Automatic fall risk assessment with Siamese network for stroke survivors using inertial sensor‐based signals

Background: Falls are common and dangerous for stroke survivors. Current fall risk assessment methods rely on subjective scales. Objective sensor-based methods could improve prediction accuracy. Objective: Develop machine learning models using inertial sensors to objectively classify fall risk in stroke survivors. Determine optimal sensor configurations and clinical test protocols. Methods: 21 stroke survivors performed balance, Timed Up and Go, 10 Meter Walk, and Sit-to-Stand tests with and without dual-tasking. A total of 8 motion sensors captured lower limb and trunk kinematics, and 92 spatiotemporal gait and clinical features were extracted. Supervised models—Support Vector Machine, Logistic Regression, and Random Forest—were implemented to classify high vs. low fall risk. Sensor setups and test combinations were evaluated. Results: The Random Forest model achieved 91% accuracy using dual-task balance sway and Timed Up and Go walk time features. Single thorax sensor models performed similarly to multi-sensor models. Balance and Timed Up and Go best-predicted fall risk. Conclusion: Machine learning models using minimal inertial sensors during clinical assessments can accurately quantify fall risk in stroke survivors. Single thorax sensor setups are effective. Findings demonstrate a feasible objective fall screening approach to assist rehabilitation.

Falls are caused by complex interaction between multiple risk factors which may be modified by age, disease and environment. A variety of methods and tools for fall risk assessment have been proposed, but none of which is universally accepted. Existing tools are generally not capable of providing a quantitative predictive assessment of fall risk. The need for objective, cost-effective and clinically applicable methods would enable quantitative assessment of fall risk on a subject-specific basis. Tracking objectively falls risk could provide timely feedback about the effectiveness of administered interventions enabling intervention strategies to be modified or changed if found to be ineffective. Moreover, some of the fundamental factors leading to falls and what actually happens during a fall remain unclear. Objectively documented and measured falls are needed to improve knowledge of fall in order to develop more effective prevention strategies and prolong independent living. In the last decade, several research groups have developed sensor-based automatic or semi-automatic fall risk assessment tools using wearable inertial sensors. This approach may also serve to detect falls. At the moment, i) several fall-risk assessment studies based on inertial sensors, even if promising, lack of a biomechanical model-based approach which could provide accurate and more detailed measurements of interests (e.g., joint moments, forces) and ii) the number of published real-world fall data of older people in a real-world environment is minimal since most authors have used simulations with healthy volunteers as a surrogate for real-world falls. With these limitations in mind, this thesis aims i) to suggest a novel method for the kinematics and dynamics evaluation of functional motor tasks, often used in clinics for the fall-risk evaluation, through a body sensor network and a biomechanical approach and ii) to define the guidelines for a fall detection algorithm based on a real-world fall database availability.

