1
|
Wang Y, Gao Z, Zhang Y, Lu Z, Sun F. Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study. Intern Emerg Med 2024:10.1007/s11739-024-03732-2. [PMID: 39141286 DOI: 10.1007/s11739-024-03732-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Accepted: 07/27/2024] [Indexed: 08/15/2024]
Abstract
Sepsis triggers a harmful immune response due to infection, causing high mortality. Predicting sepsis outcomes early is vital. Despite machine learning's (ML) use in medical research, local validation within the Medical Information Mart for Intensive Care IV (MIMIC-IV) database is lacking. We aimed to devise a prognostic model, leveraging MIMIC-IV data, to predict sepsis mortality and validate it in a Chinese teaching hospital. MIMIC-IV provided patient data, split into training and internal validation sets. Four ML models logistic regression (LR), support vector machine (SVM), deep neural networks (DNN), and extreme gradient boosting (XGBoost) were employed. Shapley additive interpretation offered early and interpretable mortality predictions. Area under the ROC curve (AUROC) gaged predictive performance. Results were cross verified in a Chinese teaching hospital. The study included 27,134 sepsis patients from MIMIC-IV and 487 from China. After comparing, 52 clinical indicators were selected for ML model development. All models exhibited excellent discriminative ability. XGBoost surpassed others, with AUROC of 0.873 internally and 0.844 externally. XGBoost outperformed other ML models (LR: 0.829; SVM: 0.830; DNN: 0.837) and clinical scores (Simplified Acute Physiology Score II: 0.728; Sequential Organ Failure Assessment: 0.728; Oxford Acute Severity of Illness Score: 0.738; Glasgow Coma Scale: 0.691). XGBoost's hospital mortality prediction achieved AUROC 0.873, sensitivity 0.818, accuracy 0.777, specificity 0.768, and F1 score 0.551. We crafted an interpretable model for sepsis death risk prediction. ML algorithms surpassed traditional scores for sepsis mortality forecast. Validation in a Chinese teaching hospital echoed these findings.
Collapse
Affiliation(s)
- Yiping Wang
- Department of Emergency, The First Affiliated Hospital of WenZhou Medical University, Wenzhou, 325000, China
| | - Zhihong Gao
- Department of Computer Technology and Information Management, The First Affiliated Hospital of WenZhou Medical University, Wenzhou, 325000, China
| | - Yang Zhang
- Department of Computer Technology and Information Management, The First Affiliated Hospital of WenZhou Medical University, Wenzhou, 325000, China
| | - Zhongqiu Lu
- Department of Emergency, The First Affiliated Hospital of WenZhou Medical University, Wenzhou, 325000, China.
| | - Fangyuan Sun
- Department of Computer Technology and Information Management, The First Affiliated Hospital of WenZhou Medical University, Wenzhou, 325000, China.
| |
Collapse
|
2
|
Zhou L, Wang L, Liu G, Cai E. Prognosis prediction models for post-stroke depression: a protocol for systematic review, meta-analysis, and critical appraisal. Syst Rev 2024; 13:138. [PMID: 38778417 PMCID: PMC11110183 DOI: 10.1186/s13643-024-02544-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Accepted: 04/23/2024] [Indexed: 05/25/2024] Open
Abstract
INTRODUCTION Post-stroke depression (PSD) is a prevalent complication that has been shown to have a negative impact on rehabilitation outcomes and quality of life and poses a significant risk for suicidal intention. However, models for discriminating and predicting PSD in stroke survivors for effective secondary prevention strategies are inadequate as the pathogenesis of PSD remains unknown. Prognostic prediction models that exhibit greater rule-in capacity have the potential to mitigate the issue of underdiagnosis and undertreatment of PSD. Thus, the planned study aims to systematically review and critically evaluate published studies on prognostic prediction models for PSD. METHODS AND ANALYSIS A systematic literature search will be conducted in PubMed and Embase through Ovid. Two reviewers will complete study screening, data extraction, and quality assessment utilizing appropriate tools. Qualitative data on the characteristics of the included studies, methodological quality, and the appraisal of the clinical applicability of models will be summarized in the form of narrative comments and tables or figures. The predictive performance of the same model involving multiple studies will be synthesized with a random effects meta-analysis model or meta-regression, taking into account heterogeneity. ETHICS AND DISSEMINATION Ethical approval is considered not applicable for this systematic review. Findings will be shared through dissemination at academic conferences and/or publication in peer-reviewed academic journals. SYSTEMATIC REVIEW REGISTRATION PROSPERO CRD42023388548.
