Unveiling Fall Triggers in Older Adults: A Machine Learning Graphical Model Analysis
Abstract
:1. Introduction
1.1. Related Studies
1.2. Study Objectives
2. Materials and Proposed Method
2.1. Study Design and Participants
2.2. Study Variables/Features
- Sociodemographic and Self-rated Health. Sociodemographic variables were obtained using a self-report questionnaire [22]. Participant age was collected numerically and gender categorically. Participant’s race consisted of White and Non-White, where the Non-White category included Hispanic, African-American, and Asian older adults. The level of education was divided into two categories, high school or below and college or higher. Financial difficulty was categorized as adequate or less and more than adequate. Household composition was defined as living alone or living with others. Self-rated health status was acquired using a five-point Likert scale, and participants were classified as excellent, very good, or good or below.
- Psychological Status. Depressive symptoms were assessed using the self-report PHQ-9, which consists of nine items assessed using a four-point scale [26,27]. Anxiety was assessed by the GAI-SF, which comprises only five of the original items, has a closed-choice response format (yes/no), and is scored in a single direction [28]. Additionally, participants’ attention and awareness of present occurrence (mindfulness) were evaluated using the MAAS, a fifteen-item questionnaire on a six-point scale [29]. These features are continuously distributed.
- Body Composition Measurements. Height was measured in centimeters and weight was measured in kilograms with no shoes. The body mass index was calculated as the weight divided by the square of height (kg/m2). The body composition measurements comprised whole-body, trunk, and both sides’ limbs at six different frequencies (1, 5, 50, 250, 500, and 1000 kHz). Fat and water measurements were recorded including intracellular water, extracellular water, total body water, body fat mass, lean body mass, dry lean mass, skeletal muscle mass, skeletal muscle index, visceral fat level, visceral fat area, and basal metabolic rate results.
- Fall Risks’ Self-assessments and Performance Tests.
- -
- Frailty was evaluated through the FRAIL scale, a self-report questionnaire comprising five items assessing fatigue, resistance, ambulation, illnesses, and weight loss [30].
- -
- The short FES-I questionnaire was employed to assess the fear of falling, consisting of seven items measuring the level of concern related to falling during the performance of daily activities on a four-point Likert scale [31].
- -
- The STEADI algorithm is a self-risk checklist consisting of twelve questions that focus on fall risk factors [32].
- -
- The brief version of the Senior Technology Acceptance (STA) was employed to measure older adults’ acceptance of technology. The questionnaire contains four domains with fourteen items on a ten-point scale [33].
- -
- For performance tests, grip strength, an indicator of hand and forearm muscle strength, was collected numerically on both sides using a hydraulic hand dynamometer [34]. The 30 s STS test (also called the chair-stand test) was used to assess dynamic balance. Participants were directed to cross their arms over their chest, stand away from a chair, and return to a sitting position as many times as possible within 30 s. Any use of hands during the test resulted in a score of zero [35]. The BTrackS balance assessment consists of four 20 s trials, measuring postural sway by tracking the center of pressure on a force platform. The first trial is for familiarity, and each trial requires the participants to stand as still as possible on the balance plate with hands on their hips, eyes closed, and feet shoulder width apart [36].
- COVID-19 related questions. Participants were asked whether they had ever tested positive for COVID-19 and to rate their perception of COVID-19 severity in their community over the past month on a four-point Likert scale. Fear of COVID-19 was evaluated using the Fear of COVID-19 Scale (FCV-19S), a seven-item, four-point Likert scale adapted from [37].
- Accelerometer Data and Physical Activity Level. The processing of accelerometer data was carried out using the R package GGIR (version 2.4-0) [38], in which the minutes (per week) spent in sedentary behavior (SB), light physical activity (LPA), and moderate-to-vigorous physical activity (MVPA) were recorded. RAPA, a nine-item, self-administered questionnaire, was utilized to evaluate a wide range of physical activity levels, from sedentary to vigorous activity (the first seven questions; the total score is out of seven), as well as strength and flexibility training (scored separately; strength training , flexibility , both ) [39].