Just as there are many causes for falls among older adults, there also are many prevention strategies. The key to finding the right ones for each patient is to perform a thorough fall risk assessment, according to experts speaking in a Web-based conference sponsored by ECRI, a nonprofit health services research agency. Effective fall prevention can make a big difference in quality of life for seniors and give residents and caregivers a greater sense of peace. And, as with all safety measures, effective fall prevention also can mean savings for long-term care facilities. The majority of falls (60%) occur in the home environment, and 30% of falls occur in an institutional setting. It's estimated that 30% of falls in acute care facilities and 20% of falls in long-term care facilities result in “serious injury,” said Karen Holloway, a risk management analyst at ECRI and primary author of the organization's new guide “Falls Prevention Strategies in Healthcare Settings.” Of those who sustain hip fractures, 50% never return to their normal level of functioning. The cost of treating the 20% of falls resulting in serious injury in long-term care facilities in 2005 is estimated at $4.9 billion, excluding physician fees, according to the Center for Injury Prevention and Control and Treatment Costs data. Defensive barriers form the core of fall prevention strategies, according to Patricia Quigley, Ph.D, deputy director of the Veterans Health Administration's Patient Safety Center of Inquiry in Tampa. Fall prevention with defensive barriers may best be described through the “Swiss cheese theory,” she said. Defensive barriers to falls can be thought of as holes in a block of Swiss cheese. For a fall to occur, all of the holes have to line up—in other words, all of the barriers have to fail. Fall prevention assessments can be invaluable in pulling together the most effective defensive barriers for each patient. One effective model has been established at several VA centers, where fall risk assessments are performed for all patients at these clinics. The assessment team spans several disciplines, including a geriatrician, an advanced registered nurse practitioner, a physical therapist (who specializes in balance problems), and a pharmacist. The 2-hour fall risk assessment attempts to identify potential causes for falls and includes evaluations of vital signs, visual acuity and depth perception, and deep tendon reflexes, lower extremity sensory testing, a neurologic assessment, laboratory tests, and imaging. In an ongoing analysis of the reasons patients were referred to her falls clinic, accident and environmental factors accounted for 37%, followed by weakness and balance and gait disorders (12%), dizziness and vertigo (8%), and orthostatic hypotension (5%). Other reasons (acute illness, confusion, poor eyesight, and drugs) together accounted for 18%. Certain medications also contribute to fall risk, especially psychotropics, diuretics, antiarrhythmics, and digoxin. When assessing the home environment, an assessment team looks for uneven ground, and scrutinizes steps or ramps into the house and entry stairs. It also looks for clutter, throw rugs, problem floor surfaces, quality of lighting, and bathroom issues such as nonslip shower mats and grab bars. The team also tries to determine whether assistive devices are being used or are appropriate. Once the assessment is completed, the team evaluates the findings to develop an individualized fall prevention plan. In cases where a fall has occurred, the mnemonic SPLATT (Symptoms, Previous Falls, Location, Activity, Time, and Trauma) can provide a framework for doing a postfall evaluation to identify risk factors for additional falls. The algorithm could help narrow in on interventions to reduce fall risks, Dr. Quigley said. The ECRI guide is available for purchase by visiting www.ecri.org/Products_and_Services/Products.

The effectiveness of multifactorial fall risk assessment and intervention strategies is well documented. Although identifying feet/footwear-related influences on fall risk is a vital fall risk assessment component, few evidence-based resources or screening tools are available. To address this need, we developed the Screening Tool for Feet/Footwear-Related Influences on Fall Risk. Our tool is designed for older adults who are identified as at risk for falling, based on the CDC’s Stopping Elderly Accidents, Deaths, and Injuries (STEADI) Algorithm for Fall Risk Screening, Assessment, and Intervention. Tool development was informed by results of our systematic review of lower-limb factors associated with balance and falls. Our initial tool was evaluated by an external group of 9 interprofessional content experts. Those experts recommended modification of 8 items and rated the tool’s clarity as 81.2/100, appeal as 79.1/100, and clinical feasibility as 76.1/100. After incorporating recommended changes, we completed a modified Delphi study using 8 new interprofessional experts (average years of experience: 19.3). During Phase 1, Delphi participants recommended we combine items with similar treatment recommendations, add a question about orthoses, and increase the specificity of 9 items. This refinement resulted in a 20-item screening tool, which met approval after two rounds of consensus voting. Approval was defined based on the Item Content Validation Index, percentage of agreement > 80% on each item. The high level of agreement illustrates the tool’s content validity. Using our tool, an older adult’s feet/footwear-related risk factors can be identified and incorporated into an effective multifactorial fall prevention intervention.

Cognitive biases and contextual factors explaining variability in nurses’ fall risk judgements: a multi-centre cross-sectional study

BackgroundFalls are a serious and common problem among older adults. Low-tech, inexpensive, community-based fall prevention programs have been shown to be both effective and cost effective, however, these programs are not well-integrated into clinical practice.Research designWe surveyed primary care providers at a convenience sample of two accountable care organizations in Massachusetts to assess their beliefs, attitudes, knowledge, and practices relative to fall risk assessment and intervention for their older patients.ResultsResponse rate was 71%. Providers’ beliefs about the efficacy of fall risk assessment and intervention were mixed. Eighty-seven percent believed that they could be effective in reducing fall risk among their older adult patients. Ninety-six percent believed that all older adults should be assessed for fall risk; and, 85% believed that this assessment would identify fall risk factors that could be modified. Nonetheless, only 52% believed that they had the expertise to conduct fall risk assessment and only 68% believed that assessing older adult patients for fall risk was the prevailing standard of practice among their peer providers. Although most providers believed it likely that an evidence-based program could reduce fall risk among their patients, only 14% were aware of the Centers for Disease Control and Prevention’s fall risk assessment algorithm (STEADI Toolkit), and only 15% were familiar with Matter of Balance, the most widely disseminated community fall risk prevention program in Massachusetts.DiscussionNew strategies that more directly target providers are needed to accelerate integration of fall risk assessment and intervention into primary care practice.

