International Journal of Clinical Case Reports 2025, Vol.15 http://medscipublisher.com/index.php/ijccr © 2025 MedSci Publisher, registered at the publishing platform that is operated by Sophia Publishing Group, founded in British Columbia of Canada. All Rights Reserved.
International Journal of Clinical Case Reports 2025, Vol.15 http://medscipublisher.com/index.php/ijccr © 2025 MedSci Publisher, registered at the publishing platform that is operated by Sophia Publishing Group, founded in British Columbia of Canada. All Rights Reserved. MedSci Publisher is an international Open Access publisher specializing in clinical case, clinical medicine, new variations in disease processesregistered at the publishing platform that is operated by Sophia Publishing Group (SPG), founded in British Columbia of Canada. Publisher MedSci Publisher Edited by Editorial Team of International Journal of Clinical Case Reports Email: edit@ijccr.medscipublisher.com Website: http://medscipublisher.com/index.php/ijccr Address: 11388 Stevenston Hwy, PO Box 96016, Richmond, V7A 5J5, British Columbia Canada International Journal of Clinical Case Reports (ISSN 1927-579X) is an open access, peer reviewed journal published online by MedSci Publisher. The journal is considering all the latest and outstanding research articles, letters and reviews in all aspects of clinical case, containing clinical medicine which advance general medical knowledge; the event in the course of observing or treating a patient; new variations in disease processes; as well as the expands the field of clinical relating to case reports. All the articles published in International Journal of Clinical Case Reports are Open Access, and are distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. MedSci Publisher uses CrossCheck service to identify academic plagiarism through the world’s leading plagiarism prevention tool, iParadigms, and to protect the original authors’ copyrights.
International Journal of Clinical Case Reports (online), 2025, Vol. 15, No.5 ISSN 1927-579X http://medscipublisher.com/index.php/ijccr © 2025 MedSci Publisher, registered at the publishing platform that is operated by Sophia Publishing Group, founded in British Columbia of Canada. All Rights Reserved. Latest Content Applicability Analysis ofFall Risk Assessment Tools in Community-Dwelling Older Adults YongCheng International Journal of Clinical Case Reports, 2025, Vol. 15, No. 5, 200-208 Comparative Study on Construction Methods of Chronic Disease Prediction Models Based on Big Data Jingqiang Wang International Journal of Clinical Case Reports, 2025, Vol. 15, No. 5, 209-218 Tracking Health Behavior Changes and Quality of Life Among Elderly Patients in Home Quarantine Liqin Guo, Jiayi Wu International Journal of Clinical Case Reports, 2025, Vol. 15, No. 5, 219-227 Exploring How COVID-19 Vaccines Work and Their Reactions in Older People JianWang International Journal of Clinical Case Reports, 2025, Vol. 15, No. 5, 228-238 The Role of the SIRT3–FOXO3a Axis in Mitochondrial Homeostasis and Oxidative Stress: Insights into Septic Cardiomyopathy Xiaohong Yang, Liting Wang International Journal of Clinical Case Reports, 2025, Vol. 15, No. 5, 239-247
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 200 Systematic Review Open Access Applicability Analysis of Fall Risk Assessment Tools in Community-Dwelling Older Adults YongCheng Physicov. Med. Tech. Ltd., Zhejiang, Zhuji, 311800, Zhejiang, China Corresponding email: 2741098603@qq.com International Journal of Clinical Case Reports 2025, Vol.15, No.5 doi: 10.5376/ijccr.2025.15.0021 Received: 26 Jun., 2025 Accepted: 05 Aug., 2025 Published: 29 Aug., 2025 Copyright © 2025 Cheng, This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Preferred citation for this article: Cheng Y., 2025, Applicability analysis of fall risk assessment tools in community-dwelling older adults, International Journal of Clinical Case Reports, 15(5): 200-208 (doi: 10.5376/ijccr.2025.15.0021) Abstract This study explores several commonly used fall risk assessment tools in the community, such as the Morse Fall Scale, Tinetti Balance Assessment, Hendrich II, Stand up and Walk Test, and Berg Balance Scale, etc. The performance of these tools in terms of reliability, validity, sensitivity, specificity and operational convenience was compared, and their respective advantages and disadvantages were summarized. Although these methods offer a more convenient and labor-saving approach for fall risk screening, there is currently no tool that can maintain stable and high judgment accuracy across different populations, and psychological and environmental factors are often overlooked. Foreign research pays more attention to the application of wearable devices and artificial intelligence technology, while domestic research focuses more on developing assessment tools suitable for local culture and making use of national data. However, it is still constrained by the limited sample size and insufficient verification at present. Existing research suggests that combining simple and feasible tools with clinical experience remains a relatively feasible strategy in community care. Future research should focus on developing more comprehensive and user-friendly assessment methods, integrating new technologies to more effectively identify multiple risk factors, thereby enhancing the accuracy and applicability of fall risk assessment. Keywords Fall risk assessment; Community-dwelling older adults; Applicability; Reliability and validity; Nursing practice 1 Introduction For the elderly living in the community, falls are a very important health issue. Among people over 65 years old, a certain proportion experience falls every year. Such incidents often lead to serious physical injuries, psychological burdens, reduced self-care abilities and increased medical expenses. Many elderly people may fall multiple times and have conditions such as fractures or require hospitalization (Mourad-Chehade et al., 2023). The impact of falls is not limited to individuals; it also increases the pressure on caregivers and imposes a greater burden on the global healthcare system (Chen et al., 2022). Common risk factors for falls among the elderly include weak balance ability, insufficient muscle strength, difficulty walking, urinary incontinence, and unsafe living environment (Chen et al., 2020; Argyrou et al., 2023). Accurate assessment of the risk of falls helps to identify high-risk groups early and take timely countermeasures, thereby reducing the occurrence of falls and the harm they cause. Fall risk assessment methods, including questionnaires, self-assessment forms, physical fitness tests, and sensor technology, have been recommended by health institutions and professional organizations for use in community and primary care (Bravo et al., 2021; Wang et al., 2022). These methods can assist medical staff, especially nurses, in formulating more targeted prevention plans for individuals, allocating resources more rationally, and improving health outcomes. The use of reliable and effective assessment tools in daily work plays an important role in reducing the occurrence of falls among the elderly and mitigating their consequences (Ong et al., 2022; Jasper et al., 2025). This study will explore the applicability, advantages and disadvantages of different fall risk assessment tools used among the elderly population in the community. By comparing the research results of these tools in terms of prediction accuracy, operability and clinical application, this study aims to provide references for best practices in fall prevention and care, help healthcare workers select appropriate tools, point out the directions that need further research, and ultimately contribute to reducing the morbidity and mortality rates among the elderly caused by falls.