2.3. Graphical Models
2.4. Data Analysis Methods
2.4.1. Exploratory Data Analysis
2.4.2. Exploratory Factor Analysis on Body Composition Variables
- Common variance is the amount of variance shared among a set of variables. Communality (or ) is a common variance that ranges between 0 and 1, with closer to 1 suggesting that the extracted factors explain more of the variance of an individual item.
- Unique variance (or ) consists of specific variance and error variance, and it is any portion of variance that is not common [46].
2.4.3. Model Development and Validation
Algorithm 1 The Mixed Undirected Graphical Model (MUGM) Method |
|
3. Results
3.1. Participant Characteristics
3.2. Mixed Undirected Graphical Models: Relationships between All Features
3.3. Spearman’s Correlation and Correlation Matrix
3.4. Exploratory Factor Analysis on Body Composition Measurements
4. Discussion
4.1. Main Findings
4.2. Limitations
5. Conclusions and Future Work
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Centers for Disease Control and Prevention. Facts About Falls. 2017. Available online: https://www.cdc.gov/falls/facts.html (accessed on 16 October 2023).
- Lee, H.; Lim, J.H. Living Alone, Environmental Hazards, and Falls Among U.S. Older Adults. Innov. Aging 2023, 7, igad055. [Google Scholar] [CrossRef] [PubMed]
- Byun, M.; Kim, J.; Kim, J.E. Physical and Psychological Factors Contributing to Incidental Falls in Older Adults Who Perceive Themselves as Unhealthy: A Cross-Sectional Study. Int. J. Environ. Res. Public Health 2021, 18, 3738. [Google Scholar] [CrossRef] [PubMed]
- Falsarella, G.R.; Gasparotto, L.P.R.; Barcelos, C.C.; Coimbra, I.B.; Moretto, M.C.; Pascoa, M.A.; Ferreira, T.C.B.R.; Coimbra, A.M.V. Body composition as a frailty marker for the elderly community. Clin. Interv. Aging 2015, 10, 1661–1666, Place: New Zealand. [Google Scholar] [CrossRef] [PubMed]
- Thiamwong, L.; Xie, R.; Conner, N.E.; Renziehausen, J.M.; Ojo, E.O.; Stout, J.R. Body composition, fear of falling and balance performance in community-dwelling older adults. Transl. Med. Aging 2023, 7, 80–86. [Google Scholar] [CrossRef] [PubMed]
- World Health Organization. Decade of Healthy Ageing Connection Series No. 1—COVID-19. 2020. Available online: https://www.who.int/publications/m/item/decade-connection-series-no1 (accessed on 31 March 2024).
- Centers for Disease Control and Prevention. Severe Outcomes Among Patients with Coronavirus Disease 2019 (COVID-19)—United States, February 12–March 16, 2020. MMWR Morb. Mortal. Wkly. Rep. 2020, 69, 343–346. [Google Scholar] [CrossRef] [PubMed]
- Derrer-Merk, E.; Reyes-Rodriguez, M.F.; Soulsby, L.K.; Roper, L.; Bennett, K.M. Older adults’ experiences during the COVID-19 pandemic: A qualitative systematic literature review. BMC Geriatr. 2023, 23, 580. [Google Scholar] [CrossRef] [PubMed]
- Cocuzzo, B.; Wrench, A.; O’Malley, C. Effects of COVID-19 on Older Adults: Physical, Mental, Emotional, Social, and Financial Problems Seen and Unseen. Cureus 2022, 14, e29493. [Google Scholar] [CrossRef] [PubMed]