Mastery learning is a form of competency-based education in which learning time varies but outcomes are uniform. Trainees must meet a minimum passing standard (MPS) before completing a mastery learning curriculum. The objective of this study was to establish a curriculum for fall risk and gait assessment for medical students, determine an MPS for a fall risk and gait assessment clinical skills examination (CSE), and apply the MPS to a sample of medical students completing a fall risk and gait assessment CSE. Medical students completed an interactive session about fall risk and gait assessment including the Timed Up and Go (TUG) test and completed deliberate practice with 3 patients. Skills were evaluated using an 18-item skills checklist. A panel of clinical experts set the MPS at 82%. Eighty-seven medical students participated. The average score on the checklist was 14.7 of 18 (81.4%.) Although almost all performed the TUG correctly, only 61% met the MPS for the checklist. Our results suggest that a mastery learning approach may better prepare the 39% of students that did not meet MPS to complete a fall risk and gait assessment.

This systematic review aimed to explore the recommended fall risk assessment practices in audiology, identify audiologists' reported practices in fall risk assessment, and recognize the barriers and facilitators affecting fall risk assessment in clinical practice. This systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses. CINAHL, PubMed, and gray literature yielded 262 articles. A total of 27 full-text articles were included in this review article. An additional 16 scope of practice and guideline documents were also reviewed. Pertinent data and findings from the review were tabulated and analyzed using a qualitative, inductive approach. Results revealed that despite fall risk assessment measures and protocols being mentioned, discussed, and reportedly implemented clinically in audiology literature, many audiologists are not conducting fall risk assessments clinically. The main challenges presented appear to be due to limited guidance within audiology documentation and inadequate training and knowledge of audiologists on fall risk factors and measures. This review article highlighted that all audiologists have an important role to play in reducing the global crisis of falls in older adults. However, without further research to aid in the development of standardization of documentation and training programs, we may continue to see a lack of awareness and education on fall risk and on the audiologist's role in the screening and early detection hereof.

Purpose. This study examined the reliability and validity of a Falls Risk Assessment (FRA) tool developed to identify risk factors associated with falls in homebound older adults. Design and Methods. FRA scores of 307 Medicare-eligible adults over 65 admitted sequentially to a home health agency (HHA) were analyzed retrospectively using a case-control design. A total of 18 subjects participated prospectively in assessment of criterion-related validity and rater reliability. Results. Mean FRA scores of fallers were significantly higher than non-fallers (10.13, 7.2, respectively; p < 0.05). The FRA and Performance-Oriented Mobility Assessment (POMA) demonstrated a strong negative correlation (r = −0.74), utilizing a Pearson correlation. Using percent agreement, FRA scores of nine raters yielded 94.74% agreement. Kuder-Richardson (KR)-20 analysis yielded internal consistency of 0.98, 0.97, and 0.98 within subjects scored, indicating high consistency among raters. An intraclass correlation coefficient (Model 3, 1) of 0.83 supports intra-rater reliability. History of recurrent falls was the only significant predictor in logistic regression (p = 0.027, odds ratio: 2.83). Implications. Data support use of the FRA in screening for fall-related risk factors in home-bound older adults.