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 201 2 Risk Factors for Falls Among the Elderly 2.1 Physiological factors: balance issues, chronic diseases, and drug use Balance problems are the main physiological risk factors for falls among the elderly in the community. Balance and activity limitations significantly increase the risk of single and repeated falls. A summary of studies shows that balance problems can triple the risk of falls (Jehu et al., 2021; Li et al., 2022). Abnormal gait, muscle weakness and sensory function decline will further increase this risk. Therefore, tests of balance and body function are very important in fall risk assessment (Saunders et al., 2025). Chronic diseases such as diabetes, heart disease, hypertension, stroke and Parkinson's disease are also significantly associated with an increased risk of falls. Frailty is a state of reduced physical reserves and is closely related to a higher incidence of falls. Compared with elderly people of the same age but not frail, frail elderly people have a 48% higher risk of falls (Xu et al., 2022; Yang et al., 2023). In addition, taking multiple medications or certain specific drugs - especially psychotropic drugs, antihypertensive drugs, and drugs that act on the central nervous system - is also often regarded as an important cause of falls, as these drugs may lead to problems such as dizziness, orthostatic hypotension, and decreased attention (Yang et al., 2016). 2.2 Psychological factors: cognitive decline, depression, fear of falling Cognitive decline, especially slower executive ability and processing speed, is an important psychological risk factor for falls. Elderly people with dementia or mild cognitive impairment have a significantly higher risk. Dementia almost doubles the risk of falling (Li et al., 2022). Inattention and weakened judgment can easily lead to unsafe behaviors and reduced risk awareness, thereby further increasing the possibility of falls (Saunders et al., 2025). Depression and the fear of falling are also common psychological factors. Depression can increase the risk of falls by up to 23%, which may be related to reduced activity, poor attention and side effects of medication. Fear of falling is quite common among the elderly. It can cause limited activity, muscle incoordination, thereby increasing the risk of falling and causing further psychological distress (Xu et al., 2022). Therefore, addressing these psychological issues is crucial for comprehensive fall prevention. 2.3 Environmental factors: insufficient family safety and inadequate community facilities Environmental issues are also crucial in the risk of falls among the elderly. Unsafe home environments-such as insufficient light, slippery floors, loose carpets and lack of handrails-are common causes of falls (Mehta et al., 2021; Xu et al., 2022). Since many elderly people spend most of their time at home, it is important to identify and improve these problems as protective measures. Incomplete community supporting facilities, such as uneven roads, dim lighting, and difficulties in entering and exiting public places, all increase the risk of falls among the elderly in the community (Qian et al., 2020). Certain social factors, such as living in areas with poorer economic conditions, or lacking social activities or support, are also associated with a higher incidence of falls. Although the importance of environmental factors has been recognized, studies show that compared with physiological and psychological factors, research on the environment is still relatively scarce. This indicates that a more careful assessment of the environment should be conducted in fall prevention programs (Saunders et al., 2024; Saunders et al., 2025). 3 Overview of Common Fall Risk Assessment Tools 3.1 Common tools A variety of fall risk assessment methods are often used to identify elderly people at risk of falls, especially in community and primary care. The Moors Fall Scale (MFS), Tinetti Balance Assessment (also known as Performance-Oriented Activity Assessment, POMA), and Hendrich II Fall Risk Model are the most common. These tools are popular for their simplicity, ease of use and low equipment requirements, and can be used in places such as clinics and community centers. In addition, there are some common methods, such as Timed Up and Go (TUG) test, Berg Balance Scale (BBS), gait speed and functional range test, which reflect the activities and balance of the elderly from different perspectives (Meekes et al., 2021).