- Kiyoshi-Teo, H.; Izumi, S.S.; Stoyles, S.; McMahon, S.K. Older Adults’ Biobehavioral Fall Risks Were Affected by the COVID-19 Pandemic: Lessons Learned for Future Fall Prevention Research to Incorporate Multilevel Perspectives. Innov. Aging 2022, 6, igac033. [Google Scholar] [CrossRef] [PubMed]
- Vernooij-Dassen, M.; Verhey, F.; Lapid, M. The risks of social distancing for older adults: A call to balance. Int. Psychogeriatr. 2020, 32, 1235–1237. [Google Scholar] [CrossRef]
- Khaleghi, M.M.; Jamshidi, A.; Afrashteh, S.; Emamat, H.; Farhadi, A.; Nabipour, I.; Jalaliyan, Z.; Malekizadeh, H.; Larijani, B. The association of body composition and fat distribution with hypertension in community-dwelling older adults: The Bushehr Elderly Health (BEH) program. BMC Public Health 2023, 23, 2001. [Google Scholar] [CrossRef]
- Merchant, R.A.; Soong, J.T.Y.; Morley, J.E. Gender Differences in Body Composition in Pre-Frail Older Adults With Diabetes Mellitus. Front. Endocrinol. 2022, 13, 795594. [Google Scholar] [CrossRef] [PubMed]
- Kodepogu, K.R.; Annam, J.R.; Vipparla, A.; Krishna, B.V.N.V.S.; Kumar, N.; Viswanathan, R.; Gaddala, L.K.; Chandanapalli, S.K. A novel deep convolutional neural network for diagnosis of skin disease. Trait. Signal 2022, 39, 1873–1877. [Google Scholar] [CrossRef]
- Das, N.; Kumar, N.; Kaur, M.; Kumar, V.; Singh, D. Automated Deep Transfer Learning-Based Approach for Detection of COVID-19 Infection in Chest X-rays. Ing. Rech. Biomed. 2022, 43, 114–119. [Google Scholar] [CrossRef]
- Chen, X.; He, L.; Shi, K.; Wu, Y.; Lin, S.; Fang, Y. Interpretable Machine Learning for Fall Prediction among Older Adults in China. Am. J. Prev. Med. 2023, 65, 579–586. [Google Scholar] [CrossRef] [PubMed]
- Savadkoohi, M.; Oladunni, T.; Thompson, L. Deep neural networks for human’s fall-risk prediction using force-plate time series signal. Expert Syst. Appl. 2021, 182, 115220. [Google Scholar] [CrossRef] [PubMed]
- Speiser, J.L.; Callahan, K.E.; Houston, D.K.; Fanning, J.; Gill, T.M.; Guralnik, J.M.; Newman, A.B.; Pahor, M.; Rejeski, W.J.; Miller, M.E. Machine Learning in Aging: An Example of Developing Prediction Models for Serious Fall Injury in Older Adults. J. Gerontol. Ser. A 2021, 76, 647–654. [Google Scholar] [CrossRef] [PubMed]
- Odden, M.C.; Melzer, D. Machine Learning in Aging Research. J. Gerontol. Ser. A Biol. Sci. Med Sci. 2019, 74, 1901–1902. [Google Scholar] [CrossRef] [PubMed]
- Das, A.; Dhillon, P. Application of machine learning in measurement of ageing and geriatric diseases: A systematic review. BMC Geriatr. 2023, 23, 841. [Google Scholar] [CrossRef] [PubMed]
- Rajula, H.S.R.; Verlato, G.; Manchia, M.; Antonucci, N.; Fanos, V. Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment. Medicina 2020, 56, 455. [Google Scholar] [CrossRef]
- Thiamwong, L.; Stout, J.R.; Park, J.H.; Yan, X. Technology-Based Fall Risk Assessments for Older Adults in Low-Income Settings: Protocol for a Cross-sectional Study. JMIR Res. Protoc. 2021, 10, e27381. [Google Scholar] [CrossRef]
