Evaluation of Blood Biomarkers and Parameters for the Prediction of Stroke Survivors’ Functional Outcome upon Discharge Utilizing Explainable Machine Learning

Abstract

Despite therapeutic advancements, stroke remains a leading cause of death and long-term disability. The quality of current stroke prognostic models varies considerably, whereas prediction models of post-stroke disability and mortality are restricted by the sample size, the range of clinical and risk factors and the clinical applicability in general. Accurate prognostication can ease post-stroke discharge planning and help healthcare practitioners individualize aggressive treatment or palliative care, based on projected life expectancy and clinical course. In this study, we aimed to develop an explainable machine learning methodology to predict functional outcomes of stroke patients at discharge, using the Modified Rankin Scale (mRS) as a binary classification problem. We identified 35 parameters from the admission, the first 72 h, as well as the medical history of stroke patients, and used them to train the model. We divided the patients into two classes in two approaches: “Independent” vs. “Non-Independent” and “Non-Disability” vs. “Disability”. Using various classifiers, we found that the best models in both approaches had an upward trend, with respect to the selected biomarkers, and achieved a maximum accuracy of 88.57% and 89.29%, respectively. The common features in both approaches included: age, hemispheric stroke localization, stroke localization based on blood supply, development of respiratory infection, National Institutes of Health Stroke Scale (NIHSS) upon admission and systolic blood pressure levels upon admission. Intubation and C-reactive protein (CRP) levels upon admission are additional features for the first approach and Erythrocyte Sedimentation Rate (ESR) levels upon admission for the second. Our results suggest that the said factors may be important predictors of functional outcomes in stroke patients.

From Admission to Discharge: Predicting National Institutes of Health Stroke Scale Progression in Stroke Patients Using Biomarkers and Explainable Machine Learning

“…There are numerous data points regarding the variables influencing the prognosis, the severity, and the functional outcomes of stroke. The variables under consideration herein encompass the simultaneous factors of the genetic and demographic features of the patients, along with the data collected during the acute phase of the stroke and its related components [ 8 ].…”

Random Forest-Based Prediction Models for Assessing Cardiovascular Disease Risk: Integrating Clinical and Genetic Factors

“…Random Forest is a gathering learning strategy that builds numerous choice trees amid preparing and yields the mode of the classes (classification) or cruel forecast (regression) of person trees [5]. Each decision tree is prepared on a bootstrapped test of the dataset and at each part, a random subset of highlights is considered, driving to decorrelated trees.…”

Integrative Approaches in Acute Ischemic Stroke: From Symptom Recognition to Future Innovations

“…In contrast, MLP, which mirrors the intricate design of human neural networks, can adeptly handle multifaceted data. Additionally, the study leveraged SVMs, which excel in high-dimensional data scenarios, and the LR model, recognized for its prowess in binary classification tasks [320].…”