Analyzing and predicting the risk of death in stroke patients using machine learning
BackgroundStroke is an acute disorder and dysfunction of the focal neurological system that has long been recognized as one of the leading causes of death and severe disability in most regions globally. This study aimed to supplement and exploit multiple comorbidities, laboratory tests and demograph...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1096153/full |
| _version_ | 1811173229010616320 |
|---|---|
| author | Enzhao Zhu Zhihao Chen Pu Ai Jiayi Wang Min Zhu Ziqin Xu Jun Liu Zisheng Ai Zisheng Ai |
| author_facet | Enzhao Zhu Zhihao Chen Pu Ai Jiayi Wang Min Zhu Ziqin Xu Jun Liu Zisheng Ai Zisheng Ai |
| author_sort | Enzhao Zhu |
| collection | DOAJ |
| description | BackgroundStroke is an acute disorder and dysfunction of the focal neurological system that has long been recognized as one of the leading causes of death and severe disability in most regions globally. This study aimed to supplement and exploit multiple comorbidities, laboratory tests and demographic factors to more accurately predict death related to stroke, and furthermore, to make inferences about the heterogeneity of treatment in stroke patients to guide better treatment planning.MethodsWe extracted data from the Medical Information Mart from the Intensive Care (MIMIC)-IV database. We compared the distribution of the demographic factors between the control and death groups. Subsequently, we also developed machine learning (ML) models to predict mortality among stroke patients. Furthermore, we used meta-learner to recognize the heterogeneity effects of warfarin and human albumin. We comprehensively evaluated and interpreted these models using Shapley Additive Explanation (SHAP) analysis.ResultsWe included 7,483 patients with MIMIC-IV in this study. Of these, 1,414 (18.9%) patients died during hospitalization or 30 days after discharge. We found that the distributions of age, marital status, insurance type, and BMI differed between the two groups. Our machine learning model achieved the highest level of accuracy to date in predicting mortality in stroke patients. We also observed that patients who were consistent with the model determination had significantly better survival outcomes than the inconsistent population and were better than the overall treatment group.ConclusionWe used several highly interpretive machine learning models to predict stroke prognosis with the highest accuracy to date and to identify heterogeneous treatment effects of warfarin and human albumin in stroke patients. Our interpretation of the model yielded a number of findings that are consistent with clinical knowledge and warrant further study and verification. |
| first_indexed | 2024-04-10T17:43:27Z |
| format | Article |
| id | doaj.art-a9aeab49173948a3993350509a1ec41c |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-04-10T17:43:27Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-a9aeab49173948a3993350509a1ec41c2023-02-03T07:02:04ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-02-011410.3389/fneur.2023.10961531096153Analyzing and predicting the risk of death in stroke patients using machine learningEnzhao Zhu0Zhihao Chen1Pu Ai2Jiayi Wang3Min Zhu4Ziqin Xu5Jun Liu6Zisheng Ai7Zisheng Ai8School of Medicine, Tongji University, Shanghai, ChinaSchool of Business, East China University of Science and Technology, Shanghai, ChinaSchool of Medicine, Tongji University, Shanghai, ChinaSchool of Medicine, Tongji University, Shanghai, ChinaDepartment of Computer Science and Technology, School of Electronics and Information Engineering, Tongji University, Shanghai, ChinaDepartment of Industrial Engineering and Operations Research, Columbia University, New York, NY, United StatesSchool of Medicine, Tongji University, Shanghai, ChinaClinical Research Center for Mental Disorders, Chinese-German Institute of Mental Health, Shanghai Pudong New Area Mental Health Center, School of Medicine, Tongji University, Shanghai, ChinaDepartment of Medical Statistics, School of Medicine, Tongji University, Shanghai, ChinaBackgroundStroke is an acute disorder and dysfunction of the focal neurological system that has long been recognized as one of the leading causes of death and severe disability in most regions globally. This study aimed to supplement and exploit multiple comorbidities, laboratory tests and demographic factors to more accurately predict death related to stroke, and furthermore, to make inferences about the heterogeneity of treatment in stroke patients to guide better treatment planning.MethodsWe extracted data from the Medical Information Mart from the Intensive Care (MIMIC)-IV database. We compared the distribution of the demographic factors between the control and death groups. Subsequently, we also developed machine learning (ML) models to predict mortality among stroke patients. Furthermore, we used meta-learner to recognize the heterogeneity effects of warfarin and human albumin. We comprehensively evaluated and interpreted these models using Shapley Additive Explanation (SHAP) analysis.ResultsWe included 7,483 patients with MIMIC-IV in this study. Of these, 1,414 (18.9%) patients died during hospitalization or 30 days after discharge. We found that the distributions of age, marital status, insurance type, and BMI differed between the two groups. Our machine learning model achieved the highest level of accuracy to date in predicting mortality in stroke patients. We also observed that patients who were consistent with the model determination had significantly better survival outcomes than the inconsistent population and were better than the overall treatment group.ConclusionWe used several highly interpretive machine learning models to predict stroke prognosis with the highest accuracy to date and to identify heterogeneous treatment effects of warfarin and human albumin in stroke patients. Our interpretation of the model yielded a number of findings that are consistent with clinical knowledge and warrant further study and verification.https://www.frontiersin.org/articles/10.3389/fneur.2023.1096153/fullstrokestroke mortalitymachine learningdeep learningtreatment heterogeneity |
| spellingShingle | Enzhao Zhu Zhihao Chen Pu Ai Jiayi Wang Min Zhu Ziqin Xu Jun Liu Zisheng Ai Zisheng Ai Analyzing and predicting the risk of death in stroke patients using machine learning Frontiers in Neurology stroke stroke mortality machine learning deep learning treatment heterogeneity |
| title | Analyzing and predicting the risk of death in stroke patients using machine learning |
| title_full | Analyzing and predicting the risk of death in stroke patients using machine learning |
| title_fullStr | Analyzing and predicting the risk of death in stroke patients using machine learning |
| title_full_unstemmed | Analyzing and predicting the risk of death in stroke patients using machine learning |
| title_short | Analyzing and predicting the risk of death in stroke patients using machine learning |
| title_sort | analyzing and predicting the risk of death in stroke patients using machine learning |
| topic | stroke stroke mortality machine learning deep learning treatment heterogeneity |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1096153/full |
| work_keys_str_mv | AT enzhaozhu analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT zhihaochen analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT puai analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT jiayiwang analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT minzhu analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT ziqinxu analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT junliu analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT zishengai analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning AT zishengai analyzingandpredictingtheriskofdeathinstrokepatientsusingmachinelearning |