Prognosticating global functional outcome in the recurrent ischemic stroke using baseline clinical and pre‐clinical features: A machine learning study

Journal of Evaluation in Clinical Practice - Tập 31 Số 1 - 2025
Tran Nhat Phong Dao1,2, Hien Nguyen Thanh Dang3, My Thi Kim Pham4, Hien Thi Nguyen5, Cuong Q. Tran6, Văn Minh Lê7,8,9
1Can Tho Traditional Medicine Hospital Can Tho Vietnam
2Faculty of Traditional Medicine, Can Tho University of Medicine and Pharmacy, Can Tho, Vietnam
3Department of Cardiology Hoan My Cuu Long General Hospital Can Tho Vietnam
4Department of Cardiac Surgery Can Tho Central General Hospital Can Tho Vietnam
5Department of Nutrition and Food Safety, Faculty of Public Health Can Tho University of Medicine and Pharmacy Can Tho Vietnam
6Can Tho Stroke International Services (S.I.S) General Hospital Can Tho Vietnam
7Department of Neurology Can Tho Central General Hospital Can Tho Vietnam
8Department of Neurology Can Tho University of Medicine and Pharmacy Hospital Can Tho Vietnam
9Department of Neurology, Faculty of Medicine Can Tho University of Medicine and Pharmacy Can Tho Vietnam

Tóm tắt

AbstractBackground and PurposeRecurrent ischemic stroke (RIS) induces additional functional limitations in patients. Prognosticating globally functional outcome (GFO) in RIS patients is thereby important to plan a suitable rehabilitation programme. This study sought to investigate the ability of baseline features for classifying the patients with and without improving GFO (task 1) and identifying patients with poor GFO (task 2) at the third month after discharging from RIS.MethodsA total of 86 RIS patients were recruited and divided into the training set and testing set (50:50). The clinical and pre‐clinical data were recorded. The outcome was the changes in Modified Rankin Scale (mRS) (task 1) and the mRS score at the third month (mRS 0–2: good GFO, mRS >2: poor GFO) (task 2). The permutation importance ranking method selected features. Four algorithms were trained on the training set with five‐fold cross‐validation. The best model was tested on the testing set.ResultsIn task 1, the support vector machine (SVM) model outperformed the other models, with the high performance matrix on the training set (sensitivity = 0.80; specificity = 1.00) and the testing set (sensitivity = 0.80; specificity = 0.95). In task 2, the SVM model with selected features also performed well on both datasets (training set: sensitivity = 0.76; specificity = 0.92; testing set: sensitivity = 0.72; specificity = 0.88).ConclusionA machine learning model could be used to classify GFO responses to treatment and identify the third‐month poor GFO in RIS patients, supporting physicians in clinical practice.

Từ khóa


Tài liệu tham khảo

10.1016/j.amjmed.2021.07.027

10.1097/PHM.0000000000000502

10.1001/jamaneurol.2020.4396

10.1161/STROKEAHA.116.013599

10.1159/000121343

10.1161/STROKEAHA.123.044072

10.1161/01.STR.0000258355.23810.c6

10.1016/j.mri.2019.05.031

10.3390/app10155135

10.3389/fcvm.2022.804410

10.3390/jcm10061286

10.3389/fneur.2023.1114360

10.23736/S1973-9087.18.05161-4

Ministry of Health. Decision No. 5331/QD‐BYT Guidelines for diagnosis and treatment of stroke. In: Ha Noi ‐ Vietnam 2020.

Dang NTH, 2023, Assessment of treatment results on recurrent ischemic stroke patient at Can Tho central general hospital from 2022 to 2023, Can Tho J Med Pharm, 65, 80

Ministry of Health. Decision No. 3109/QD‐BYT Guidelines for diagnosis and treatment specialized in rehabilitation. In: Ha Noi ‐ Viet Nam 2014;91‐95.

10.1097/WON.0b013e318275012f

10.1159/000095343

National Institute of Neurological Disorders and Stroke (U.S.).NIH Stroke Scale. [Bethesda Md.?]: National Institute of Neurological Disorders and Stroke Dept. of Health and Human Services USA;2011.

10.3389/fneur.2023.1064642

10.21105/joss.03167

Pedregosa F, 2011, Scikit‐learn: machine learning in python, J Mach Learn Res, 12, 2825

Lemaître G, 2017, Imbalanced‐learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning, J Mach Learn Res, 18, 1

10.1002/sam.11583

10.1186/s12916-023-02858-y

10.1038/s41598-022-10358-x

10.3390/biomedicines10123002

Aurélien G, 2019, Keras, and TensorFlow

SulistianiI WulandariW AstutiFD.Widodo. Breast cancer prediction using random forest and Gaussian Naïve Bayes algorithmsIn:2022 1st International Conference on Information System & Information Technology (ICISIT).2022;170‐175.

10.36255/exon-publications-digital-health-explainable-decisions

10.1016/j.jbi.2018.12.003

10.3389/fneur.2018.00308

10.5402/2011/354642

10.1111/jch.14331

10.1161/JAHA.118.008744

10.1515/tnsci-2022-0307

10.1161/STROKEAHA.120.032487

10.1136/bmjno-2021-000183

10.3390/jcm11112997

10.1001/jamaneurol.2019.4838

10.1111/jdi.12932

Thông tin
Thông tin xuất bản

Journal of Evaluation in Clinical Practice

Tập 31 Số 1

Thông tin tác giả