single-camera-based gait monitoring is unobtrusive, inexpensive, and easy-to-use to monitor daily gait of seniors in their homes. However, most studies require subjects to walk perpendicularly to camera's optical axis or along some specified routes, which limits its application in elderly home monitoring. To build unconstrained monitoring environments, we propose a method to measure step length symmetry ratio (a useful gait parameter representing gait symmetry without significant relationship with age) from unconstrained straight walking using a single camera, without strict restrictions on walking directions or routes. according to projective geometry theory, we first develop a calculation formula of step length ratio for the case of unconstrained straight-line walking. Then, to adapt to general cases, we propose to modify noncollinear footprints, and accordingly provide general procedure for step length ratio extraction from unconstrained straight walking. Our method achieves a mean absolute percentage error (MAPE) of 1.9547% for 15 subjects' normal and abnormal side-view gaits, and also obtains satisfactory MAPEs for non-side-view gaits (2.4026% for 45°-view gaits and 3.9721% for 30°-view gaits). The performance is much better than a well-established monocular gait measurement system suitable only for side-view gaits with a MAPE of 3.5538%. Independently of walking directions, our method can accurately estimate step length ratios from unconstrained straight walking. This demonstrates our method is applicable for elders' daily gait monitoring to provide valuable information for elderly health care, such as abnormal gait recognition, fall risk assessment, etc. single-camera-based gait monitoring is unobtrusive, inexpensive, and easy-to-use to monitor daily gait of seniors in their homes. However, most studies require subjects to walk perpendicularly to camera's optical axis or along some specified routes, which limits its application in elderly home monitoring. To build unconstrained monitoring environments, we propose a method to measure step length symmetry ratio (a useful gait parameter representing gait symmetry without significant relationship with age) from unconstrained straight walking using a single camera, without strict restrictions on walking directions or routes. according to projective geometry theory, we first develop a calculation formula of step length ratio for the case of unconstrained straight-line walking. Then, to adapt to general cases, we propose to modify noncollinear footprints, and accordingly provide general procedure for step length ratio extraction from unconstrained straight walking. Our method achieves a mean absolute percentage error (MAPE) of 1.9547% for 15 subjects' normal and abnormal side-view gaits, and also obtains satisfactory MAPEs for non-side-view gaits (2.4026% for 45°-view gaits and 3.9721% for 30°-view gaits). The performance is much better than a well-established monocular gait measurement system suitable only for side-view gaits with a MAPE of 3.5538%. Independently of walking directions, our method can accurately estimate step length ratios from unconstrained straight walking. This demonstrates our method is applicable for elders' daily gait monitoring to provide valuable information for elderly health care, such as abnormal gait recognition, fall risk assessment, etc.

Older adults with cognitive impairment (CI) are twice as likely to fall compared to the general older adult population. Traditional fall risk assessments may not be suitable for older adults with CI due to their reliance on attention and recall. Hence, there is an interest in using objective technology-based fall risk assessment tools to assess falls within this population. This systematic review aims to evaluate the features and performance of technology-based fall risk assessment tools for older adults with CI. A systematic search was conducted across several databases such as PubMed and IEEE Xplore, resulting in the inclusion of 22 studies. Most studies focused on participants with dementia. The technologies included sensors, mobile applications, motion capture, and virtual reality. Fall risk assessments were conducted in the community, laboratory, and institutional settings; with studies incorporating continuous monitoring of older adults in everyday environments. Studies used a combination of technology-based inputs of gait parameters, socio-demographic indicators, and clinical assessments. However, many missed the opportunity to include cognitive performance inputs as predictors to fall risk. The findings of this review support the use of technology-based fall risk assessment tools for older adults with CI. Further advancements incorporating cognitive measures and additional longitudinal studies are needed to improve the effectiveness and clinical applications of these assessment tools. Additional work is also required to compare the performance of existing methods for fall risk assessment, technology-based fall risk assessments, and the combination of these approaches.

To assess the fall of risk among the elderly in selected urban area of Thrissur. Objectives a) To assess the fall risk among the elderly people in selected urban area of Kachery, Thrissur. b) To associate fall risk score with selected demographic variables. c) To correlate fall risk assessment questionnaire score and modified fall prevention checklist for personal risk factors score among elderly individuals. d) To teach the elderly people about fall prevention exercise. Methodology: Non-experimental descriptive research design is adopted in this study. We selected 60 samples through random sampling technique. Standardized fall risk assessment questionnaire built by national aging research institute and modified fall prevention checklist for personal risk factors built by Hamilton county was used to collect the data. Tool was administered by interview method for assessing fall risk. Fall preventive intervention module developed, validated and administered following data collection. The data collected were analyzed by using descriptive and inferential statistics. Result: The demographic profile of elderly people shows that 46.66% belongs to age group between 60-70 years and most of them 58.33% were females. The majority 73.33% of elderly person are at low risk for fall and 26.66% are at high risk for fall in questionnaire and 81.67% of elderly are low risk for fall, 18.33% are risk and there is no elderly person high risk for fall in checklist. The overall fall risk is high among elderly individual alone in home and low in elderly in nuclear families. The risk for fall among elderly based on previous history of fall shows that elderly with visual impairment those who don’t have previous knowledge about fall prevention and elderly age between 91-100 is high risk for fall. The risk for fall based on ability to perform ADL in elderly shows those who living alone in the home high risk for fall. There is significant association between score with selected variables like age, previous knowledge about fall prevention, elderly residing in their home alone. We found that there is perfect positive correlation r=1 between fall risk assessment, questionnaires and checklist score. Discussion: At the end of the study the investigator found that the risk for fall based on the assessment of fall history among elderly people shows that, there is significant association between age (p=0.0273) that is, age group between 91-100 years are high risk for fall. Previous knowledge about fall prevention shows that, elderly without previous knowledge about fall prevention is at high risk for fall (p= 0.03074). In sensory impairment that is, elderly having visual impairment (p=0.998) having risk for fall. The risk for fall among elderly people based on their ability to perform activities of daily living shows that, elderly residing in their home alone shows more risk for fall.