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 202 Although these tools are widely used, their predictive effects vary greatly. Most studies have found that the area under the curve (AUC) of these tools ranges from 0.5 to 0.7, indicating that they can only reach a medium level. The sensitivity and specificity vary greatly among different studies and populations, indicating that no single tool can completely and accurately identify all high-risk groups. Therefore, clinical guidelines generally recommend the combined use of multiple tools and clinical judgment to enhance the reliability of fall risk identification among the elderly in the community (Strini et al., 2021; Jepsen et al., 2022). 3.2 Main contents and evaluation aspects of each tool The Morse Fall Scale (MFS) consists of six items: fall history, combined diagnosis, use of assistive devices, intravenous therapy, gait, and mental state. Each project has a score, and the total score represents the degree of risk. The higher the score, the greater the risk (Cai et al., 2025; Li et al., 2025). The Tinetti Balance Assessment (POMA) scores balance and gait respectively by observing actions such as sitting, standing, turning and walking, thereby comprehensively understanding the activity ability and stability of the elderly (Meekes et al., 2021). The Hendrich II fall risk model examines mental state, depression, excretory changes, dizziness, gender, the use of specific drugs (such as antiepileptic drugs or benzodiazepines), and performance in the "stand-up walk" test (Cho et al., 2020). Other methods such as BBS evaluate static and dynamic balance through multiple action tasks; The TUG test reflects the overall activity level by measuring the time required to stand up, walk, turn around and sit down. The fall history tool only needs to ask about past fall situations and is a fast and effective screening method. Each tool focuses on different risk aspects. Some emphasize physical and functional factors, while others combine cognitive, medication and environmental factors (Meekes et al., 2021; Strini et al., 2021; Jepsen et al., 2022). 3.3 Advantages and disadvantages of tools These methods each have their own advantages. For instance, MFS, TUG and BBS can complete evaluations quickly without the need for special equipment, making them suitable for application in communities and primary care. Tinetti and the Balance Scale can simultaneously examine balance and gait, which is helpful for identifying multi-dimensional risks. The fall history tool is very simple and does not require professional training, making it suitable for large-scale screening (Meekes et al., 2021; Strini et al., 2021). But no method can maintain a very high prediction accuracy in all cases. Their sensitivity and specificity vary significantly, and most tools mainly focus on the physical aspect, easily neglecting environmental and psychological factors. In addition, products like MFS and Hendrich II were originally developed in hospital Settings. Their direct use in the community might not be entirely appropriate and some adjustments are needed (Xu and Li, 2025). Therefore, it is recommended that multiple tools be combined with clinical judgment to improve the accuracy and practical effect of the assessment of elderly people in the community (Jepsen et al., 2022). 4 Evaluate the Applicability of the Tools Among the Community Population 4.1 Reliability and validity: evidence from community-aged individuals Many studies have shown that fall risk assessment methods can achieve good reliability and validity among elderly people in the community. For instance, some tools, such as the revised "Stay Independent" manual, the Fall Risk Self-Assessment Form (FRSAS), and the EASY-Care standard, have demonstrated good internal consistency, test-retest reliability, and discriminative validity in community Settings, with Cronbach coefficients generally above 0.75. The intra-class correlation coefficient exceeded 0.9 (Shahrestanaki et al., 2022). These methods are usually short and easy to understand, and can be accomplished by individuals or with minimal assistance, making them suitable for application in large-scale community screening (Wang et al., 2022). Some traditional assessment methods have limited effectiveness when used in the community, mainly because they were originally designed for hospitals or clinical Settings. For instance, the predictive effects of these methods on the elderly in the community usually only reach a medium level (with AUC values mostly ranging from 0.6 to 0.7). The results may vary depending on the population and the environment. Therefore, it is necessary
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 203 to continuously optimize and validate these tools in different community groups to ensure their accurate judgment and applicability (Meekes et al., 2021; Ong et al., 2022). 4.2 Sensitivity and specificity: the effect of identifying high-risk groups The commonly used fall risk assessment tools in the community show significant differences in sensitivity and specificity. Take BBS and TUG as examples. Their sensitivity in distinguishing whether there is a history of falls is approximately 61% to 67.5%, and their specificity is between 53% and 56.3%. Some more complex tools or those that rely on sensors can achieve higher sensitivity (such as up to 93.8%), but sometimes their specificity will decline accordingly (Table 1) (Wang et al., 2022; Alharbi, 2023). For example, the sensitivity and specificity of the EASY-Care criterion in predicting falls within 6 months were 76.6% and 87.5%, respectively (Shahrestanaki et al., 2022). These results indicate that certain tools are effective in identifying high-risk individuals, but currently no method can maintain both high sensitivity and high specificity in all community Settings simultaneously. Table 1 Comparative analysis of fall assessment score between participants with and without a history of fall (Adopted from Alharbi, 2023) - With a history of fall Without a history of fall P-value¹ Berg Balance Scale score <0.0001 Mean/standard deviation 34.44/16.04 42.78/11.58 - Five Times Sit-to-Stand test score 0.56 Mean/standard deviation 36.77/1103 29.38/10.32 - Timed Up and Go test score 0.07 Mean/standard deviation 24.46/8.82 18.66/6.97 - Table caption: 1 Post-test accuracy (%) was calculated using the selected cut-off score Furthermore, the predictive power relying solely on questionnaires is generally lower than that of methods based on sports tests or sensor data. If self-reported risk factors are combined with physical examination or sensor information, high-risk groups can be identified more accurately. However, due to the relatively complex operation and high resource requirements, such methods may be difficult to be widely implemented in some communities (Kulkarni, 2022; Mourad-Chehade et al., 2023). 