网络与带有遗忘门的长短期记忆网络模型--LSTM结合的方式,建立了一个CNN-LSTM预测模型;Step S6 is to use the feature variables screened out in step S5 to establish a CNN-LSTM prediction model by combining the convolutional neural network - CNN as the backbone network with the long short-term memory network model with forget gate - LSTM. ;S7:建立机器学习模型3——刺激观察-关键点选择;S7: Establish machine learning model 3 - stimulus observation - key point selection;利用已经在步骤S6中训练好的CNN-LSTM模型在不同的mRS缺失情况下进行测试评估,以便更好地探究随访过程每一时间步mRS评分对病人康复情况的影响;Use the CNN-LSTM model that has been trained in step S6 to conduct testing and evaluation under different mRS loss conditions to better explore the impact of mRS scores on the patient's recovery at each time step of the follow-up process;所述CNN-LSTM模型是指通过学习开发集中病人每个时间步的康复情况进而对康复进展进行了仿真建模,改变模型的输入得到不同情况下的康复进展;The CNN-LSTM model refers to the simulation modeling of the rehabilitation progress by focusing on the patient's recovery situation at each time step through learning and development, and changing the input of the model to obtain the rehabilitation progress under different circumstances;通过CNN-LSTM模型输入的改变,对比不同时间步下mRS评分的影响程度;在该模型中,利用mRS-180代表病人最终的康复状态,然后使用mRS-15、mRS-30、mRS-90这三个时间步中探索分析mRS评分的缺失的影响;Through changes in the input of the CNN-LSTM model, the impact of mRS scores at different time steps is compared; in this model, mRS-180 is used to represent the patient's final recovery status, and then mRS-15, mRS-30, and mRS-90 are used to represent the patient's final recovery status. Explore and analyze the impact of missing mRS scores in three time steps;步骤7是重复数次步骤6建模过程,但每次建模时在步骤6的基础上减少一个变量(每次减少一个时间步下的mRS评分),比较不同建模的结果,得到一个预测效能最好的模型;Step 7 is to repeat the modeling process of step 6 several times, but reduce one variable on the basis of step 6 each time (reduce the mRS score at one time step each time), compare the results of different modeling, and obtain a prediction The best performing model;S8:结果对比,选择模型;S8: Compare results and select model;经过S5、S6以及S的结果对比后得到特异性和敏感性最好的是CNN-LSTM模型,判定其为缺血性脑卒中早期康复后功能预后的预测模型。After comparing the results of S5, S6 and S, it was found that the CNN-LSTM model had the best specificity and sensitivity, and was judged to be a predictive model for functional prognosis after early recovery from ischemic stroke.
- 如权利要求1所述的一种基于深度学习的脑卒中早期康复后功能预测模型建立方法,其特征在于:所述步骤S2中,所述医学特征值为人口统计、实验室和临床检查、药物和侵入性治疗和康复干预特征中各个医学特征的具体数值;所述人口统计信息包括性别、年龄、职业、婚姻状态、教育、身高、体重、BMI、收缩压、舒张压、心率、是否为首次脑血管意外、TOAST分型、OCSP分型、既往史、高血压病程、糖尿病病程、吸烟状态、烟龄、每日吸烟支数、吸烟指数、饮酒史、常规体育活动以及家族史;所述实验室和临床检查相关信息包括糖化血红蛋白、甘油三脂、总胆固醇、低密度脂蛋白胆固醇、高密度脂蛋白胆固醇、脂蛋白a、同型半胱氨酸、部分凝血活酶时间、凝血酶原时间-国际标准化比值、心电图、结构影像学检查结果、颈 总动脉狭窄、颈动脉球狭窄、颈内动脉狭窄、锁骨下动脉狭窄、左颈内动脉颅内狭窄、左侧大脑前动脉狭窄、左侧大脑中动脉狭窄、左脑后动脉狭窄、左椎动脉狭窄、右颈内动脉颅内狭窄、右大脑前动脉狭窄、右大脑中动脉狭窄、右大脑后动脉狭窄、右椎动脉狭窄、椎基底动脉狭窄、吞咽功能评估、洼田饮水试验;所述药物和侵入性治疗相关信息包括:静脉溶栓、血管内治疗、48小时内抗血小板治疗、48小时内抗凝治疗、降压药、调脂药、降糖药;所述康复干预相关信息包括从发病至第一次康复干预时长、从发病至第一次动员时长、第一次康复干预中早期动员的效益、第一次康复干预中早期动员时长、14天早期动员总时长、14天早期动员平均时长、物理治疗时长、作业治疗时长、言语治疗时长、第一次14天进行连续物理治疗、第一次14天进行连续物理治疗、第一次14天进行连续言语治疗。A method for establishing a functional prediction model after early recovery from stroke based on deep learning according to claim 1, characterized in that: in the step S2, the medical characteristic values are demographics, laboratory and clinical examinations, drugs and the specific values of each medical characteristic in the characteristics of invasive treatment and rehabilitation intervention; the demographic information includes gender, age, occupation, marital status, education, height, weight, BMI, systolic blood pressure, diastolic blood pressure, heart rate, whether it is the first time Cerebrovascular accident, TOAST classification, OCSP classification, past history, hypertension duration, diabetes duration, smoking status, smoking age, number of cigarettes smoked per day, smoking index, drinking history, regular physical activities