Sağlık Hizmetinde Yapay Zeka: Makine Öğrenmesi Teknikleri Kullanılarak Yaşlılarda Düşme Riski Tespiti

Year 2025, EARLY VIEW, 1 - 1

Gökçe Özden Gürcan , Hakan Gokdas , Ebru Turan Kızıldoğan

https://doi.org/10.2339/politeknik.1446723

Abstract

Yaşlılara daha bağımsız bir yaşam sağlamak için birçok girişimde bulunulmaktadır. Bu yaş grubundaki insanların karşılaştığı temel sorunlardan biri düşme olaylarıdır. Düşme, yaşlılar arasında en sık görülen kazalardan biridir ve hastanede kalış süresinin uzamasına ve tıbbi maliyetlerin artmasına neden olabilmektedir. Yaşlı nüfusun artması nedeniyle düşme tespiti gibi bakım hizmetlerine olan ihtiyaç da artmaktadır. Bu çalışmada yaşlıların düşme riskinin tahmin edilmesi amacıyla makine öğrenmesi teknikleri (Logistic Regresyon, Random Forest, Decision Tree) kullanılmıştır. Veri setinde yer alan kişilerin fiziksel ve klinik özelliklerinin yanı sıra girdi ve çıktıların elde edilmesi için düşme riski değerlendirme yöntemleri kullanılmıştır.
Bu çalışma, yaşlı bireylerin düşme risk faktörlerini belirlemek ve tahminlerde bulunmak amacıyla, sağlık profesyonellerinin düşme riski değerlendirme sürecini kolaylaştırmak amacıyla yapılmıştır. Düşme tahmininin sonuçlarına dayanarak bu sayede, yaşlı bireylerin düşme oranlarını azaltmak için bireyselleştirilmiş düşme önleme müdahaleleri geliştirilebilecektir.

Keywords

Düşme Riski, Makine Öğrenimi, Lojistik Regresyon, Karar Ağacı, Rastgele Orman Algoritması

Thanks

We thank the sharing of data for scientific researches by Michele Menezes, Ney Armando de Mello Meziat-Filho, Thiago Lemos, Arthur Sá Ferreira, and Camila Santos Araújo in the Rehabilitation Sciences department at the Augusto Motta University Center in Brazil.

Artificial Intelligence in Healthcare: Fall Risk Assessment in Older Adults Using Machine Learning Techniques

Abstract

There are many attempts to provide the elderly with a life more independently. One of the main problems facing people in this age group is fall events. Falls are one of the most common accidents among the elderly and may result in extended hospitalization and increased medical costs. The requirement for care services, such as fall detection, is increasing because of the growing population of elderly people. In this study, machine learning techniques- Logistic Regression, Random Forest, and Decision Tree are used to predict fall risk of elderly people. Fall risk assessment methods are used to obtain inputs and outputs in addition to the physical and clinical features of people in the dataset.
This study aimed to facilitate the fall risk assessment process of health professionals to determine the fall risk factors of elderly individuals and to make predictions. Based on the results of fall prediction, individualized fall prevention interventions can be developed to reduce the fall rates of elderly individuals.