4.3 Feasibility and potential for community use When promoting in the community, operability is an important consideration. Most of the assessment tools for the elderly in the community are relatively simple, requiring only a small amount of equipment. Even non-professionals and the elderly themselves can complete them. Therefore, these tools are very practical in both large-scale screening and daily use (Vilpunaho et al., 2023). "Remain Independent", FRSAS and some mobile application-based tools (such as FallSA) have good acceptance among the elderly, are easy to operate and have a high completion rate (Ong et al., 2022). However, some action-based tools (such as BBS and TUG) require more time, space or professional support, which may be limited in some communities (Meekes et al., 2021). Sensors and application tools have advantages in terms of accuracy and scalability, but their popularization is limited by technical conditions and usage habits. Overall, the most suitable tool should strike a balance among simplicity, operability and predictive effect, and be selected based on the actual resources and needs of the community (Singh et al., 2021; Wang et al., 2022). 5 Comparison of Research Progress at Home and Abroad 5.1 Main characteristics of tool application in international research International research on the risk assessment of falls among the elderly generally employs validated standardized tools, such as the Morse Fall Scale, Tinetti Balance Assessment, and the Hendrich II Fall Risk Model, etc. These tools are commonly found in large-scale, multi-center studies, and their reliability, validity, sensitivity and specificity have been tested in different populations and scenarios (Figure 1) (Liang et al., 2025). The current research trend focuses on introducing new technologies, such as wearable sensors and machine learning, to
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 204 enhance the accuracy and objectivity of predictions. Some models have good prediction effects (AUC values can reach 0.84), and can simultaneously incorporate multiple risk factors such as physiology, psychology, and environment (Yu et al., 2025). In addition, international research also focuses on developing methods that comprehensively consider multiple factors, integrating questionnaires, self-reports, physical fitness tests and sensor data. This approach helps to more accurately identify high-risk populations, promote targeted interventions, and emphasize cross-cultural applicability and external validation, thereby enhancing the universal applicability of research results (Chen et al., 2022; Chen et al., 2023). 5.2 Limitations and challenges of domestic research In China, research on fall risk assessment has also made certain progress, especially in developing tools that are more suitable for the local population, such as the Self-Assessment Form for Fall Risk (FRSAS) and predictive models based on national data (such as CHARLS). These tools have demonstrated excellent reliability and practicality in community applications. In recent years, there have also been studies attempting to enhance the predictive ability by leveraging machine learning (Chen et al., 2023; Liang et al., 2025). However, many studies still have problems such as limited sample size, concentration in a single region, and lack of external validation, which affect the generalization and practical application value of the results (Wang et al., 2022). On the other hand, the deficiency is that compared with foreign countries, the application of advanced technologies and multi-factor comprehensive analysis in China is still not extensive enough. Although there have been attempts in sensors and machine learning, the overall application level still needs to be improved. In the future, more complete models need to be constructed to incorporate risk factors such as the environment and social psychology. Furthermore, the lack of unified intervention standards in various regions has also restricted the promotion of research results in practice (Xia et al., 2022). 5.3 Similarities and differences between chinese and western research achievements and their implications Both Western and Chinese research hold that the risk of falls is the result of multiple factors working together and emphasize the importance of comprehensive assessment tools. Both attach importance to key risk points such as physical function, cognitive level, depression and environmental factors, and both have proved that combining self-reporting with objective measurement can improve the accuracy of prediction (Chen et al., 2023; Yu et al., 2025). There are still differences between domestic and foreign countries in terms of technology application, research scope and standardization. International research began to use wearable sensors, artificial intelligence technology and conduct large-scale validation earlier, while China has made progress in developing tools suitable for local needs and building models using national databases (Liang et al., 2025). These differences indicate that it is necessary to enhance cross-cultural collaboration, promote the validation of local tools among a broader population, and introduce advanced technologies more widely within the country, thereby improving the accuracy and applicability of fall risk assessment for elderly people in the community. 6 Existing Problems and Challenges 6.1 Insufficient adaptability of tools: cultural and demographic differences Many fall risk assessment methods were originally designed and validated among Western populations, and thus have limited adaptability when applied to different cultures or groups. These tools often have difficulty reflecting the risks brought about by differences in lifestyle, environmental conditions and health concepts among different populations, especially among the elderly in communities in non-Western countries (Strini et al., 2021; Ong et al., 2022). Therefore, when these tools are used outside the original environment, their predictive accuracy and relevance may decline, and they are also prone to overlook important risk factors in specific communities. Most of the existing assessment tools focus more on physical functions and structural aspects, while giving relatively insufficient consideration to factors such as the environment, personal habits and cultural background.
