Machine learning methods for functional recovery prediction and prognosis in post-stroke rehabilitation: a systematic review

Abstract

Background: Rehabilitation medicine is facing a new development phase thanks to a recent wave of rigorous clinical trials aimed at improving the scientific evidence of protocols. This phenomenon, combined with new trends in personalised medical therapies, is expected to change clinical practice dramatically. The emerging field of Rehabilomics is only possible if methodologies are based on biomedical data collection and analysis. In this framework, the objective of this work is to develop a systematic review of machine learning algorithms as solutions to predict motor functional recovery of post-stroke patients after treatment.

Methods: We conducted a comprehensive search of five electronic databases using the Patient, Intervention, Comparison and Outcome (PICO) format. We extracted health conditions, population characteristics, outcome assessed, the method for feature extraction and selection, the algorithm used, and the validation approach. The methodological quality of included studies was assessed using the prediction model risk of bias assessment tool (PROBAST). A qualitative description of the characteristics of the included studies as well as a narrative data synthesis was performed.

Results: A total of 19 primary studies were included. The predictors most frequently used belonged to the areas of demographic characteristics and stroke assessment through clinical examination. Regarding the methods, linear and logistic regressions were the most frequently used and cross-validation was the preferred validation approach.

Conclusions: We identified several methodological limitations: small sample sizes, a limited number of external validation approaches, and high heterogeneity among input and output variables. Although these elements prevented a quantitative comparison across models, we defined the most frequently used models given a specific outcome, providing useful indications for the application of more complex machine learning algorithms in rehabilitation medicine.

Keywords: Automated pattern recognition; Clinical; Efficacy treatment; Machine learning; Prognosis; Regression analysis; Rehabilitation; Rehabilitation outcome; Stroke.

Fig. 1

Terminology used in this review paper regarding the technical steps and parts of the models

Fig. 2

Study flow-chart. It is reported the number of papers screened and the reasons for exclusion

Fig. 3

Frequencies of the predictor classes among models (N = 31)

Fig. 4

Algorithms (on the left) and validation approaches (on the right) among the best performing models (N = 31). FOS fast orthogonal search, LogR Logistic Regression, LR Linear Regression, SVM Support Vector Machines, kNN k-Nearest Neighbours, RF Random Forest, NN Neural Network, PCI Parallel Cascade Identification

Fig. 5

Alluvial charts reporting an overview of the models. They show outcome measures—outcome classes—predictor classes (top) and the number of participants—validation approach—algorithm (bottom)