Keywords

Fall Risk, Machine Learning, Random Forest, Logistic Regression, Decision Tree

References

• [1] Scheckel B., Stock S. and Müller D., "Cost-effectiveness of group-based exercise to prevent falls in elderly community-dwelling people", BMC geriatrics, 21, 1-9, (2021).
• [2] "İstatistiklerle Yaşlılar 2017", Türkiye İstatistik Kurumu (TUİK) 27587, (2018).
• [3] Gale C.R., Cooper C. and Aihie Sayer A., "Prevalence and risk factors for falls in older men and women: The English Longitudinal Study of Ageing", Age and ageing, 45(6), 789-794, (2016).
• [4] Rodrigues A.R.G.d.M., Assef J.C. and Lima C.B.d., "Assessment of risk factors associated with falls among the elderly in a municipality in the state of Paraíba, Brazil. A cross-sectional study", Sao Paulo Medical Journal, 137, 430-437, (2020).
• [5] Organization W.H. and Unit L.C., "WHO global report on falls prevention in older age", World Health Organization, (2008).
• [6] Pérez-Ros P., Martínez-Arnau F.M., Orti-Lucas R.M. and Tarazona-Santabalbina F.J., "A predictive model of isolated and recurrent falls in functionally independent community-dwelling older adults", Brazilian journal of physical therapy, 23(1), 19-26, (2019).
• [7] Liu C.-H., Hu Y.-H. and Lin Y.-H., "A machine learning–based fall risk assessment model for inpatients", CIN: Computers, Informatics, Nursing, 39(8),450-459, (2021).
• [8] Rafiq M., McGovern A., Jones S., Harris K., Tomson C., Gallagher H. and de Lusignan S., "Falls in the elderly were predicted opportunistically using a decision tree and systematically using a database-driven screening tool", Journal of clinical epidemiology, 67(8), 877-886, (2014).
• [9] Razmara J., Zaboli M.H. and Hassankhani H., "Elderly fall risk prediction based on a physiological profile approach using artificial neural networks", Health informatics journal, 24(4), 410-418, (2018).
• [10] Bongue B., Dupré C., Beauchet O., Rossat A., Fantino B. and Colvez A., "A screening tool with five risk factors was developed for fall-risk prediction in community-dwelling elderly", Journal of clinical epidemiology, 64(10), 1152-1160, (2011).
• [11] Millet A., Madrid A., Alonso-Webber J.M., Rodríguez-Mañas L. and Pérez-Rodríguez R., "Machine Learning techniques applied to the development of a fall risk index for older adults", IEEE Access, (2023).
• [12] Silva D.A., Branco N.F.L.C., de Andrade Mesquita L.S., Branco H.M.G.C. and de Alencar Barreto G., "Electromyography and dynamometry in the prediction of risk of falls in the elderly using machine learning tools", Biomedical Signal Processing and Control, 88, 105635, (2024).
• [13] Wang S., Nguyen T.K. and Bhatt T., "Trip-Related Fall Risk Prediction Based on Gait Pattern in Healthy Older Adults: A Machine-Learning Approach", Sensors, 23(12), 5536, (2023).
• [14] Chen X., He L., Shi K., Wu Y., Lin S. and Fang Y., "Interpretable machine learning for fall prediction among older adults in China", American journal of preventive medicine, (2023).
• [15] Chen X., Lin S., Zheng Y., He L. and Fang Y., "Long-term trajectories of depressive symptoms and machine learning techniques for fall prediction in older adults: Evidence from the China Health and Retirement Longitudinal Study (CHARLS)", Archives of Gerontology and Geriatrics, 111, 105012, (2023).
• [16] Yongjian L., Koryu S., Masato N., Hirokazu M., Katsunori K. and Naoki K., "Machine Learning–Based Prediction of Functional Disability: a Cohort Study of Japanese Older Adults in 2013–2019", Journal of General Internal Medicine, 1-8, (2023).
• [17] Sharma V., Kulkarni V., Joon T., Eurich D.T., Simpson S.H., Voaklander D., Wright B. and Samanani S., "Predicting falls-related admissions in older adults in Alberta, Canada: a machine-learning falls prevention tool developed using population administrative health data", BMJ open, 13(8), e071321, (2023).
• [18] Langsetmo L., Schousboe J.T., Taylor B.C., Cauley J.A., Fink H.A., Cawthon P.M., Kado D.M., Ensrud K.E. and Group O.F.i.M.R., "Advantages and disadvantages of random forest models for prediction of hip fracture risk versus mortality risk in the oldest old", JBMR plus, 7(8), e10757, (2023).
• [19] Ikeda T., Cooray U., Hariyama M., Aida J., Kondo K., Murakami M. and Osaka K., "An interpretable machine learning approach to predict fall risk among community-dwelling older adults: a three-year longitudinal study", Journal of General Internal Medicine, 37(11), 2727-2735, (2022).
• [20] Lathouwers E., Dillen A., Díaz M.A., Tassignon B., Verschueren J., Verté D., De Witte N. and De Pauw K., "Characterizing fall risk factors in Belgian older adults through machine learning: a data-driven approach", BMC public health, 22(1), 2210, (2022).
• [21] Mishra A.K., Skubic M., Despins L.A., Popescu M., Keller J., Rantz M., Abbott C., Enayati M., Shalini S. and Miller S., "Explainable fall risk prediction in older adults using gait and geriatric assessments", Frontiers in digital health, 4, 869812, (2022).