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 205 For instance, a systematic review revealed that only approximately 7% of the evaluations involved environmental and personal factors, while the vast majority of the rest still focused on physical functions. This situation suggests that it is necessary to develop tools that better reflect cultural differences and individual circumstances, so as to more accurately assess the fall risk of different groups of people. Figure 1 Nomogram used to quantitatively predict the risk of falls in the older individuals (Adopted from Liang et al., 2025) 6.2 Application limitations: insufficient personnel training and lack of resources When promoting fall risk assessment tools in the community, there are often constraints such as insufficient staff training and limited resources. Many tools require certain professional knowledge or operational skills to be used correctly and understand the results, but community health workers often fail to receive adequate training or continuous support (Chalke et al., 2025). These deficiencies can easily lead to inconsistent assessment operations, a decline in the reliability of results, and may affect the timing of early risk identification and intervention. Meanwhile, the limited medical resources in the community, such as insufficient time, manpower and equipment, also restrict the wide application of comprehensive assessment methods. Even tools designed for primary care can be difficult to implement if they require more time, space or materials than in general community environments (Strini et al., 2021). These issues indicate that developing more convenient and user-friendly tools and enhancing personnel training are important directions for improving fall prevention. 6.3 Lack of system integration The current fall risk assessment methods often lack an overall and multi-angle framework. They mainly focus on the physical or functional aspects, while often neglecting the influences in the psychological, social and environmental aspects. Review studies have shown that most tools fail to comprehensively incorporate various risk factors, resulting in insufficiently comprehensive assessment and possibly limiting the actual effect of preventive measures (Strini et al., 2021). The singularity of this assessment perspective weakens the ability to accurately identify high-risk groups, whose falls are usually caused by a combination of multiple factors. At present, there is still a lack of an integrated system that can combine qualitative information (such as patient opinions) with quantitative data, which also reduces the role of existing tools. More and more studies suggest the development of multi-factor assessment methods and more advanced models, such as combining sensor data,
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 206 artificial intelligence and user-centered design, in order to assess the fall risk of the elderly more comprehensively and accurately (Yu et al., 2025). Without such a system, fall prevention might remain fragmented and its practical effectiveness in the community would also be limited. 7 Concluding Remarks The commonly used fall risk assessment methods at present, such as Timed Up and Go (TUG) test, Berg balance scale and fall history, are practical and easy to operate in the community. However, their predictive effects are average, and the area under the curve (AUC) is mostly lower than 0.7. No single method can maintain a high level of accuracy in all populations, so clinical judgment remains very important when identifying high-risk groups among the elderly in the community. To better prevent falls in community care, it is recommended to use short and effective tools, such as the fall history or the "Stay Independent" manual, and combine them with the clinical judgment of professionals. These methods have relatively low demands for resources and training and are suitable for large-scale application. However, medical staff should still be aware of the shortcomings of each tool and, on the basis of assessment, cooperate with targeted intervention and continuous follow-up. Future research should focus on developing and validating multi-factor, easy-to-use assessment tools that can integrate sensor technology, artificial intelligence and multiple risk factors. The effectiveness of such new methods still needs to be verified through large-scale prospective studies to ensure their applicability, accuracy and feasibility, so that they can be widely used among different community populations. Acknowledgments The author extends sincere thanks to Dr An for her feedback on the manuscript. Conflict of Interest Disclosure The author affirms that this research was conducted without any commercial or financial relationships that could be construed as a potential conflict of interest. References Alharbi A., 2023, Comparison of three fall risk assessment tools in community-dwelling saudi elderlies, Majmaah Journal of Health Sciences, 11(4): 1445. https://doi.org/10.5455/mjhs.2023.04.004 Argyrou C., Dionyssiotis Y., Galanos A., Vlamis J., K.Triantafyllopoulos I., Dontas I., and Chronopoulos E., 2023, Fall risk question-based tools for fall screening in community-dwelling older adults: a systematic review of the literature, Journal of Frailty Sarcopenia and Falls, 8: 240-253. https://doi.org/10.22540/JFSF-08-240 Bravo J., Rosado H., Tomás-Carús P., Carrasco C., Batalha N., Folgado H., and Pereira C., 2021, Development and validation of a continuous fall risk score in community-dwelling older people: an ecological approach, BMC Public Health, 21(Suppl 2): 808. https://doi.org/10.1186/s12889-021-10813-w Cai W.P., Huang Z.M., Han Q.X., and Huang Y.L., 2025, Research on the chronic disease management model for the elderly based on a community health assessment system, International Journal of Clinical Case Reports, 15(1): 44-51. https://doi.org/10.5376/ijccr.2025.15.0005 Chalke A., Leito G., Sidhu A., McClelland J., Agyemang S., Luzingu J., Agarwal N., Steckler L., Wu A., and Chen Z., 2025, Practice and impact of using fall screening tools in emergency medicine for