Machine Learning for Predicting Early Functional Outcomes in Patients with Stroke
- Authors: Chernykh E.M.1, Khasanova N.M.1, Karyakin A.A.1, Jafarova Z.E.1, Klyukas A.А.1
-
Affiliations:
- Northern State Medical University
- Issue: Vol 7, No 2 (2025)
- Pages: 82-94
- Section: ORIGINAL STUDY ARTICLE
- URL: https://journals.rcsi.science/2658-6843/article/view/314422
- DOI: https://doi.org/10.36425/rehab678920
- EDN: https://elibrary.ru/JEMEVO
- ID: 314422
Cite item
Full Text
Abstract
BACKGROUND: Development of a universal predictive tool for patients with stroke remains a challenge.
AIM: The study aimed to develop machine learning–based models that could predict functional outcomes from the first day after stroke. The models were trained using clinical and anamnestic predictors, and functional outcomes were evaluated using the National Institutes of Health Stroke Scale (NIHSS) and the modified Rankin Scale (mRS) at hospital discharge.
METHODS: Models based on artificial neural network (ANN) and random forest (RF) algorithms were developed using a database created from 5,225 records of patients with stroke discharged from neurological departments. Twenty-one parameters were used, including patient demographics; baseline National Institutes of NIHSS and mRS scores; stroke type; time from stroke onset to hospitalization; comorbidities; and emergency revascularization. Outcomes were predicted using NIHSS and mRS scores. The algorithms solved the classification problem for multiple sets of outcome values. Model I had 26 classes (NIHSS score pf 0–25), while model II had 6 classes (mRS score of 0–5). The quality of the models was evaluated using the area under the receiver operating characteristic curve (ROC-AUC). The contribution of each predictor was evaluated using the SHapley Additive exPlanations (SHAP).
RESULTS: The predictive value of the ANN was determined based on the AUC-ROC: 0.771 for model I and 0.844 for model II. The RF AUC-ROC was 0.778 for model I and 0.845 for model II. The RF algorithm was chosen for further work due to its better interpretability. The most significant features that influenced the predicted outcomes were baseline NIHSS and mRs scores, patient age, time from stroke onset to admission, and stroke type. When RF performance was tested on an external validation set of 783 records, ROC-AUC values were 0.786 for model I and 0.774 for model II. A calculator was developed for practical use.
CONCLUSION: The proposed RF-based models can reliably predict an early functional outcome within the first day of stroke onset, using NIHSS and mRs scores and clinical and anamnestic predictors. This tool can be used to develop personalized therapeutic and rehabilitation strategies in the acute phase of a stroke. These models are versatile to be used in rural and remote healthcare organizations that lack specialized staff and diagnostic equipment.
Full Text
##article.viewOnOriginalSite##About the authors
Ekaterina M. Chernykh
Northern State Medical University
Author for correspondence.
Email: raduga0302@mail.ru
ORCID iD: 0000-0002-6523-7071
SPIN-code: 8296-2286
Russian Federation, Arkhangelsk
Nina M. Khasanova
Northern State Medical University
Email: khasanovanina@rambler.ru
ORCID iD: 0000-0003-0729-3726
SPIN-code: 6834-6281
MD, Cand. Sci. (Medicine), Associate Professor
Russian Federation, ArkhangelskAlexey A. Karyakin
Northern State Medical University
Email: biophyzica@yandex.ru
ORCID iD: 0000-0002-4458-8702
SPIN-code: 7296-3303
Cand. Sci. (Engineering), Associate Professor
Russian Federation, ArkhangelskZohra E. Jafarova
Northern State Medical University
Email: zohrajafarova@yandex.ru
ORCID iD: 0009-0003-2429-9158
Russian Federation, Arkhangelsk
Alexey А. Klyukas
Northern State Medical University
Email: alexeythekly@gmail.com
ORCID iD: 0009-0005-3428-187X
Russian Federation, Arkhangelsk
References
- Bösel J, Mathur R, Cheng L, et al. AI and neurology. Neurol Res Pract. 2025;7(1):11. doi: 10.1186/s42466-025-00367-2
- AbuAlrob MA, Mesraoua B. Harnessing artificial intelligence for the diagnosis and treatment of neurological emergencies: A comprehensive review of recent advances and future directions. Front Neurol. 2024;15:1485799. doi: 10.3389/fneur.2024.1485799
- Mainali S, Darsie ME, Smetana KS. Machine learning in action: Stroke diagnosis and outcome prediction. Front Neurol. 2021;12:734345. doi: 10.3389/fneur.2021.734345
- Abedi V, Kawamura Y, Li J, et al. Editorial: Machine learning in action: Stroke diagnosis and outcome prediction. Front Neurol. 2022;13:984467. doi: 10.3389/fneur.2022.984467
- Abedi V, Khan A, Chaudhary D, et al. Using artificial intelligence for improving stroke diagnosis in emergency departments: A practical framework. Ther Adv Neurol Dis. 2020;13:1756286420938962. doi: 10.1177/1756286420938962
- Rajashekar D, Hill MD, Demchuk AM, et al. Prediction of clinical outcomes in acute ischaemic stroke patients: A comparative study. Front Neurol. 2021;12:663899. doi: 10.3389/fneur.2021.663899