Collapse
Affiliation(s)
- Lu Zhou
- School of Nursing, Yunnan University of Chinese Medicine, Kunming, China
| | - Lei Wang
- School of Nursing, Yunnan University of Chinese Medicine, Kunming, China
| | - Gao Liu
- School of Nursing, Yunnan University of Chinese Medicine, Kunming, China
| | - EnLi Cai
- School of Nursing, Yunnan University of Chinese Medicine, Kunming, China.
| |
Collapse
|
3
|
Oei CW, Ng EYK, Ng MHS, Tan RS, Chan YM, Chan LG, Acharya UR. Explainable Risk Prediction of Post-Stroke Adverse Mental Outcomes Using Machine Learning Techniques in a Population of 1780 Patients. SENSORS (BASEL, SWITZERLAND) 2023; 23:7946. [PMID: 37766004 PMCID: PMC10538068 DOI: 10.3390/s23187946] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Revised: 09/13/2023] [Accepted: 09/15/2023] [Indexed: 09/29/2023]
Abstract
Post-stroke depression and anxiety, collectively known as post-stroke adverse mental outcome (PSAMO) are common sequelae of stroke. About 30% of stroke survivors develop depression and about 20% develop anxiety. Stroke survivors with PSAMO have poorer health outcomes with higher mortality and greater functional disability. In this study, we aimed to develop a machine learning (ML) model to predict the risk of PSAMO. We retrospectively studied 1780 patients with stroke who were divided into PSAMO vs. no PSAMO groups based on results of validated depression and anxiety questionnaires. The features collected included demographic and sociological data, quality of life scores, stroke-related information, medical and medication history, and comorbidities. Recursive feature elimination was used to select features to input in parallel to eight ML algorithms to train and test the model. Bayesian optimization was used for hyperparameter tuning. Shapley additive explanations (SHAP), an explainable AI (XAI) method, was applied to interpret the model. The best performing ML algorithm was gradient-boosted tree, which attained 74.7% binary classification accuracy. Feature importance calculated by SHAP produced a list of ranked important features that contributed to the prediction, which were consistent with findings of prior clinical studies. Some of these factors were modifiable, and potentially amenable to intervention at early stages of stroke to reduce the incidence of PSAMO.
Collapse
Affiliation(s)
- Chien Wei Oei
- Management Information Department, Office of Clinical Epidemiology, Analytics and kNowledge (OCEAN), Tan Tock Seng Hospital, Singapore 308433, Singapore;
- School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore
| | - Eddie Yin Kwee Ng
- School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore
| | - Matthew Hok Shan Ng
- Rehabilitation Research Institute of Singapore, Nanyang Technological University, Singapore 308232, Singapore;
| | - Ru-San Tan
- National Heart Centre Singapore, Singapore 169609, Singapore;
- Duke-NUS Medical School, Singapore 169857, Singapore
| | - Yam Meng Chan
- Department of General Surgery, Vascular Surgery Service, Tan Tock Seng Hospital, Singapore 308433, Singapore;
| | - Lai Gwen Chan
- Department of Psychiatry, Tan Tock Seng Hospital, Singapore 308433, Singapore;
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore 308232, Singapore
| | - Udyavara Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, QLD 4305, Australia;
| |
Collapse
|
4
|
Liu X, Zhang Z, Lin B, Guo Y, Mei Y, Ping Z, Wang W, Jiang H, Wang S, Zhang C, Chen S, Zhang Q. Relationship between perceptions of recurrence risk and depression state among first-episode ischemic stroke patients in rural areas: The mediating role of coping style. Nurs Open 2023; 10:4515-4525. [PMID: 37014075 PMCID: PMC10277436 DOI: 10.1002/nop2.1695] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2022] [Revised: 01/05/2023] [Accepted: 02/14/2023] [Indexed: 04/05/2023] Open
Abstract