older adults: a scoping review, Journal of Applied Gerontology, 12: 07334648251315279. https://doi.org/10.1177/07334648251315279 Chen M., Wang H., Yu L., Yeung E., Luo J., Tsui K., and Zhao Y., 2022, A systematic review of wearable sensor-based technologies for fall risk assessment in older adults, Sensors, 22(18): 6752. https://doi.org/10.3390/s22186752 Chen P., Lin H., Ong J.R., and Ma H., 2020, Development of a fall-risk assessment profile for community-dwelling older adults by using the National Health Interview Survey in Taiwan, BMC Public Health, 20(1): 234. https://doi.org/10.1186/s12889-020-8286-8 Chen X., He L., Shi K., Wu Y., Lin S., and Fang Y., 2023a, Interpretable machine learning for fall prediction among older adults in China, American Journal of Preventive Medicine, 65(4): 579-586. https://doi.org/10.1016/j.amepre.2023.04.006 Chen X., Lin S., Zheng Y., He L., and Fang Y., 2023b, 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. https://doi.org/10.1016/j.archger.2023.105012
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 207 Cho E., Woo Y., Han A., Chung Y., Kim Y., and Park H., 2020, Comparison of the predictive validity of three fall risk assessment tools and analysis of fall risk factors at a tertiary teaching hospital, Journal of Clinical Nursing, 29(17-18): 3482-3493. https://doi.org/10.1111/jocn.15387 Jasper A., Karim R., Vitente A., Rafael C., Tayag E., Uy S., Baloy R., and Lazaro R., 2025, Concurrent validity and reliability of in-person and supervised remote STEADI fall risk assessment in community-dwelling older adults, Journal of Geriatric Physical Therapy, (2025): 10-1519. https://doi.org/10.1519/JPT.0000000000000446 Jehu D., Jehu D., Davis J., Davis J., Falck R., Falck R., Bennett K., Bennett K., Tai D., Tai D., Souza M., Cavalcante B., Zhao M., Zhao M., Liu-Ambrose T., and Liu-Ambrose T., 2021, Risk factors for recurrent falls in older adults: a systematic review with meta-analysis, Maturitas, 144: 23-28. https://doi.org/10.1016/j.maturitas.2020.10.021 Jepsen B., Robinson K., Ogliari G., Montero-Odasso M., Kamkar N., Ryg J., Freiberger E., and Tahir M., 2022, Predicting falls in older adults: an umbrella review of instruments assessing gait balance and functional mobility, BMC Geriatrics, 22(1): 615. https://doi.org/10.1186/s12877-022-03271-5 Kulkarni S., 2022, A comparative study of fall risk assessment in community dwelling older adults in India, Innovation in Aging, 6: 865. https://doi.org/10.1093/geroni/igac059.3093 Li M., Huang Q., Li C., Xie L., Wang Y., and Yang J., 2025, Evaluation of different fall risk screening tools for risk prediction of ophthalmology inpatients, BMC Ophthalmology, 25(1): 1-3. https://doi.org/10.1186/s12886-025-04071-2 Li Y., Hou L., Zhao H., Xie R., Yi Y., and Ding X., 2022, Risk factors for falls among community-dwelling older adults: a systematic review and meta-analysis, Frontiers in Medicine, 9: 1019094. https://doi.org/10.3389/fmed.2022.1019094 Liang X., Chai J., Li G., Li W., Zhang B., Zhou Z., and Li G., 2025, A fall risk prediction model based on the CHARLS database for older individuals in China, BMC Geriatrics, 25(1): 170. https://doi.org/10.1186/s12877-025-05814-y Lockhart T., Soangra R., Yoon H., Wu T., Frames C., Weaver R., and Roberto K., 2021, Prediction of fall risk among community-dwelling older adults using a wearable system, Scientific Reports, 11(1): 20976. https://doi.org/10.1038/s41598-021-00458-5 Meekes W., Korevaar J., Leemrijse C., and Van De Goor I., 2021, Practical and validated tool to assess falls risk in the primary care setting: a systematic review, BMJ Open, 11(9): e045431. https://doi.org/10.1136/bmjopen-2020-045431 Mehta J., Czanner G., Harding S., Newsham D., and Robinson J., 2021, Visual risk factors for falls in older adults: a case-control study, BMC Geriatrics, 22(1): 134. https://doi.org/10.1186/s12877-022-02784-3 Mourad-Chehade F., Glynn N., Chkeir A., Waterval N., Claassen C., Helm F., and Kruk E., 2023, Predictability of fall risk assessments in community-dwelling older adults: a scoping review, Sensors, 23(18): 7686. https://doi.org/10.3390/s23187686 Ong M., Soh K., Saimon R., Myint W., Pawi S., and Saidi H., 2022, Falls risk screening tools intended to reduce fall risk among independent community-dwelling older adults: a systematic review, International Journal of Nursing Practice, 29(4): e13083. https://doi.org/10.1111/ijn.13083 Qian X., Chau P., Kwan C., Lou V., Leung A., Ho M., Fong D., and Chi I., 2020, Investigating risk factors for falls among community-dwelling older adults according to WHO’s risk factor model for falls, The Journal of Nutrition Health and Aging, 25: 425-432. https://doi.org/10.1007/s12603-020-1539-5 Saunders S., D’Amore C., Hao Q., Kuspinar A., Richardson J., and Beauchamp M., 2024, Fall risk factors in community-dwelling older adults: an umbrella review of systematic reviews, Innovation in Aging, 8: 1046-1046 https://doi.org/10.1093/geroni/igae098.3365 Saunders S., D'Amore C., Hao Q., El-Moneim A., Kuspinar A., Richardson J., and Beauchamp M., 2025, Risk factors for falls in community-dwelling older adults: an umbrella review, medRxiv, (2025): 2025-04. https://doi.org/10.1101/2025.04.04.25325029 Shahrestanaki S., Sharifi F., Shahsavari H., Ghonoodi F., Philp I., Bahramnezhad F., and Navab E., 2022, Predicting the risk of fall in community-dwelling older adults in Iran, Journal of Aging and Environment, 37: 1-18. https://doi.org/10.1080/26892618.2021.1918813 Singh D., Goh J., Shaharudin M., and Shahar S., 2021, A mobile app (FallSA) to identify fall risk among malaysian community-dwelling older persons: development and validation study, JMIR mHealth and uHealth, 9(10): e23663. https://doi.org/10.2196/23663 Strini V., Schiavolin R., and Prendin A., 2021, Fall risk assessment scales: a systematic literature review, Nursing Reports, 11: 430-443. https://doi.org/10.3390/nursrep11020041 Vilpunaho T., Karinkanta S., Sievänen H., Kopra J., Kröger H., and Rikkonen T., 2023, Predictive ability of a self-rated fall risk assessment tool in community-dwelling older women, Aging Clinical and Experimental Research, 35: 1205-1212.
