Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul 30;24(1):215.
doi: 10.1186/s12911-024-02621-0.

A machine learning approach to determine the risk factors for fall in multiple sclerosis

Su Özgür  1   2 , Meryem Koçaslan Toran  3   4 , İsmail Toygar  5 , Gizem Yağmur Yalçın  6 , Mefkure Eraksoy  7
Affiliations

A machine learning approach to determine the risk factors for fall in multiple sclerosis

Su Özgür et al. BMC Med Inform Decis Mak. .

Abstract

Background: Falls in multiple sclerosis can result in numerous problems, including injuries and functional loss. Therefore, determining the factors contributing to falls in people with Multiple Sclerosis (PwMS) is crucial. This study aims to investigate the contributing factors to falls in multiple sclerosis using a machine learning approach.

Methods: This cross-sectional study was conducted with 253 PwMS admitted to the outpatient clinic of a university hospital between February and August 2023. A sociodemographic data collection form, Fall Efficacy Scale (FES-I), Berg Balance Scale (BBS), Fatigue Severity Scale (FSS), Expanded Disability Status Scale (EDSS), Multiple Sclerosis Impact Scale (MSIS-29), and Timed 25 Foot Walk Test (T25-FW) were used for data collection. Gradient-boosting algorithms were employed to predict the important variables for falls in PwMS. The XGBoost algorithm emerged as the best performed model in this study.

Results: Most of the participants (70.0%) were female, with a mean age of 40.44 ± 10.88 years. Among the participants, 40.7% reported a fall history in the last year. The area under the curve value of the model was 0.713. Risk factors of falls in PwMS included MSIS-29 (0.424), EDSS (0.406), marital status (0.297), education level (0.240), disease duration (0.185), age (0.130), family type (0.119), smoking (0.031), income level (0.031), and regular exercise habit (0.026).

Conclusions: In this study, smoking and regular exercise were the modifiable factors contributing to falls in PwMS. We recommend that clinicians facilitate the modification of these factors in PwMS. Age and disease duration were non-modifiable factors. These should be considered as risk increasing factors and used to identify PwMS at risk. Interventions aimed at reducing MSIS-29 and EDSS scores will help to prevent falls in PwMS. Education of individuals to increase knowledge and awareness is recommended. Financial support policies for those with low income will help to reduce the risk of falls.

Keywords: Fall; Machine learning; Multiple sclerosis; Risk factors,Risk prediction.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Study workflow
Fig. 2
Fig. 2
Flow chart of XGBoost Algorithm
Fig. 3
Fig. 3
Variable Importance in Machine Learning Analysis
Fig. 4
Fig. 4
AUC ROC for the prediction model
Fig. 5
Fig. 5
Regression estimates on the MSIS-29 subscales on falls
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Khan F, Amatya B, Kesselring J, Galea M. Telerehabilitation for persons with multiple sclerosis. Cochrane Database Syst Rev. 2015;4:CD010508. - PMC - PubMed
    1. Walton C, King R, Rechtman L, Kaye W, Leray E, Marrie RA, et al. Rising prevalence of multiple sclerosis worldwide: Insights from the Atlas of MS. Mult Scler J. 2020;26(14):1816–21.10.1177/1352458520970841 - DOI - PMC - PubMed
    1. Gunn HJ, Newell P, Haas B, Marsden JF, Freeman JA. Identification of risk factors for falls in multiple sclerosis: a systematic review and meta-analysis. Phys Ther. 2013;93(4):504–13. 10.2522/ptj.20120231 - DOI - PubMed
    1. Filli L, Sutter T, Easthope CS, Killeen T, Meyer C, Reuter K, et al. Profiling walking dysfunction in multiple sclerosis: characterisation, classification and progression over time. Sci Rep. 2018;8(1):4984. 10.1038/s41598-018-22676-0 - DOI - PMC - PubMed
    1. Gianni C, Prosperini L, Jonsdottir J, Cattaneo D. A systematic review of factors associated with accidental falls in people with multiple sclerosis: a meta-analytic approach. Clin Rehabil. 2014;28(7):704–16. 10.1177/0269215513517575 - DOI - PubMed

LinkOut - more resources