• [22] Gökler S.H., Yılmaz D., Ürük Z.F. and Boran S., "A new hybrid risk assessment method based on Fine-Kinney and ANFIS methods for evaluation spatial risks in nursing homes", Heliyon, 8(10), (2022).
• [23] Makino K., Lee S., Bae S., Chiba I., Harada K., Katayama O., Tomida K., Morikawa M. and Shimada H., "Simplified decision-tree algorithm to predict falls for community-dwelling older adults", Journal of clinical medicine, 10(21), 5184, (2021).
• [24] Yoo S. and Oh D., "An artificial neural network–based fall detection", International Journal of Engineering Business Management, 10, 1847979018787905, (2018).
• [25] Nait Aicha A., Englebienne G., Van Schooten K.S., Pijnappels M. and Kröse B., "Deep learning to predict falls in older adults based on daily-life trunk accelerometry", Sensors, 18(5), 1654, (2018).
• [26] Deschamps T., Le Goff C.G., Berrut G., Cornu C. and Mignardot J.-B., "A decision model to predict the risk of the first fall onset", Experimental gerontology, 81, 51-55, (2016).
• [27] Vidigal M., Lima M. and Neto A.D.A., "Elder falls detection based on artificial neural networks", Fourteenth Mexican International Conference on Artificial Intelligence (MICAI), 226-230, (2015).
• [28] Menezes M., de Mello Meziat-Filho N.A., Araújo C.S., Lemos T. and Ferreira A.S., "Agreement and predictive power of six fall risk assessment methods in community-dwelling older adults", Archives of Gerontology and Geriatrics, 87, 103975, (2020).
• [29] Camargos F.F., Dias R.C., Dias J. and Freire M.T., "Adaptação transcultural e avaliação das propriedades psicométricas da Falls Efficacy Scale-International em idosos brasileiros (FES-I-BRASIL)", Brazilian journal of physical therapy, 14, 237-243, (2010).
• [30] Gates S., Smith L.A., Fisher J.D. and Lamb S.E., "Systematic review of accuracy of screening instruments for predicting fall risk among independently living older adults", Database of Abstracts of Reviews of Effects (DARE): Quality-assessed Reviews [Internet], (2008).
• [31] Berg K., Wood-Dauphine S., Williams J. and Gayton D., "Measuring balance in the elderly: preliminary development of an instrument", Physiotherapy Canada, 41(6), 304-311, (1989).
• [32] Berg K., "Measuring balance in the elderly: Development and validation of an instrument", Canadian journal of public health, 83, 7-11, (1992).
• [33] Chiu A.Y., Au-Yeung S.S. and LO S.K., "A comparison of four functional tests in discriminating fallers from non-fallers in older people", Disability and rehabilitation, 25(1), 45-50, (2003).
• [34] Yardley L., Beyer N., Hauer K., Kempen G., Piot-Ziegler C. and Todd C., "Development and initial validation of the Falls Efficacy Scale-International (FES-I)", Age and ageing, 34(6), 614-619, (2005).
• [35] El Miedany Y., El Gaafary M., Toth M., Palmer D. and Ahmed I., "Falls risk assessment score (FRAS): time to rethink", Journal of clinical Gerontology and Geriatrics, 2(1), 21-26, (2011).
• [36] Lopes C.S., Faerstein E. and Chor D., "Stressful life events and common mental disorders: results of the Pro-Saude Study", Cadernos de saude publica, 19, 1713-1720, (2003).
• [37] Wild Ali A.B., "Prediction of employee turn over using random forest classifier with intensive optimized pca algorithm", Wireless Personal Communications, 119(4), 3365-3382, (2021).
• [38] Freund Y. and Schapire R.E., "Experiments with a new boosting algorithm", icml, 148-156
• [39] Breiman L., "Random forests", Machine learning, 45, 5-32, (2001).
• [40] Biau G. and Scornet E., "A random forest guided tour", Test, 25, 197-227, (2016).
• [41] Rokach L. and Maimon O., "Data mining and knowledge discovery handbook", Springer New York, (2010).
• [42] Kothari R. and Dong M., "Decision trees for classification: A review and some new results", Pattern recognition: from classical to modern approaches, 169-184, (2001).
• [43] Niuniu X. and Yuxun L., "Notice of Retraction: Review of decision trees", 3rd international conference on computer science and information technology, 105-109, (2010).
• [44] Pedregosa F., "Scikit‐learn: Machine learning in python Fabian", Journal of machine learning research, 12, 2825, (2011).
• [45] Freund Y. and Schapire R.E., "A decision-theoretic generalization of on-line learning and an application to boosting", Journal of computer and system sciences, 55(1), 119-139, (1997).
• [46] Drucker H., "Improving regressors using boosting techniques", Icml, e115, (1997).
• [47] Shrestha D.L. and Solomatine D.P., "Experiments with AdaBoost. RT, an improved boosting scheme for regression", Neural computation, 18(7), 1678-1710, (2006).
• [48] Sejuti Z.A., Islam M.S., “A hybrid CNN–KNN approach for identification of COVID-19 with 5-fold cross validation”, Sensors International, 4 (2023).