and family history; the experiment Laboratory and clinical examination-related information includes glycosylated hemoglobin, triglycerides, total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, lipoprotein A, homocysteine, partial thromboplastin time, prothrombin time - International normalized ratio, electrocardiogram, structural imaging examination results, common carotid artery stenosis, carotid bulb stenosis, internal carotid artery stenosis, subclavian artery stenosis, left internal carotid artery intracranial stenosis, left anterior cerebral artery stenosis, left brain Middle artery stenosis, left posterior cerebral artery stenosis, left vertebral artery stenosis, right internal carotid artery intracranial stenosis, right anterior cerebral artery stenosis, right middle cerebral artery stenosis, right posterior cerebral artery stenosis, right vertebral artery stenosis, vertebrobasilar artery stenosis , swallowing function assessment, Kubota drinking test; the information related to the drugs and invasive treatments includes: intravenous thrombolysis, endovascular treatment, antiplatelet treatment within 48 hours, anticoagulant treatment within 48 hours, antihypertensive drugs, lipid-lowering drugs , hypoglycemic drugs; the rehabilitation intervention related information includes the duration from onset to the first rehabilitation intervention, the duration from onset to the first mobilization, the benefits of early mobilization in the first rehabilitation intervention, early mobilization in the first rehabilitation intervention Duration, total duration of 14 days of early mobilization, average duration of 14 days of early mobilization, duration of physical therapy, duration of occupational therapy, duration of speech therapy, first 14 days of continuous physical therapy, first 14 days of continuous physical therapy, first Continuous speech therapy was performed for 14 days.
- 如权利要求1所述的一种基于深度学习的脑卒中早期康复后功能预测模型建立方法,其特征在于:所述步骤S5中XGBoost模型特征筛选是指使用XGBoost自动找出最相关的特征,用于目标结果的mRS90二元分类;利用开发集上的初始特征对估计器进行训练,并通过网格搜索技术进行参数调整或超参数优化的三折交叉验证,训练后的模型生成排序的关键特征,通过为每个变量分配一个权重来量化其相对重要性;所述XGBoost模型特征分析是指对标准数据样本进行计算,筛选相关特征的统计学方法为T检验、Mann-Whitney U检验、Kruskal-Wallis单因素方差分析;其次对筛选出的特征变量以及所有康复干预相关信息进行层次聚类分析;所述层次聚类使用的评价 标准为‘enclidean’,方法选择Ward’s method,具体实现采用开源工具库seaborn;使用选择出来的人口学特征信息和临床特征信息、所有康复干预相关的特征信息和mRS首次作为输入信息进行建模实验。A method for establishing a functional prediction model after early recovery from stroke based on deep learning as claimed in claim 1, characterized in that: the XGBoost model feature screening in step S5 refers to using XGBoost to automatically find the most relevant features. mRS90 binary classification of target results; use the initial features on the development set to train the estimator, and perform three-fold cross-validation of parameter adjustment or hyperparameter optimization through grid search technology. The trained model generates key features for ranking , quantifying its relative importance by assigning a weight to each variable; the XGBoost model feature analysis refers to the calculation of standard data samples, and the statistical methods for screening relevant features are T test, Mann-Whitney U test, Kruskal- Wallis single-factor variance analysis; secondly, hierarchical cluster analysis was performed on the selected characteristic variables and all rehabilitation intervention-related information; the evaluation standard used for the hierarchical clustering was 'enclidean', the method was Ward's method, and the open source tool library was used for the specific implementation seaborn; uses the selected demographic feature information and clinical feature information, all rehabilitation intervention-related feature information and mRS as input information for the first time to conduct modeling experiments.
