Fall Risk Prediction Model for Chinese Community-Dwelling Older Adults Aged 60+

Zhihao Jin; Xinghua Ma

doi:10.54097/2pamxe08

Authors

Zhihao Jin
Xinghua Ma

DOI:

https://doi.org/10.54097/2pamxe08

Keywords:

Elderly, Falls, Risk Assessment, Prediction Model.

Abstract

Background: Falls among community-dwelling Chinese older adults are a significant public health issue. This study aimed to develop a predictive model for fall risk in individuals aged ≥60 years. Methods: We analyzed data from four waves of the China Health and Retirement Longitudinal Study (CHARLS, 2011-2018) to assess fall status and associated factors. Socio-demographic, socio-economic, and emotional variables were summarized using descriptive statistics. Multiple machine-learning methods (Random Forest, Boruta, XGBoost, and ABESS) identified key predictors, which were incorporated into a logistic regression model. Model performance was evaluated via the AUC, and the optimal model was visualized with a nomogram. Results: Sex, history of chronic diseases, hearing status, sleep duration, self-reported pain, and depression score were significantly associated with fall risk. The model demonstrated good predictive accuracy (AUC=0.685,95% CI: 0.650-0.721). Conclusion: Our predictive model provides an effective tool for early identification of high-risk elderly individuals, facilitating personalized interventions to reduce falls and enhance quality of life.

Downloads

Download data is not yet available.

References

[1] Chamie J. Population Ageing: An Inescapable Future. https://www.globalissues.org/news/2022/01/05/29746.

[2] Colon-Emeric C S, McDermott C L, Lee D S, et al. Risk Assessment and Prevention of Falls in Older Community-Dwelling Adults: A Review. JAMA, 2024, 331 (16): 1397-1406.

[3] Phelan E A, Ritchey K. Fall Prevention in Community-Dwelling Older Adults. Ann Intern Med, 2018, 169 (11): C81-C96.

[4] Rikkonen T, Sund R, Koivumaa-Honkanen H, et al. Effectiveness of exercise on fall prevention in community-dwelling older adults: a 2-year randomized controlled study of 914 women. Age Ageing, 2023, 52 (4).

[5] Wang J, Chen Z, Song Y. Falls in aged people of the Chinese mainland: epidemiology, risk factors and clinical strategies. Ageing Res Rev, 2010, 9 Suppl 1: S13-S17.

[6] Hsieh K L, Chen L, Sosnoff J J. Mobile Technology for Falls Prevention in Older Adults. J Gerontol A Biol Sci Med Sci, 2023, 78 (5): 861-868.

[7] Howcroft J, Kofman J, Lemaire E D. Review of fall risk assessment in geriatric populations using inertial sensors. J Neuroeng Rehabil, 2013, 10 (1): 91.

[8] Kang C M. Risk Factors for Falls Among Older Adults with Diabetes in the Community: A Zero-Inflated Negative Binomial Regression Model. J Community Health Nurs, 2025, 42 (1): 1-10.

[9] Bourke R, Doody P, Perez S, et al. Cardiovascular Disorders and Falls Among Older Adults: A Systematic Review and Meta-Analysis. J Gerontol A Biol Sci Med Sci, 2024, 79 (2).

[10] Lima C A, Ricci N A, Nogueira E C, et al. The Berg Balance Scale as a clinical screening tool to predict fall risk in older adults: a systematic review. Physiotherapy, 2018, 104 (4): 383-394.

[11] Omana H, Bezaire K, Brady K, et al. Functional Reach Test, Single-Leg Stance Test, and Tinetti Performance-Oriented Mobility Assessment for the Prediction of Falls in Older Adults: A Systematic Review. Phys Ther, 2021, 101 (10).

[12] Yoshimoto Y, Tanaka M, Sakamoto A. Effective Combined Assessments of Weight Bearing Ratio and Four Square Step Test in Predicting Falls in Discharged Stroke Patients. J Stroke Cerebrovasc Dis, 2021, 30 (3): 105582.

[13] Park S H, Lee Y S. The Diagnostic Accuracy of the Berg Balance Scale in Predicting Falls. West J Nurs Res, 2017, 39 (11): 1502-1525.

[14] Chen M, Wang H, Yu L, et al. A Systematic Review of Wearable Sensor-Based Technologies for Fall Risk Assessment in Older Adults. Sensors (Basel), 2022, 22 (18).

[15] Bezold J, Krell-Roesch J, Eckert T, et al. Sensor-based fall risk assessment in older adults with or without cognitive impairment: a systematic review. Eur Rev Aging Phys Act, 2021, 18 (1): 15.

[16] Antcliff S R, Witchalls J B, Wallwork S B, et al. Developing a multivariate prediction model of falls among older community-dwelling adults using measures of neuromuscular control and proprioceptive acuity: A pilot study. Australas J Ageing, 2023, 42 (3): 463-471.