- Yang Y, Tang L, Deng Y, et al. The predictive performance of artificial intelligence on the outcome of stroke: A systematic review and meta-analysis. Front Neurol. 2023;17:1256592. doi: 10.3389/fnins.2023.1256592
- Qu S, Zhou M, Jiao S, et al. Optimizing acute stroke outcome prediction models: Comparison of generalized regression neural networks and logistic regressions. PLOS One. 2022;17(5):e0267747. doi: 10.1371/journal.pone.0267747
- Lee J, Park KM, Park S. Interpretable machine learning for prediction of clinical outcomes in acute ischemic stroke. Front Neurol. 2023;14:1234046. doi: 10.3389/fneur.2023.1234046
- Gaviria E, Eltayeb Hamid AH. Neuroimaging biomarkers for predicting stroke outcomes: A systematic review. Health Sci Rep. 2024;7(7):e2221. doi: 10.1002/hsr2.2221
- Pedersen M, Verspoor K, Jenkinson M, et al. Artificial intelligence for clinical decision support in neurology. Brain Commun. 2020;2(2):fcaa096. doi: 10.1093/braincomms/fcaa096
- Wang W, Kiik M, Peek N, et al. A systematic review of machine learning models for predicting outcomes of stroke with structured data. PLOS One. 2020;15(6):e0234722. doi: 10.1371/journal.pone.0234722
- Alyasein S, Alqaran R, Al-Aiad A. Using machine learning algorithms for predicting stroke disease-2024. In: 15th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan; 2024. P. 1–6. doi: 10.1109/ICICS63486.2024.10638280
- Heo J, Yoon JG, Park H, et al. Machine learning-based model for prediction of outcomes in acute stroke. Stroke. 2019;50(5):1263–1265. doi: 10.1161/STROKEAHA.118.024293
- Daidone M, Ferrantelli S, Tuttolomondo A. Machine learning applications in stroke medicine: Advancements, challenges, and future prospectives. Neural Reg Res. 2024;19(4):769–773. doi: 10.4103/1673-5374.382228
- Jeon ET, Jung SJ, Yeo TY, et al. Predicting short-term outcomes in atrial-fibrillation-related stroke using machine learning. Front Neurol. 2023;14:1243700. doi: 10.3389/fneur.2023.1243700
- Chernykh EM, Khasanova NM, Grzhibovsky AM, Bogdanova AI. Functional predictor variables in the acute period of stroke in patients living in the Arctic Macroregion: Multivariate modeling findings. Physical and rehabilitation medicine, medical rehabilitation. 2024;6(4):336–347. doi: 10.36425/rehab637339 EDN: LNEYEF
- Van der Groen O, Ghosh M, Norman R, et al. Point of view on outcome prediction models in post-stroke motor recovery. Neurorehab Neural Rep. 2024;38(5):386–398. doi: 10.1177/15459683241237975
- Kiær C, Lundquist CB, Brunner I. Knowledge and application of upper limb prediction models and attitude toward prognosis among physiotherapists and occupational therapists in the clinical stroke setting. Top Stroke Rehabil. 2021;28(2):135–141. doi: 10.1080/10749357.2020.1783915
- Man S, Bruckman D, Uchino K, et al. Rural hospital performance in guideline-recommended ischemic stroke thrombolysis, secondary prevention, and outcomes. Stroke. 2024;55(10):2472–2481. doi: 10.1161/STROKEAHA.124.047071
- Loccoh EC, Joynt Maddox KE, Wang Y, et al. Rural-urban disparities in outcomes of myocardial infarction, heart failure, and stroke in the United States. J Am College Cardiol. 2022;79(3):267–279. doi: 10.1016/j.jacc.2021.10.045
- Ali F, Hamid U, Zaidat O, et al. Role of artificial intelligence in telestroke: An overview. Front Neurol. 2020;11:559322. doi: 10.3389/fneur.2020.559322
- Zhou Y, Wu D, Yan S, et al. Feasibility of a clinical-radiomics model to predict the outcomes of acute ischemic stroke. Korean J Radiol. 2022;23(8):811–820. doi: 10.3348/kjr.2022.0160
- Loggini A, Saleh Velez FG, Hornik J, et al. Validation of prognostic scales for functional outcome in ischemic stroke patients treated with intravenous thrombolysis in a rural setting. Cerebrovasc Dis Extra. 2024;14(1):148–157. doi: 10.1159/000541801
- Alaka SA, Menon BK, Brobbey A, et al. Functional outcome prediction in ischemic stroke: a comparison of machine learning algorithms and regression models. Front Neurol. 2020;11:889. doi: 10.3389/fneur.2020.00889
- Heo J, Yoon JG, Park H, et al. Machine learning-based model for prediction of outcomes in acute stroke. Stroke. 2019;50(5):1263–1265. doi: 10.1161/STROKEAHA.118.024293
- Çelik G, Baykan ÖK, Kara Y, Tireli H. Predicting 10-day mortality in patients with strokes using neural networks and multivariate statistical methods. J Stroke Cerebrovasc Dis. 2014;23(6):1506–1512. doi: 10.1016/j.jstrokecerebrovasdis.2013.12.018
- Zahidi NF, Tukiran Z, Tukiran I. Analyzing Classification Models: Random Forest vs. Neural Networks in Health Prediction. In: 2024 International Conference on Future Technologies for Smart Society (ICFTSS). Kuala Lumpur, Malaysia; 2024. P. 183–187. doi: 10.1109/ICFTSS61109.2024.10691342
- Khairunnisa A, Notodiputro KA, Sartono B. A comparative study of random forest and double random forest models from view points of their interpretability. Sci J Inform. 2024;11(1). doi: 10.15294/sji.v11i1.48721
Supplementary files