- 如权利要求3所述的一种基于深度学习的脑卒中早期康复后功能预测模型建立方法,其特征在于:所述建模试验是指使用XGBoost、SVM、random forest(RF)、Logistic Regression(LR)四种机器学习算法在开发集Develop Set进行建模,在建模过程中,每种机器学习方法都使用网格搜索方法系统的进行自动化超参数调优,网格搜索过程中使用F1 score作为模型评价标准,采用5折交叉验证选择的最优模型。A method for establishing a functional prediction model after early recovery from stroke based on deep learning as claimed in claim 3, characterized in that: the modeling test refers to using XGBoost, SVM, random forest (RF), Logistic Regression (LR ) Four machine learning algorithms are modeled in the Develop Set. During the modeling process, each machine learning method uses the grid search method to systematically perform automated hyperparameter tuning. The F1 score is used as the grid search process. The model evaluation standard uses 5-fold cross-validation to select the optimal model.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210681225.2A CN115019919B (en) | 2022-06-16 | 2022-06-16 | Deep learning-based method for establishing function prediction model after early recovery of stroke |
CN202210681225.2 | 2022-06-16 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023241012A1 true WO2023241012A1 (en) | 2023-12-21 |
Family
ID=83074245
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/143730 WO2023241012A1 (en) | 2022-06-16 | 2022-12-30 | Method for establishing deep learning-based model for predicting functions after post-cerebral stroke early rehabilitation |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN115019919B (en) |
WO (1) | WO2023241012A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117524464A (en) * | 2024-01-04 | 2024-02-06 | 北京和兴创联健康科技有限公司 | Method and system for calculating postoperative target hemoglobin based on big data |
CN117637154A (en) * | 2024-01-27 | 2024-03-01 | 南通大学附属医院 | Nerve internal department severe index prediction method and system based on optimization algorithm |
CN117828490A (en) * | 2024-03-06 | 2024-04-05 | 南京信息工程大学 | Typhoon disaster forecasting method and system based on ensemble learning |
CN117828490B (en) * | 2024-03-06 | 2024-05-17 | 南京信息工程大学 | Typhoon disaster forecasting method and system based on ensemble learning |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115019919B (en) * | 2022-06-16 | 2023-04-07 | 江苏省人民医院(南京医科大学第一附属医院) | Deep learning-based method for establishing function prediction model after early recovery of stroke |
CN116403714B (en) * | 2023-04-07 | 2024-01-26 | 大连市中心医院 | Cerebral apoplexy END risk prediction model building method and device, END risk prediction system, electronic equipment and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018143540A1 (en) * | 2017-02-02 | 2018-08-09 | 사회복지법인 삼성생명공익재단 | Method, device, and program for predicting prognosis of stomach cancer by using artificial neural network |
US20190246904A1 (en) * | 2016-10-20 | 2019-08-15 | Jlk Inspection | Stroke diagnosis and prognosis prediction method and system |
CN111899894A (en) * | 2020-08-03 | 2020-11-06 | 东南大学 | System and method for evaluating prognosis drug effect of depression patient |
CN113808747A (en) * | 2021-10-11 | 2021-12-17 | 南昌大学第二附属医院 | Ischemic stroke recurrence prediction method |
CN113988209A (en) * | 2021-11-09 | 2022-01-28 | 昆明同心医联科技有限公司 | Training method and device of stroke prognosis prediction model |
CN114203295A (en) * | 2021-11-23 | 2022-03-18 | 国家康复辅具研究中心 | Cerebral apoplexy risk prediction intervention method and system |
CN115019919A (en) * | 2022-06-16 | 2022-09-06 | 江苏省人民医院(南京医科大学第一附属医院) | Deep learning-based method for establishing function prediction model after early recovery of stroke |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111513704B (en) * | 2020-06-09 | 2021-06-25 | 首都医科大学附属北京天坛医院 | Index and system for predicting prognosis of acute ischemic stroke patient receiving revascularization treatment |
CN113040711B (en) * | 2021-03-03 | 2023-08-18 | 吾征智能技术(北京)有限公司 | Cerebral apoplexy incidence risk prediction system, equipment and storage medium |
CN114587385B (en) * | 2022-02-25 | 2022-11-01 | 之江实验室 | Method for constructing post-stroke rehabilitation assessment deep learning model based on brain muscle network graph theory characteristics |
-
2022
- 2022-06-16 CN CN202210681225.2A patent/CN115019919B/en active Active
- 2022-12-30 WO PCT/CN2022/143730 patent/WO2023241012A1/en unknown
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190246904A1 (en) * | 2016-10-20 | 2019-08-15 | Jlk Inspection | Stroke diagnosis and prognosis prediction method and system |
WO2018143540A1 (en) * | 2017-02-02 | 2018-08-09 | 사회복지법인 삼성생명공익재단 | Method, device, and program for predicting prognosis of stomach cancer by using artificial neural network |
CN111899894A (en) * | 2020-08-03 | 2020-11-06 | 东南大学 | System and method for evaluating prognosis drug effect of depression patient |