AIMS To investigate the relationship between stroke survivors' perceptions of recurrence risk, coping styles and depression state, and the role coping styles play in mediating that relationship. DESIGN A cross-sectional descriptive study. METHODS From one hospital in Huaxian, China, 320 stroke survivors were randomly selected as a convenience sample. In this research, the Simplified Coping Style Questionnaire, the Patient Health Questionnaire-9 and the Stroke Recurrence Risk Perception Scale were all used. Structural equation modelling and correlation analysis were used to analyse the data. This research followed the EQUATOR and STROBE checklists. RESULTS There were 278 valid survey responses. There were mild to severe depressive symptoms in 84.8% of stroke survivors. In stroke survivors, there was a significant negative relationship (p < 0.01) between the positive coping of perceptions of recurrence risk and their depression state. Recurrence risk perception's impact on depression state was partly mediated, according to mediation studies, by coping style, with the mediation effect accounting for 44.92% of the overall effect. CONCLUSIONS The connection between perceptions of recurrence risk and depression state was mediated by the coping mechanisms of stroke survivors. A lower degree of depression state among survivors was connected with positive coping to the beliefs of recurrence risk.
Collapse
Affiliation(s)
- Xueting Liu
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Zhenxiang Zhang
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Beilei Lin
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
- Academic of Medical Science, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Yunfei Guo
- Henan Provincial People's Hospital, Zhengzhou University People's Hospital, Zhengzhou City, China
| | - Yongxia Mei
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Zhiguang Ping
- School of Public Health, Zhengzhou University, Zhengzhou City, China
| | - Wenna Wang
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Hu Jiang
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Shaoyang Wang
- The Second Affiliated Hospital, Zhengzhou University, Zhengzhou City, China
| | - Chunhui Zhang
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Suyan Chen
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| | - Qiushi Zhang
- Nursing and Health School, Zhengzhou University, Zhengzhou City, Henan Province, China
| |
Collapse
|
5
|
Hassan AM, Rajesh A, Asaad M, Jonas NA, Coert JH, Mehrara BJ, Butler CE. A Surgeon's Guide to Artificial Intelligence-Driven Predictive Models. Am Surg 2023; 89:11-19. [PMID: 35588764 PMCID: PMC9674797 DOI: 10.1177/00031348221103648] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
Artificial intelligence (AI) focuses on processing and interpreting complex information as well as identifying relationships and patterns among complex data. Artificial intelligence- and machine learning (ML)-driven predictions have shown promising potential in influencing real-time decisions and improving surgical outcomes by facilitating screening, diagnosis, risk assessment, preoperative planning, and shared decision-making. Fundamental understanding of the algorithms, as well as their development and interpretation, is essential for the evolution of AI in surgery. In this article, we provide surgeons with a fundamental understanding of AI-driven predictive models through an overview of common ML and deep learning algorithms, model development, performance metrics and interpretation. This would serve as a basis for understanding ML-based research, while fostering new ideas and innovations for furthering the reach of this emerging discipline.
Collapse
Affiliation(s)
- Abbas M. Hassan
- Department of Plastic & Reconstructive Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Aashish Rajesh
- Department of Surgery, University of Texas Health Science Center, San Antonio, TX, USA
| | - Malke Asaad
- Department of Plastic Surgery, University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| | - Nelson A. Jonas
- Department of Plastic & Reconstructive Surgery, Memorial Sloan Kettering Cancer Center, New York, NY
| | - J. Henk Coert
- Department of Plastic and Reconstructive Surgery, University Medical Center Utrecht, Utrecht, Netherlands
| | - Babak J. Mehrara
- Department of Plastic & Reconstructive Surgery, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Charles E. Butler
- Department of Plastic & Reconstructive Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| |
Collapse
|