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 200-208 http://medscipublisher.com/index.php/ijccr 208 Wang X., Yu L., Wang H., Tsui K., and Zhao Y., 2024, Sensor-based multifaceted feature extraction and ensemble elastic net approach for assessing fall risk in community-dwelling older adults, IEEE Journal of Biomedical and Health Informatics, 28: 6661-6673. https://doi.org/10.1109/JBHI.2024.3447705 Wang Z., Rong Y., Gu L., Yang Y., Du X., and Zhou M., 2022, Reliability and validity of the fall risk self-assessment scale for community-dwelling older people in China: a pilot study, BMC Geriatrics, 22(1): 272. https://doi.org/10.1186/s12877-022-02962-3 Xia L., Zheng Y., Lin Z., Chen P., Mei K., Zhao J., Liu Y., Song B., Gao H., Sun C., Yang H., Wang Y., Song K., Yang Y., Luan X., Wen X., Yin X., Fu A., Cai Y., Xie L., Li Y., Lu J., Wu X., Wang R., and Gu Z., 2022, Gap between risk factors and prevention strategies? a nationwide survey of fall prevention among medical and surgical patients, Journal of Advanced Nursing, 78: 2472-2481. https://doi.org/10.1111/jan.15177 Xu Q., Ou X., and Li J., 2022, The risk of falls among the aging population: a systematic review and meta-analysis, Frontiers in Public Health, 10: 902599. https://doi.org/10.3389/fpubh.2022.902599 Xu H., and Li M., 2025, Clinical and immunological factors affecting vaccine efficacy in frail older adults, International Journal of Molecular Medical Science, 15(4): 165-174. https://doi.org/10.5376/ijmms.2025.15.0017 Yang Y., Hu X., Zhang Q., and Zou R., 2016., Diabetes mellitus and risk of falls in older adults: a systematic review and meta-analysis, Age and Ageing, 45(6): 761-767. https://doi.org/10.1093/AGEING/AFW140 Yang Z., Lin H., Jiang G., Chu Y., Gao J., Tong Z., and Wang Z., 2023, Frailty is a risk factor for falls in the older adults: a systematic review and meta-analysis, The Journal of Nutrition Health and Aging, 27: 487-495. https://doi.org/10.1007/s12603-023-1935-8 Yu X., Cai Y., Yang R., Ma F., and Kim W., 2025, Revisiting sensor-based intelligent fall risk assessment for older people: a systematic review, Eng. Appl. Artif. Intell., 144: 110176. https://doi.org/10.1016/j.engappai.2025.110176
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 209-218 http://medscipublisher.com/index.php/ijccr 209 Research Insight Open Access Comparative Study on Construction Methods of Chronic Disease Prediction Models Based on Big Data Jingqiang Wang Institute of Life Science, Jiyang College of Zhejiang A&F University, Zhuji, 311800, Zhejiang, China Corresponding email: jingqiang.wang@jicat.org International Journal of Clinical Case Reports 2025, Vol.15, No.5 doi: 10.5376/ijccr.2025.15.0022 Received: 13 Jul., 2025 Accepted: 18 Aug., 2025 Published: 23 Sep., 2025 Copyright © 2025 Wang, This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Preferred citation for this article: Wang J.Q., 2025, Comparative study on construction methods of chronic disease prediction models based on big data, International Journal of Clinical Case Reports, 15(5): 209-218 (doi: 10.5376/ijccr.2025.15.0022) Abstract This study explores various modeling methods for chronic disease prediction using big data, with a focus on chronic disease prediction. The basic theories of prediction and commonly used data types are introduced, including clinical indicators, genetic information and lifestyle-related data. The application situations of statistical models, machine learning models and deep learning models were compared. Statistical models are easy to understand, but they still have shortcomings when dealing with high-dimensional and nonlinear data. Machine learning models perform well in identifying complex patterns and integrating different data, but they rely on feature selection and parameter adjustment. Deep learning models have advantages in handling multimodal data and time series prediction, but they require more data and computing resources. This study also mentioned the evaluation criteria of the model, issues related to data quality and privacy protection, as well as the challenges in terms of acceptance and interpretability in clinical practical applications. Overall, the analysis results show that different models each have their own advantages. Future research should focus on the application of hybrid modeling, multi-source data fusion, reinforcement learning and causal reasoning in clinical practice. Keywords Big data; Chronic disease prediction; Machine learning; Deep learning; Model comparison 1 Introduction Chronic diseases such as heart disease, diabetes, cancer and kidney disease are important causes of global morbidity and mortality. The large number of patients, long treatment cycle and high cost have exerted great pressure on public health. With the aging of the population and changes in lifestyle, the problem of chronic diseases has become more serious. Therefore, the earlier the detection and intervention, the better the therapeutic effect can be improved and the cost can be reduced (Rashid et al., 2022). Traditional diagnostic methods often struggle to cope with the complexity of chronic diseases and the coexistence of multiple diseases. Therefore, more advanced predictive approaches are needed (Kim et al., 2023). In the medical field, the use of big data-including electronic medical records, management information, wearable device data and large-scale clinical data-is changing the way diseases are predicted and decisions are made. Integrating and analyzing health data from different sources can establish predictive models, identify high-risk groups, and support early diagnosis and personalized treatment. With the help of machine learning and artificial intelligence (AI) technologies of big data, complex patterns can be better discovered, the accuracy of prediction can be improved, and active health management can be promoted (Tsai et al., 2025). However, data quality, the interpretability of results, and the integration of multi-source data remain issues that need to be addressed (Liu et al., 2023). This study will explore the methods of establishing chronic disease prediction models using big data, with a focus on analyzing the advantages and disadvantages of machine learning, deep learning, and hybrid methods. The innovation points include designing a multi-task and multi-modal learning framework capable of simultaneously predicting multiple diseases, adopting more advanced feature engineering and integration strategies, and combining structured and unstructured data to enhance the prediction effect. Through experiments on different datasets and disease types, this study aims to provide practical references for researchers and clinical personnel, helping them select and apply more appropriate modeling methods in actual medical practice.
