AI-assisted assessment of fall risk in multiple sclerosis: A systematic literature review

Abstract

Background

Multiple sclerosis (MS) is an autoimmune disease that can increase the risk of falls in patients due to various factors. Traditional clinical assessments may not effectively identify those at risk of falling.

Objective

This study aimed to use artificial intelligence and machine learning techniques to predict the likelihood of falls in patients with MS based on a review of previous research.

Methods

A systematic review was conducted following PRISMA guidelines, searching electronic databases from 1990 to 2024. Data extraction and quality assessment were carried out.

Results

Seven studies were analyzed, and it was determined that patient-reported outcomes (PROs) such as MSWS-12 and EMIQ performed better than other methods. Sensor-based systems such as GAITRite and Mobility Lab achieved high F1 scores. Random forest classifiers utilizing postural sway measures were effective in discriminating low-risk MS patients from healthy controls. Deep learning models, particularly BiLSTM architectures, outperformed traditional machine learning approaches in identifying recent fallers using wearable accelerometer data.

Conclusion

The findings highlight the potential of PROs, the promise of wearable sensors and deep learning, and the importance of optimizing data collection for effective fall risk assessment in the MS population.