- Choudhury, R.; Park, J.H.; Thiamwong, L.; Xie, R.; Stout, J.R. Objectively Measured Physical Activity Levels and Associated Factors in Older US Women during the COVID-19 Pandemic: Cross-sectional Study. JMIR Aging 2022, 5, e38172. [Google Scholar] [CrossRef]
- Choudhury, R.; Park, J.H.; Banarjee, C.; Thiamwong, L.; Xie, R.; Stout, J.R. Associations of Mutually Exclusive Categories of Physical Activity and Sedentary Behavior with Body Composition and Fall Risk in Older Women: A Cross-Sectional Study. Int. J. Environ. Res. Public Health 2023, 20, 3595. [Google Scholar] [CrossRef] [PubMed]
- Thiamwong, L.; Stout, J.R.; Sole, M.L.; Ng, B.P.; Yan, X.; Talbert, S. Physio-Feedback and Exercise Program (PEER) Improves Balance, Muscle Strength, and Fall Risk in Older Adults. Res. Gerontol. Nurs. 2020, 13, 289–296. [Google Scholar] [CrossRef] [PubMed]
- Rossler, A.; Thiamwong, L.; Xie, R.; Stout, J.; Park, J.H.; Choudhury, R.; Garcia, O. Fear of Falling, Fall Risk, Depression, and Anxiety in Community-Dwelling Older Adults. Innov. Aging 2021, 5, 1033–1034. [Google Scholar] [CrossRef]
- Kroenke, K.; Spitzer, R.L.; Williams, J.B.W. The PHQ-9. J. Gen. Intern. Med. 2001, 16, 606–613. [Google Scholar] [CrossRef] [PubMed]
- Byrne, G.J.; Pachana, N.A. Development and validation of a short form of the Geriatric Anxiety Inventory—The GAI-SF. In International Psychogeriatrics; Cambridge University Press: Cambridge, UK, 2011; Volume 23, pp. 125–131. [Google Scholar] [CrossRef]
- Brown, K.W.; Ryan, R.M. The benefits of being present: Mindfulness and its role in psychological well-being. J. Personal. Soc. Psychol. 2003, 84, 822–848. [Google Scholar] [CrossRef] [PubMed]
- Torpy, J.M.; Lynm, C.; Glass, R.M. Frailty in Older Adults. JAMA 2006, 296, 2280. [Google Scholar] [CrossRef] [PubMed]
- Kempen, G.I.J.M.; Yardley, L.; Van Haastregt, J.C.M.; Zijlstra, G.A.R.; Beyer, N.; Hauer, K.; Todd, C. The Short FES-I: A shortened version of the falls efficacy scale-international to assess fear of falling. Age Ageing 2008, 37, 45–50. [Google Scholar] [CrossRef] [PubMed]
- Stevens, J.A.; Phelan, E.A. Development of STEADI: A Fall Prevention Resource for Health Care Providers. Health Promot. Pract. 2013, 14, 706–714, Publisher: SAGE Publications. [Google Scholar] [CrossRef]
- Chen, K.; Lou, V.W.Q. Measuring Senior Technology Acceptance: Development of a Brief, 14-Item Scale. Innov. Aging 2020, 4, igaa016. [Google Scholar] [CrossRef]
- Bohannon, R.W. Grip Strength: An Indispensable Biomarker For Older Adults. Clin. Interv. Aging 2019, 14, 1681–1691. [Google Scholar] [CrossRef] [PubMed]
- Yee, X.S.; Ng, Y.S.; Allen, J.C.; Latib, A.; Tay, E.L.; Abu Bakar, H.M.; Ho, C.Y.J.; Koh, W.C.C.; Kwek, H.H.T.; Tay, L. Performance on sit-to-stand tests in relation to measures of functional fitness and sarcopenia diagnosis in community-dwelling older adults. Eur. Rev. Aging Phys. Act. 2021, 18, 1. [Google Scholar] [CrossRef] [PubMed]
- Goble, D.J.; Hearn, M.C.; Baweja, H.S. Combination of BTrackS and Geri-Fit as a targeted approach for assessing and reducing the postural sway of older adults with high fall risk. Clin. Interv. Aging 2017, 12, 351–357. [Google Scholar] [CrossRef] [PubMed]