CN113808747A (en) * | 2021-10-11 | 2021-12-17 | 南昌大学第二附属医院 | Ischemic stroke recurrence prediction method |
CN113988209A (en) * | 2021-11-09 | 2022-01-28 | 昆明同心医联科技有限公司 | Training method and device of stroke prognosis prediction model |
CN114203295A (en) * | 2021-11-23 | 2022-03-18 | 国家康复辅具研究中心 | Cerebral apoplexy risk prediction intervention method and system |
CN115019919A (en) * | 2022-06-16 | 2022-09-06 | 江苏省人民医院(南京医科大学第一附属医院) | Deep learning-based method for establishing function prediction model after early recovery of stroke |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117524464A (en) * | 2024-01-04 | 2024-02-06 | 北京和兴创联健康科技有限公司 | Method and system for calculating postoperative target hemoglobin based on big data |
CN117524464B (en) * | 2024-01-04 | 2024-04-05 | 北京和兴创联健康科技有限公司 | Method and system for calculating postoperative target hemoglobin based on big data |
CN117637154A (en) * | 2024-01-27 | 2024-03-01 | 南通大学附属医院 | Nerve internal department severe index prediction method and system based on optimization algorithm |
CN117637154B (en) * | 2024-01-27 | 2024-03-29 | 南通大学附属医院 | Nerve internal department severe index prediction method and system based on optimization algorithm |
CN117828490A (en) * | 2024-03-06 | 2024-04-05 | 南京信息工程大学 | Typhoon disaster forecasting method and system based on ensemble learning |
CN117828490B (en) * | 2024-03-06 | 2024-05-17 | 南京信息工程大学 | Typhoon disaster forecasting method and system based on ensemble learning |
Also Published As
Publication number | Publication date |
---|---|
CN115019919A (en) | 2022-09-06 |
CN115019919B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023241012A1 (en) | Method for establishing deep learning-based model for predicting functions after post-cerebral stroke early rehabilitation | |
Krishnani et al. | Prediction of coronary heart disease using supervised machine learning algorithms | |
Sk et al. | Coronary Heart Disease Prediction and Classification using Hybrid Machine Learning Algorithms | |
CN111261282A (en) | Sepsis early prediction method based on machine learning | |
Kalaiselvi et al. | Prediction of heart diseases and cancer in diabetic patients using data mining techniques | |
US11735321B2 (en) | System for the prognostics of the chronic diseases after the medical examination based on the multi-label learning | |
Altikardes et al. | A novel method for dipper/non-dipper pattern classification in hypertensive and non-diabetic patients | |
CN109273093A (en) | A kind of construction method and building system of Kawasaki disease risk evaluation model | |
CN109243604A (en) | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on neural network algorithm | |
Gaikwad et al. | Effective study of machine learning algorithms for heart disease prediction | |
CN116580847B (en) | Method and system for predicting prognosis of septic shock | |
CN116403714B (en) | Cerebral apoplexy END risk prediction model building method and device, END risk prediction system, electronic equipment and medium | |
Serhani et al. | ECG-based arrhythmia classification & clinical suggestions: An incremental approach of hyperparameter tuning | |
Kaya | Performance evaluation of multilayer perceptron artificial neural network model in the classification of heart failure | |
Mora et al. | Machine learning to predict major bleeding during anticoagulation for venous thromboembolism: possibilities and limitations | |
Gilon et al. | Forecast of paroxysmal atrial fibrillation using a deep neural network | |
Guhdar et al. | Optimizing Accuracy of Stroke Prediction Using Logistic Regression | |
Guo et al. | Building and evaluating an animal model for syndrome in traditional Chinese medicine in the context of unstable angina (Myocardial Ischemia) by supervised data mining approaches | |
WO2021042372A1 (en) | Atrial fibrillation prediction model and prediction system thereof | |
Zhao et al. | Medical record data-enabled machine learning can enhance prediction of left atrial appendage thrombosis in nonvalvular atrial fibrillation | |
Xue et al. | All-cause death prediction method for CHD based on graph convolutional networks | |
Idrees et al. | Automatic prediction of coronary artery disease using differential evolution-based support vector machine | |
Ay | Classification of ischemic stroke | |
Wei et al. | Comparison of different machine learning classification models for predicting deep vein thrombosis in lower extremity fractures | |
Zeng et al. | Prediction of cardiovascular disease survival based on artificial neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22946676 Country of ref document: EP Kind code of ref document: A1 |