A Machine Learning Approach to Determine the Risk Factors for Fall in Multiple Sclerosis

Overview

Journal BMC Med Inform Decis Mak

Publisher Biomed Central

Specialty Medical Informatics

Date 2024 Jul 31

PMID 39080657

Authors

Su Ozgur

Meryem Kocaslan Toran

Ismail Toygar

Gizem Yagmur Yalcin

Mefkure Eraksoy

Affiliations

Soon will be listed here.

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.

Citing Articles

Linking Pathogenesis to Fall Risk in Multiple Sclerosis.

Patel J, Fraix M, Agrawal D Arch Intern Med Res. 2025; 8(1):36-47.

PMID: 40041760 PMC: 11879276. DOI: 10.26502/aimr.0194.

References

Gunn H, Creanor S, Haas B, Marsden J, Freeman J . Frequency, characteristics, and consequences of falls in multiple sclerosis: findings from a cohort study. Arch Phys Med Rehabil. 2013; 95(3):538-45. DOI: 10.1016/j.apmr.2013.08.244. View

Schumann P, Scholz M, Trentzsch K, Jochim T, Sliwinski G, Malberg H . Detection of Fall Risk in Multiple Sclerosis by Gait Analysis-An Innovative Approach Using Feature Selection Ensemble and Machine Learning Algorithms. Brain Sci. 2022; 12(11). PMC: 9688245. DOI: 10.3390/brainsci12111477. View

Tajali S, Shaterzadeh-Yazdi M, Negahban H, van Dieen J, Mehravar M, Majdinasab N . Predicting falls among patients with multiple sclerosis: Comparison of patient-reported outcomes and performance-based measures of lower extremity functions. Mult Scler Relat Disord. 2017; 17:69-74. DOI: 10.1016/j.msard.2017.06.014. View

Hempel S, Graham G, Fu N, Estrada E, Chen A, Miake-Lye I . A systematic review of the effects of modifiable risk factor interventions on the progression of multiple sclerosis. Mult Scler. 2017; 23(4):513-524. DOI: 10.1177/1352458517690271. View

Harris J, Brand J, Cote M, Faucett S, Dhawan A . Research Pearls: The Significance of Statistics and Perils of Pooling. Part 1: Clinical Versus Statistical Significance. Arthroscopy. 2017; 33(6):1102-1112. DOI: 10.1016/j.arthro.2017.01.053. View

Bazelier M, van Staa T, Uitdehaag B, Cooper C, Leufkens H, Vestergaard P . The risk of fracture in patients with multiple sclerosis: the UK general practice research database. J Bone Miner Res. 2011; 26(9):2271-9. PMC: 3193376. DOI: 10.1002/jbmr.418. View

Davalos-Bichara M, Lin F, Carey J, Walston J, Fairman J, Schubert M . Development and validation of a falls-grading scale. J Geriatr Phys Ther. 2012; 36(2):63-7. PMC: 3867809. DOI: 10.1519/JPT.0b013e31825f6777. View

Coote S, Comber L, Quinn G, Santoyo-Medina C, Kalron A, Gunn H . Falls in People with Multiple Sclerosis: Risk Identification, Intervention, and Future Directions. Int J MS Care. 2021; 22(6):247-255. PMC: 7780704. DOI: 10.7224/1537-2073.2020-014. View

McGuigan C, Hutchinson M . The multiple sclerosis impact scale (MSIS-29) is a reliable and sensitive measure. J Neurol Neurosurg Psychiatry. 2004; 75(2):266-9. PMC: 1738881. View

10.

Cameron M, Thielman E, Mazumder R, Bourdette D . Predicting falls in people with multiple sclerosis: fall history is as accurate as more complex measures. Mult Scler Int. 2013; 2013:496325. PMC: 3804404. DOI: 10.1155/2013/496325. View

11.

Ponce de Leon-Sanchez E, Dominguez-Ramirez O, Herrera-Navarro A, Rodriguez-Resendiz J, Paredes-Orta C, Mendiola-Santibanez J . A Deep Learning Approach for Predicting Multiple Sclerosis. Micromachines (Basel). 2023; 14(4). PMC: 10141207. DOI: 10.3390/mi14040749. View

12.

Sandroff B, Motl R, Sosnoff J, Pula J . Further validation of the Six-Spot Step Test as a measure of ambulation in multiple sclerosis. Gait Posture. 2014; 41(1):222-7. DOI: 10.1016/j.gaitpost.2014.10.011. View

13.

Ross E, Purtill H, Uszynski M, Hayes S, Casey B, Browne C . Cohort Study Comparing the Berg Balance Scale and the Mini-BESTest in People Who Have Multiple Sclerosis and Are Ambulatory. Phys Ther. 2016; 96(9):1448-55. DOI: 10.2522/ptj.20150416. View

14.

Iezzoni L, Rao S, Kinkel R . Patterns of mobility aid use among working-age persons with multiple sclerosis living in the community in the United States. Disabil Health J. 2010; 2(2):67-76. DOI: 10.1016/j.dhjo.2008.12.001. View

15.

Khan F, Amatya B, Kesselring J, Galea M . Telerehabilitation for persons with multiple sclerosis. Cochrane Database Syst Rev. 2015; (4):CD010508. PMC: 7211044. DOI: 10.1002/14651858.CD010508.pub2. View

16.

Coote S, Sosnoff J, Gunn H . Fall Incidence as the Primary Outcome in Multiple Sclerosis Falls-Prevention Trials: Recommendation from the International MS Falls Prevention Research Network. Int J MS Care. 2015; 16(4):178-84. PMC: 4321456. DOI: 10.7224/1537-2073.2014-059. View

17.

Rice L, Kalron A, Berkowitz S, Backus D, Sosnoff J . Fall prevalence in people with multiple sclerosis who use wheelchairs and scooters. Medicine (Baltimore). 2017; 96(35):e7860. PMC: 5585490. DOI: 10.1097/MD.0000000000007860. View

18.

Prosperini L, Kouleridou A, Petsas N, Leonardi L, Tona F, Pantano P . The relationship between infratentorial lesions, balance deficit and accidental falls in multiple sclerosis. J Neurol Sci. 2011; 304(1-2):55-60. DOI: 10.1016/j.jns.2011.02.014. View

19.

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. DOI: 10.1177/0269215513517575. View

20.

Nilsagard Y, Gunn H, Freeman J, Hoang P, Lord S, Mazumder R . Falls in people with MS--an individual data meta-analysis from studies from Australia, Sweden, United Kingdom and the United States. Mult Scler. 2014; 21(1):92-100. PMC: 4361466. DOI: 10.1177/1352458514538884. View