- Ahorsu, D.K.; Lin, C.Y.; Imani, V.; Saffari, M.; Griffiths, M.D.; Pakpour, A.H. The Fear of COVID-19 Scale: Development and Initial Validation. Int. J. Ment. Health Addict. 2022, 20, 1537–1545. [Google Scholar] [CrossRef] [PubMed]
- Migueles, J.H.; Rowlands, A.V.; Huber, F.; Sabia, S.; van Hees, V.T. GGIR: A Research Community–Driven Open Source R Package for Generating Physical Activity and Sleep Outcomes from Multi-Day Raw Accelerometer Data. J. Meas. Phys. Behav. 2019, 2, 188–196. [Google Scholar] [CrossRef]
- Topolski, T.D.; LoGerfo, J.; Patrick, D.L.; Williams, B.; Walwick, J.; Patrick, M.B. The Rapid Assessment of Physical Activity (RAPA) among older adults. Prev. Chronic Dis. 2006, 3, A118. [Google Scholar] [PubMed]
- Hastie, T.; Tibshirani, R.; Friedman, J. Undirected Graphical Models. In The Elements of Statistical Learning: Data Mining, Inference, and Prediction; Hastie, T., Tibshirani, R., Friedman, J., Eds.; Springer: New York, NY, USA, 2009; pp. 625–648. [Google Scholar] [CrossRef]
- Lee, J.D.; Hastie, T.J. Learning the Structure of Mixed Graphical Models. J. Comput. Graph. Stat. 2015, 24, 230–253. [Google Scholar] [CrossRef] [PubMed]
- Sedgewick, A.J.; Shi, I.; Donovan, R.M.; Benos, P.V. Learning mixed graphical models with separate sparsity parameters and stability-based model selection. BMC Bioinform. 2016, 17, S175. [Google Scholar] [CrossRef] [PubMed]
- R Core Team. R: A Language and Environment for Statistical Computing. 2022. Available online: https://www.R-project.org (accessed on 21 October 2023).
- Revelle, W. psych: Procedures for Psychological, Psychometric, and Personality Research, R Package Version 1.7.8; Northwestern University: Evanston, IL, USA, 2017; Available online: https://CRAN.R-project.org/package=psych (accessed on 20 November 2023).
- Kim, J.O.; Mueller, C.W. Introduction to Factor Analysis; SAGE Publications, Inc.: Thousand Oaks, CA, USA, 1978. [Google Scholar] [CrossRef]
- Joliffe, I.T.; Morgan, B.J. Principal Component Analysis and Exploratory Factor Analysis. Stat. Methods Med. Res. 1992, 1, 69–95. [Google Scholar] [CrossRef]
- Kaiser, H.F. The Application of Electronic Computers to Factor Analysis. Educ. Psychol. Meas. 1960, 20, 141–151. [Google Scholar] [CrossRef]
- Goretzko, D.; Bühner, M. Factor Retention Using Machine Learning with Ordinal Data. Appl. Psychol. Meas. 2022, 46, 406–421. [Google Scholar] [CrossRef] [PubMed]
- Haslbeck, J.M.B.; Waldorp, L.J. mgm: Structure Estimation for Time-Varying Mixed Graphical Models in high-dimensional Data. arXiv 2016, arXiv:1510.06871v2. Available online: http://arxiv.org/abs/1510.06871v2 (accessed on 28 November 2023). [CrossRef]
- Haslbeck, J.M.B.; Waldorp, L.J. mgm: Estimating Time-Varying Mixed Graphical Models in High-Dimensional Data. J. Stat. Softw. 2020, 93, 1–46. [Google Scholar] [CrossRef]
- Efron, B. The Jackknife, the Bootstrap and Other Resampling Plans; SIAM: Philadelphia, PA, USA, 1982; Available online: https://epubs.siam.org/doi/pdf/10.1137/1.9781611970319.fm (accessed on 1 December 2023).
