Use of Machine Learning in Stroke Rehabilitation: A Narrative Review

Abstract

A narrative review was conducted of machine learning applications and research in the field of stroke rehabilitation. The machine learning models commonly used in medical research include random forest, logistic regression, and deep neural networks. Convolutional neural networks (CNNs), a type of deep neural network, are typically used for image analysis. Machine learning has been used in stroke rehabilitation to predict recovery of motor function using a large amount of clinical data as input. Recent studies on predicting motor function have trained CNN models using magnetic resonance images as input data together with clinical data to increase the accuracy of motor function prediction models. Additionally, a model interpreting videofluoroscopic swallowing studies was developed and investigated. In the future, we anticipate that machine learning will be actively used to treat stroke patients, such as predicting the occurrence of depression and the recovery of language, cognitive, and sensory function, as well as prescribing appropriate rehabilitation treatments.

Artificial Intelligence and the Evaluation and Treatment of Stroke

“… 8 By analyzing clinical and imaging data, AI may also be able to predict which patients will suffer from depression and cognitive dysfunction after strokes. 8 …”

“…It likely also can assist in developing programs to help with the treatment of speech, language and vision problems. 8 By analyzing clinical and imaging data, AI may also be able to predict which patients will suffer from depression and cognitive dysfunction after strokes. 8 Dysphagia is a common complication of stroke.…”

Exploring Machine Learning for Predicting Cerebral Stroke: A Study in Discovery

“…Different ML models such as Random Forest Classification, K-Nearest Neighbors, Support Vector Machine, and Naïve Bayes Classification, imply multiple physiological factors to predict stroke, and Naïve Bayes emerges as the most effective algorithm, achieving an accuracy of around 82% on kaggle dataset with 5110 sample [14]. Their objectives encompassed the creation of ML prediction models for stroke disease, tackling the challenge of severe class imbalance presented by stroke patients while simultaneously delving into the model's decision-making process but achieving low accuracy (73.52%) and high FP rate (26.57%) using Logistic Regression on kaggle dataset [15]. Particularly, ML methods, including Deep Neural Networks (DNN), have proven instrumental in predicting motor outcomes in the upper and lower limbs six months post-stroke [16].…”

“…Another noteworthy endeavor involved a meticulous review of current state-of-the-art ML approaches for brain stroke, classified based on functionality or resemblance [15]. A study methodically scrutinizes diverse patient records to enhance stroke prediction and implements different ML-based classification using a dataset encompassing 29,072 patient records but gain 77% accuracy after using neural network [17].…”

Large language models in physical therapy: time to adapt and adept

“…We must embrace AI and ML, explore the capabilities of these technologies, and identify opportunities for integrating them into our practice. Start small, experiment, and learn from experience to become familiar with BioMed-LLMs and Biomed Natural Language Processing (NLP) ( 54 ). These support tools are crucial for navigating the vast medical literature, extracting valuable insights and mastering Biomed-NLP allows one to process and interpret complex medical information, enhancing one’s understanding and decision-making by contributing to dataset fine-tuning , our expertise will become invaluable in ensuring that AI and ML models are trained on accurate and scientifically transparent data ( 55 , 56 ).…”