Predictive modeling for stroke using routine clinical and socio-demographic data in Uganda
- 1Makerere University
Abstract
Stroke is a leading cause of mortality and disability in Uganda, with a prevalence of approximately 2.5% and a 25-30% 30-day mortality rate, exacerbated by limited access to predictive tools and advanced diagnostics. Machine learning (ML) offers potential for early stroke risk stratification, but its application in resource-constrained settings like Uganda requires tailored models and rigorous performance evaluation, as well as assessment of misclassification patterns. This study aimed to develop and internally validate an ML-based predictive model for stroke using clinical and socio-demographic characteristics among patients at Mulago National Referral Hospital (MNRH) and residents of Wakiso District, Uganda, identify key predictors and assess misclassification patterns to enhance targeted prevention.
A retrospective case-control study utilized secondary data from 1,016 participants (254 stroke cases, 762 controls) across three prior studies conducted between 2006 and 2015. Eight ML algorithms were evaluated using 5-fold cross-validation, with performance metrics including accuracy, sensitivity, positive predictive value, F1-score, and area under receiver operator characteristics curve (AU-ROC). McNemars test compared model classification performance of the top 2 models. Feature importance identified key predictors, and misclassification patterns were analyzed using classification matrix and line graphs.
The Random Forest (RF) model achieved the highest performance (95.18% accuracy, 90.10% F1-score, 97% AU-ROC). McNemars test confirmed RFs superior classification (p=0.01). Age, systolic blood pressure, total cholesterol, and waist-hip ratio were the top drivers of RF stroke predictions. RF misclassified 8.3% of stroke cases and 3.3% of non-stroke cases, due to overlaps in risk profiles (e.g., lower cholesterol, systolic blood pressure and age in false negatives).
The RF model demonstrates strong potential for stroke risk prediction in Uganda, leveraging routine data to prioritize high-risk individuals. Misclassification analysis highlights areas for model refinement, supporting its potential for integration into clinical workflows for early intervention and stroke prevention in resource-limited settings. Future external validation across diverse populations is recommended.
Related
- Early prediction of 3-month functional outcome after acute ischemic stroke: an explainable model based on routine clinical data
- Distinct Patterns of Mobility Recovery After Stroke Using Routine Clinical Data
- Associated factors and predictive modeling of deep vein thrombosis in stroke patients undergoing rehabilitation
- Modeling Factors Associated with Smoking Dependence Severity Using Binary Classification-Based Machine Learning: Prediction with Hematological and Demographic Patient Data
- Predictive analysis in acute ischemic stroke imaging
BibTeX
@misc{mugisha2026predictive,
title = {{Predictive modeling for stroke using routine clinical and socio-demographic data in Uganda}},
author = {D. Mugisha and B. Watyaba and H. Kiiza and D. Wagaba and H. Unith and S. Nabidda and S. Okello and J. N. Kalyango and R. Baguma and M. K. Mukasa and J. Nakibuuka},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.19.26365927},
url = {https://www.medrxiv.org/content/10.64898/2026.10.19.26365927v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Predictive modeling for stroke using routine clinical and socio-demographic data in Uganda
AU - D. Mugisha
AU - B. Watyaba
AU - H. Kiiza
AU - D. Wagaba
AU - H. Unith
AU - S. Nabidda
AU - S. Okello
AU - J. N. Kalyango
AU - R. Baguma
AU - M. K. Mukasa
AU - J. Nakibuuka
PY - 2026
DA - 2026/10/19
PB - medRxiv
DO - 10.64898/2026.10.19.26365927
UR - https://www.medrxiv.org/content/10.64898/2026.10.19.26365927v1
AB - Stroke is a leading cause of mortality and disability in Uganda, with a prevalence of approximately 2.5% and a 25-30% 30-day mortality rate, exacerbated by limited access to predictive tools and advanced diagnostics. Machine learning (ML) offers potential for early stroke risk stratification, but its application in resource-constrained settings like Uganda requires tailored models and rigorous performance evaluation, as well as assessment of misclassification patterns. This study aimed to develop and internally validate an ML-based predictive model for stroke using clinical and socio-demographic characteristics among patients at Mulago National Referral Hospital (MNRH) and residents of Wakiso District, Uganda, identify key predictors and assess misclassification patterns to enhance targeted prevention. A retrospective case-control study utilized secondary data from 1,016 participants (254 stroke cases, 762 controls) across three prior studies conducted between 2006 and 2015. Eight ML algorithms were evaluated using 5-fold cross-validation, with performance metrics including accuracy, sensitivity, positive predictive value, F1-score, and area under receiver operator characteristics curve (AU-ROC). McNemars test compared model classification performance of the top 2 models. Feature importance identified key predictors, and misclassification patterns were analyzed using classification matrix and line graphs. The Random Forest (RF) model achieved the highest performance (95.18% accuracy, 90.10% F1-score, 97% AU-ROC). McNemars test confirmed RFs superior classification (p=0.01). Age, systolic blood pressure, total cholesterol, and waist-hip ratio were the top drivers of RF stroke predictions. RF misclassified 8.3% of stroke cases and 3.3% of non-stroke cases, due to overlaps in risk profiles (e.g., lower cholesterol, systolic blood pressure and age in false negatives). The RF model demonstrates strong potential for stroke risk prediction in Uganda, leveraging routine data to prioritize high-risk individuals. Misclassification analysis highlights areas for model refinement, supporting its potential for integration into clinical workflows for early intervention and stroke prevention in resource-limited settings. Future external validation across diverse populations is recommended.
ER -