[17] Andreasson K, Hesselstrand R. Fall Prevention in Community-Dwelling Older Adults. N Engl J Med, 2020, 382 (26): 2580.

[18] Montero-Odasso M, Van der Velde N, Alexander N B, et al. New horizons in falls prevention and management for older adults: a global initiative. Age Ageing, 2021, 50 (5): 1499-1507.

[19] Smith M L, Stevens J A, Ehrenreich H, et al. Healthcare providers' perceptions and self-reported fall prevention practices: findings from a large new york health system. Front Public Health, 2015, 3: 17.

[20] Casey C M, Parker E M, Winkler G, et al. Lessons Learned From Implementing CDC's STEADI Falls Prevention Algorithm in Primary Care. Gerontologist, 2017, 57 (4): 787-796.

[21] Hu J, Szymczak S. A review on longitudinal data analysis with random forest. Brief Bioinform, 2023, 24 (2).

[22] Huang Y, Huang W, Ma X, et al. Nomogram for predicting mild cognitive impairment in Chinese elder CSVD patients based on Boruta algorithm. Front Aging Neurosci, 2025, 17: 1431421.

[23] Zhou H, Xin Y, Li S. A diabetes prediction model based on Boruta feature selection and ensemble learning. BMC Bioinformatics, 2023, 24 (1): 224.

[24] Shin H. XGBoost Regression of the Most Significant Photoplethysmogram Features for Assessing Vascular Aging. IEEE J Biomed Health Inform, 2022, 26 (7): 3354-3361.

[25] Ogunleye A, Wang Q G. XGBoost Model for Chronic Kidney Disease Diagnosis. IEEE/ACM Trans Comput Biol Bioinform, 2020, 17 (6): 2131-2140.

[26] Ilic M, Srdjevic Z, Srdjevic B. Water quality prediction based on Naive Bayes algorithm. Water Sci Technol, 2022, 85 (4): 1027-1039.

[27] Xiong Y, Ye M, Wu C. Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble. Comput Math Methods Med, 2021, 2021: 5556992.

[28] Virgolici O, Virgolici H. Predicting Prediabetes Using Simple a Multi-Layer Perceptron Neural Network Model. Stud Health Technol Inform, 2023, 305: 168-171.

[29] Lorencin I, Andelic N, Spanjol J, et al. Using multi-layer perceptron with Laplacian edge detector for bladder cancer diagnosis. Artif Intell Med, 2020, 102: 1017-1046.

[30] Gopinath B, McMahon C M, Burlutsky G, et al. Hearing and vision impairment and the 5-year incidence of falls in older adults. Age Ageing, 2016, 45 (3): 409-414.

[31] Yesantharao L V, Vohra V, Cheng M, et al. Olfactory Dysfunction and Balance Dysfunction are Associated with Increased Falls in Older Adults. Laryngoscope, 2023, 133 (8): 1964-1969.

[32] Coulter J S, Randazzo J, Kary E E, et al. Falls in Older Adults: Approach and Prevention. Am Fam Physician, 2024, 109 (5): 447-456.

[33] Mesrine S, Boutron-Ruault M C, Clavel-Chapelon F. Chronic pain and risk of falls in older adults. JAMA, 2010, 303 (12): 1147-1148, 1148-1149.

[34] Moncayo-Hernandez B A, Duenas-Suarez E P, Reyes-Ortiz C A. Relationship between Social Participation, Children's Support, and Social Frailty with Falls among Older Adults in Colombia. Ann Geriatr Med Res, 2024, 28 (3): 342-351.

[35] Zhang L, Liu S, Li Y, et al. Associations of Sleep Quality with Gait Speed and Falls in Older Adults: The Mediating Effect of Muscle Strength and the Gender Difference. Gerontology, 2022, 68 (1): 1-7.

[36] Mesas A E, Lopez-Garcia E, Rodriguez-Artalejo F. Self-reported sleep duration and falls in older adults. J Sleep Res, 2011, 20 (1): 21-27.

[37] Lin F R, Ferrucci L. Hearing loss and falls among older adults in the United States. Arch Intern Med, 2012, 72 (4): 369-371.

[38] Yeo B, Tan V, Ng J H, et al. Hearing Loss and Falls: A Systematic Review and Meta-Analysis. JAMA Otolaryngol Head Neck Surg, 2025.

[39] Riska K M, Peskoe S B, Kuchibhatla M, et al. Impact of Hearing Aid Use on Falls and Falls-Related Injury: Results From the Health and Retirement Study. Ear Hear, 2022, 43 (2): 487-494.

[40] Feng Y, Liu Y, Fang Y, et al. Advances in the application of wearable sensors for gait analysis after total knee arthroplasty: a systematic review. Arthroplasty, 2023, 5 (1): 49.