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 209-218 http://medscipublisher.com/index.php/ijccr 210 2 Theoretical Basis and Literature Review 2.1 The main theoretical framework and development of chronic disease prediction The formation of chronic disease prediction models mainly relies on two forces: one is data-driven, and the other is theoretical guidance. Early work mostly used statistical methods such as logistic regression and Cox proportional hazards to estimate the risk of disease based on clinical and demographic data (Riley et al., 2016). With the development of big data, machine learning and deep learning have gradually become mainstream. They can handle high-dimensional information from multiple sources and achieve higher accuracy and better scalability (Ngiam and Khor, 2019). At the same time, theoretical frameworks such as social ecology and multi-factor were introduced to guide data selection and integration, so that the results could better reflect the health influencing factors at the individual and group levels. The latest research has proposed a way of combining theory with data, that is, integrating top-down theoretical guidance with bottom-up data mining. This method can help identify new risk factors and establish a multi-level prediction model that considers genetic, clinical, behavioral and environmental influences simultaneously (Prosperi et al., 2018). The combination of such frameworks helps to form more stable and scalable models, providing support for clinical and public health. 2.2 Common data types: clinical indicators, genomic data, lifestyle data More and more models for predicting chronic diseases are beginning to combine information from different sources. Clinical indicators, such as laboratory tests, medical images and electronic health records, are the basis of most models and can provide health information collected systematically and routinely (Tse et al., 2023). Genomic data, such as gene sequencing and multi-omics information, can help identify genetic risks and molecular mechanisms associated with diseases (Snyder and Zhou, 2019). Lifestyle data, such as exercise, diet and environmental exposure, are now available through wearable devices, health apps and self-reports, enabling dynamic and long-term tracking of behaviors related to chronic diseases (Snyder and Zhou, 2019). Combining these different types of data can enhance the predictive ability of the model and support individualized risk assessment and intervention (Alonso et al., 2017). 2.3 Research progress and limitations of big data-driven health prediction at home and abroad Health prediction based on big data has made significant progress worldwide. At present, large-scale information such as electronic medical records, medical images and multi-omics data is often used to establish more accurate models, which is conducive to the early detection of diseases, risk differentiation and personalized treatment (Snyder and Zhou, 2019; Nascimento et al., 2021). In many application scenarios, artificial intelligence and machine learning methods perform better than traditional statistical methods, with higher accuracy, specificity and scalability (Ngiam and Khor, 2019). These advancements have also driven the use of real-time risk estimation and prediction tools in clinical Settings (Tse et al., 2023). At present, there are still many difficult problems to be solved. Many studies have been restricted due to different data quality, incomplete information or non-standard records, and it is impossible to effectively combine data from different sources together. Methodological issues such as overfitting, lack of external validation, and limited applicability of the model to different populations are also very common (Riley et al., 2016; Nascimento et al., 2021). In addition, data privacy and security, as well as possible biases in the prediction results, have also attracted increasing attention (Prosperi et al., 2018; Ngiam and Khor, 2019). Only by addressing these challenges well can we better leverage the potential of big data in chronic disease prediction and promote fairer health outcomes. 3 Big data Processing and Feature Engineering 3.1 Data collection and integration: fusion of multi-source heterogeneous data In the context of big data, integrating data from multiple different sources is an important foundation for the prediction of chronic diseases. The data may come from electronic medical records, sensors, genetic information and patient self-reports, and the formats and structures of these data are all different. Combining them effectively can more comprehensively depict the health status of patients, discover complex relationships and improve
International Journal of Clinical Case Reports, 2025, Vol.15, No.5, 209-218 http://medscipublisher.com/index.php/ijccr 211 predictive effects. Some automated processing systems, such as tools based on AutoML, are increasingly being applied to simplify data collection and integration processes, including data cleaning, annotation, and encoding, in order to transform raw and diverse data into usable information. Multi-source data often leads to problems such as inconsistent data quality, many missing values, and inconsistent detailed data content. To solve these problems, complex data processing steps and corresponding professional knowledge are often required to ensure that the comprehensive data is both reliable and truly reflects the actual situation. With more advanced visualization tools, such as parallel coordinate graphs, the characteristics of the data can be understood more clearly, which is helpful for formulating integration strategies and thereby provides support for more stable feature extraction and model construction (Zhao et al., 2024). 3.2 Data preprocessing: missing values, outliers and normalization processing Data preprocessing is a crucial step in preparing data, as the original data is usually incomplete and may contain outliers or have inconsistent formats. Common processing methods include standardization, identification of outliers and normalization. These operations can enhance data quality and make the model more stable and reliable. Some automated tools can also reduce manual operations and lower the probability of errors. For instance, missing values can be filled in by using k-nearest neighbor impution or machine learning methods. Normalization can adjust different features to similar scales, thereby helping the model converge faster and improving interpretability. Although automation methods are becoming increasingly mature, the pretreatment process is still not simple and usually requires the repeated adjustment of parameters with the help of professional experience. Different preprocessing methods will directly affect the model's performance. If missing values or outliers are not handled properly, errors may be introduced or the prediction accuracy may be affected (Chicco et al., 2022). Therefore, the design and inspection of the preprocessing scheme need to be carried out with extreme caution, especially in health informatics applications where data quality requirements are extremely high. 3.3 Feature engineering: feature selection, dimension reduction and construction Feature engineering is of great significance for extracting useful information from complex data and enhancing the effectiveness of chronic disease prediction models. Through feature selection methods, such as SHAP-based importance assessment, filtering method, encapsulation method and embedding method, the most relevant variables can be screened out, redundancy can be reduced and understandability can be enhanced (Zhang, 2024). Dimensionality reduction techniques such as principal component analysis (PCA) and autoencoders can further simplify data and alleviate the computational pressure brought by high-dimensional data (Santoso and Priyadi, 2025). In addition to selection and compression, feature construction-through manual design, ensemble learning or deep learning-can also generate new information features and better capture latent patterns (Verdonck et al., 2021). Some automated feature engineering tools, such as tsfresh for time series, can automatically extract and screen statistically significant features, accelerating analysis and application implementation (Christ et al., 2018). Combining these methods can help establish more stable and scalable models in big data-driven health prediction (Rong et al., 2019; Mumuni and Mumuni, 2024). 4 Construction Methods of Chronic Disease Prediction Models 4.1 Statistical models Logistic regression and Cox regression have always been commonly used methods for predicting chronic diseases due to their ease of use and clear results. Logistic regression is highly effective in binary classification problems, such as using clinical indicators to predict whether diabetes, cardiovascular diseases or chronic kidney diseases will occur. Studies have found that when the data is not highly nonlinear or ultra-high-dimensional, the performance of logistic regression can be similar to that of some complex machine learning methods. Cox regression is commonly used in survival analysis and can estimate the occurrence time of events, so it is of great value for predicting disease progression and patient risk (Figure 1) (Zhang et al., 2023).
RkJQdWJsaXNoZXIy MjQ4ODYzNA==