- Akaike, H. Information Theory and an Extension of the Maximum Likelihood Principle; Springer: New York, NY, USA, 1973; Available online: https://api.semanticscholar.org/CorpusID:64903870 (accessed on 1 December 2023).
- Schwarz, G. Estimating the Dimension of a Model. Ann. Stat. 1978, 6, 461–464. Available online: http://www.jstor.org/stable/2958889 (accessed on 1 December 2023). [CrossRef]
- Liu, H.; Roeder, K.; Wasserman, L. Stability Approach to Regularization Selection (StARS) for High Dimensional Graphical Models. Adv. Neural Inf. Process. Syst. 2010, 24, 1432–1440. Available online: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4138724/#R6 (accessed on 15 December 2023). [PubMed]
- Chen, J.; Chen, Z. Extended Bayesian information criteria for model selection with large model spaces. Biometrika 2008, 95, 759–771. [Google Scholar] [CrossRef]
- Epskamp, S.; Cramer, A.O.; Waldorp, L.J.; Schmittmann, V.D.; Borsboom, D. qgraph: Network Visualizations of Relationships in Psychometric Data. J. Stat. Softw. 2012, 48, 1–18. [Google Scholar] [CrossRef]
- Bhushan, N.; Mohnert, F.; Sloot, D.; Jans, L.; Albers, C.; Steg, L. Using a Gaussian Graphical Model to Explore Relationships Between Items and Variables in Environmental Psychology Research. Front. Psychol. 2019, 10, 1050. [Google Scholar] [CrossRef] [PubMed]
- García-Franco, J.D.; Díez, F.J.; Carrasco, M.Á. Probabilistic Graphical Model for the Evaluation of the Emotional and Dramatic Personality Disorders. Front. Psychol. 2022, 13, 996609. [Google Scholar] [CrossRef]
- Pavlovskii, V.V.; Derevitskii, I.V.; Savitskaya, D.A. Probabilistic graphical models for finding optimal multipurpose multicomponent therapy. Procedia Comput. Sci. 2021, 193, 382–392. [Google Scholar] [CrossRef]
- Kalisch, M.; Fellinghauer, B.A.; Grill, E.; Maathuis, M.H.; Mansmann, U.; Bühlmann, P.; Stucki, G. Understanding Human Functioning Using Graphical Models. BMC Med. Res. Methodol. 2010, 10, 14. [Google Scholar] [CrossRef] [PubMed]
- Altenbuchinger, M.; Weihs, C.; Quackenbush, J.; Grabe, H.J.; Zacharias, H.U. Gaussian and Mixed Graphical Models as (Multi-)Omics Data Analysis Tools. Biochim. Biophys. Acta-Gene Regul. Mech. 2020, 1863, 194418. [Google Scholar] [CrossRef] [PubMed]
- Ozcan, A.; Donat, H.; Gelecek, N.; Ozdirenc, M.; Karadibak, D. The Relationship Between Risk Factors for Falling and the Quality of Life in Older Adults. BMC Public Health 2005, 5, 90. [Google Scholar] [CrossRef] [PubMed]
- Chen, Y.; Du, H.; Song, M.; Liu, T.; Ge, P.; Xu, Y.; Pi, H. Relationship Between Fear of Falling and Fall Risk Among Older Patients with Stroke: A Structural Equation Modeling. BMC Geriatr. 2023, 23, 647. [Google Scholar] [CrossRef] [PubMed]
- Lee, S. Falls associated with indoor and outdoor environmental hazards among community-dwelling older adults between men and women. BMC Geriatr. 2021, 21, 547. [Google Scholar] [CrossRef] [PubMed]
