A Machine Learning Approach to Support Urgent Stroke Triage Using Administrative Data and Social Determinants of Health at Hospital Presentation: Retrospective Study

Background: The key to effective stroke management is timely diagnosis and triage. Machine learning (ML) methods developed to assist in detecting stroke have focused on interpreting detailed clinical data such as clinical notes and diagnostic imaging results. However, such information may not be readily available when patients are initially triaged, particularly in rural and underserved communities. Objective: This study aimed to develop an ML stroke prediction algorithm based on data widely available at the time of patients' hospital presentations and assess the added value of social determinants of health (SDoH) in stroke prediction. Methods: We conducted a retrospective study of the emergency department and hospitalization records from 2012 to 2014 from all the acute care hospitals in the state of Florida, merged with the SDoH data from the American Community Survey. A case-control design was adopted to construct stroke and stroke mimic cohorts. We compared the algorithm performance and feature importance measures of the ML models (ie, gradient boosting machine and random forest) with those of the logistic regression model based on 3 sets of predictors. To provide insights into the prediction and ultimately assist care providers in decision-making, we used TreeSHAP for tree-based ML models to explain the stroke prediction. Results: Our analysis included 143,203 hospital visits of unique patients, and it was confirmed based on the principal diagnosis at discharge that 73% (n=104,662) of these patients had a stroke. The approach proposed in this study has high sensitivity and is particularly effective at reducing the misdiagnosis of dangerous stroke chameleons (false-negative rate <4%). ML classifiers consistently outperformed the benchmark logistic regression in all 3 input combinations. We found significant consistency across the models in the features that explain their performance. The most important features are age, the number of chronic conditions on admission, and primary payer (eg, Medicare or private insurance). Although both the individual-and community-level SDoH features helped improve the predictive performance of the models, the inclusion of the individual-level SDoH features led to a much larger improvement (area under the receiver operating characteristic curve increased from 0.694 to 0.823) than the inclusion of the community-level SDoH features (area under the receiver operating characteristic curve increased from 0.823 to 0.829). Conclusions: Using data widely available at the time of patients' hospital presentations, we developed a stroke prediction model with high sensitivity and reasonable specificity. The prediction algorithm uses variables that are routinely collected by providers and payers and might be useful in underresourced hospitals with limited availability of sensitive diagnostic tools or incomplete data-gathering capabilities.