Cross-validation of predictive models for functional recovery after post-stroke rehabilitation

Abstract

Background Rehabilitation treatments and services are essential for the recovery of post-stroke patients’ functions; however, the increasing number of available therapies and the lack of consensus among outcome measures compromises the possibility to determine an appropriate level of evidence. Machine learning techniques for prognostic applications offer accurate and interpretable predictions, supporting the clinical decision for personalised treatment. The aim of this study is to develop and cross-validate predictive models for the functional prognosis of patients, highlighting the contributions of each predictor. Methods A dataset of 278 post-stroke patients was used for the prediction of the class transition, obtained from the modified Barthel Index. Four classification algorithms were cross-validated and compared. On the best performing model on the validation set, an analysis of predictors contribution was conducted. Results The Random Forest obtained the best overall results on the accuracy (76.2%), balanced accuracy (74.3%), sensitivity (0.80), and specificity (0.68). The combination of all the classification results on the test set, by weighted voting, reached 80.2% accuracy. The predictors analysis applied on the Support Vector Machine, showed that a good trunk control and communication level, and the absence of bedsores retain the major contribution in the prediction of a good functional outcome. Conclusions Despite a more comprehensive assessment of the patients is needed, this work paves the way for the implementation of solutions for clinical decision support in the rehabilitation of post-stroke patients. Indeed, offering good prognostic accuracies for class transition and patient-wise view of the predictors contributions, it might help in a personalised optimisation of the patients’ rehabilitation path.

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

“…Given the expanding availability of rehabilitation therapies, the absence of unanimity among metrics poses a hindrance to effectively harnessing clinical results and establishing a satisfactory degree of evidence for interventions. Therefore, a precise and comprehensive evaluation is required to assess patient recovery factors and to guide clinical treatment decisions [ 9 , 10 , 11 ].…”

Clinical phenotypes and prognostic factors in persons with hip osteoarthritis undergoing total hip arthroplasty: protocol for a longitudinal prospective cohort study (HIPPROCLIPS)

“…If this approach is not successful, random decision forest will be used [ 94 ]. However, it is preferred to keep the model as simple as possible to ease the clinical interpretation.…”

NSF DARE—transforming modeling in neurorehabilitation: a patient-in-the-loop framework

“…Cross validation is another useful approach to prevent overfitting and to test model accuracy. Cross validation uses multiple different subsets of the original data to fit the data, and then tests the resulting model accuracy on the remaining subsets of the data [ 294 , 295 ]. This approach is particularly popular for machine learning and is useful for testing how accurate a model is when applied to new data sets.…”