- Paliwal, Y.; Slattum, P.W.; Ratliff, S.M. Chronic Health Conditions as a Risk Factor for Falls among the Community-Dwelling US Older Adults: A Zero-Inflated Regression Modeling Approach. BioMed Res. Int. 2017, 2017, 5146378. [Google Scholar] [CrossRef]
- Thiamwong, L.; Xie, R.; Park, J.H.; Lighthall, N.; Loerzel, V.; Stout, J. Optimizing a Technology-Based Body and Mind Intervention to Prevent Falls and Reduce Health Disparities in Low-Income Populations: Protocol for a Clustered Randomized Controlled Trial. JMIR Res. Protoc. 2023, 12, e51899. [Google Scholar] [CrossRef]
Features | Participants, n = 120 |
---|---|
Sociodemographic | |
Age (Years) | |
Mean (SD) | 74.8 (7.38) |
Median (IQR) | 74 (69–79) |
Gender | |
Female | 93 (77.5%) |
Male | 27 (22.5%) |
Race/Ethnicity | |
Non-Hispanic White | 87 (72.5%) |
Hispanic | 21 (17.5%) |
Others | 12 (10%) |
Education | |
High school or below | 34 (28.3%) |
College or higher | 86 (71.7%) |
Financial difficulty | |
Adequate or less | 54 (45%) |
More than adequate | 66 (55%) |
Living status | |
Alone | 50 (41.7%) |
With others | 70 (58.3%) |
General health | |
Excellent or very good | 64 (53.3%) |
Good or below | 56 (46.7%) |
Psychological status | |
Depression PHQ-9 1, median (IQR) | 10 (9–12) |
Anxiety GAI-SF 2, median (IQR) | 10 (8.8–10) |
Mindfulness MAAS 3, median (IQR) | 81 (69.8–86) |
COVID-19-related | |
Fear of COVID-19, median (IQR) | 14 (10–17) |
Self-assessment Fall risks | |
History of falls | |
None | 85 (70.8%) |
One | 19 (15.8%) |
Two or more | 16 (13.4%) |
Number of injurious falls | |
None | 109 (90.8%) |
One | 9 (7.5%) |
Two or more | 2 (1.6%) |
FRAIL 4 | |
Healthy | 66 (55%) |
Pre-frail or Frail | 54 (45%) |
Short FES-I 5, median (IQR) | 9 (7–12) |
STEADI 6, median (IQR) | 22.5 (21–24) |
STA 7, median (IQR) | 101 (90.8–112.3) |
Performance-based Fall risks | |
RAPA 8 Aerobics, median (IQR) | 3 (2–3.3) |
RAPA Strength and flexibility, median (IQR) | 2.5 (0–3) |
30 s sit-to-stand, median (IQR) | 14.5 (12–17) |
BTrackS 9 balance test, median (IQR) | 27 (20–36) |
Grip strength, left (kgs) | 19.1 (15.8–24.9) |
Grip strength, right (kgs) | 20.6 (16.7–26.3) |
Accelerometer data | |
SB 10 (mins/day) | 12.3 (11–13.6) |
LPA 11 (mins/day) | 3.4 (2.8–4.1) |
MVPA 12 (mins/day) | 0.7 (0.4–1) |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Nguyen, T.; Thiamwong, L.; Lou, Q.; Xie, R. Unveiling Fall Triggers in Older Adults: A Machine Learning Graphical Model Analysis. Mathematics 2024, 12, 1271. https://doi.org/10.3390/math12091271
Nguyen T, Thiamwong L, Lou Q, Xie R. Unveiling Fall Triggers in Older Adults: A Machine Learning Graphical Model Analysis. Mathematics. 2024; 12(9):1271. https://doi.org/10.3390/math12091271
Chicago/Turabian StyleNguyen, Tho, Ladda Thiamwong, Qian Lou, and Rui Xie. 2024. "Unveiling Fall Triggers in Older Adults: A Machine Learning Graphical Model Analysis" Mathematics 12, no. 9: 1271. https://doi.org/10.3390/math12091271
APA StyleNguyen, T., Thiamwong, L., Lou, Q., & Xie, R. (2024). Unveiling Fall Triggers in Older Adults: A Machine Learning Graphical Model Analysis. Mathematics, 12(9), 1271. https://doi.org/10.3390/math12091271