Stroke is one of the leading causes of severe handicap. Deficiencies in walking may present significant challenges to mobility, resulting in abnormal and inefficient gait patterns in stroke survivors. This study compared the gait characteristics of hemiparetic stroke survivors and those of healthy individuals and determined the relationship between gait characteristics, anthropometric and clinical characteristics of stroke survivors. A cross-sectional study of seventy patients who had survived six months or more after a stroke and seventy healthy individuals was conducted. They included seventy stroke survivors (46 males and 24 females) with mean age of 53.52±10.35 years and 70 age and gender matched controls. The stroke survivors were patients managed at the physiotherapy outpatient clinics of two teaching hospitals in Osun, South-West Nigeria. Using Observational Gait Analysis and Foot Print Method, gaits of participants were assessed in the following variables; gait speed, cadence, stride length, step length, step width and foot angle. Significant differences were found between all the gait characteristics of hemiparetic stroke survivors and those of the healthy control group. There was significant correlation among most of the gait characteristics of the stroke survivors and between stroke duration and all the gait characteristics with the exception of foot angle of nonparetic limb. This study confirmed that the gait characteristics of Nigerian stroke survivors deviate greatly from normal because of the morbidity, and stroke duration was related to gait characteristics. In the rehabilitative management of stroke survivors, attention should be given to improving the gait characteristics in order to enhance their functional ability. Keywords : Stroke survivor, gait analysis, hemiparesis, gait speed.

Falls are the most common preventable adverse events in hospitals and are strongly linked to movement-related disorders. Conducting fall risk assessments and implementing personalized interventions for older adults in sports rehabilitation settings can significantly reduce fall incidence. Sensor-based techniques and machine learning models offer new opportunities for measuring gait and balance in a more sophisticated way to enhance fall risk assessments. This study aims to develop an integrated sensor method to provide continuous and effective fall risk assessments for older adults in rehabilitation settings. A joint feature extraction scheme based on integrated sensors was proposed, including temporal features from inertial measurement unit (IMU) signals and spatial features from depth camera data during 3-m timed up and go (TUG) test. A set of classifiers, including support vector machine (SVM), logistic regression (LR), k-nearest neighbors (KNNs), random forest (RF), and eXtreme gradient boosting (XGBoost), were used in conjunction with a feature selection strategy to facilitate developing the predictive models for fall risk assessment. We conducted validation experiments using real-world data for comprehensive comparative analysis. The results demonstrate that our integrated approach achieves superior classification performance (AUC: 0.8633–0.9586). These findings suggest that the complementary features from sensors have advantages in bridging information gaps, reducing missed diagnoses, and assisting clinicians in early fall risk identification. The proposed method shows significant potential to deliver comprehensive fall risk assessments for older adults in rehabilitation settings.

Stroke survivors face a 73% fall rate within the first year after leaving the hospital. These falls cause serious injuries in 40% of cases and lead to healthcare costs of over $50 billion each year. Many of these falls are due to ongoing center of pressure (COP) abnormalities, such as velocity increases of 2-3 times normal levels, weight-bearing asymmetry exceeding 70%, and limits of stability reduced by 40-60%. These issues are often not addressed by standard rehabilitation. Although COP measurements provide objective indicators of fall risk, there has been no comprehensive review of interventions aimed at correcting these modifiable deficits. To systematically map the scope, variety, and characteristics of interventions aimed at adjusting COP variables in adult stroke survivors to reduce fall risk, while incorporating stakeholder insights on clinical implementation. We conducted a scoping review following PRISMA-ScR guidelines, searching PubMed, MEDLINE, and the Cochrane Library from January 2015 to June 2025 for studies on COP-targeted interventions with fall-related outcomes. We extracted data on intervention details, COP parameters, measurement protocols, and clinical results. A diverse stakeholder panel of seven members, including stroke survivors, physiotherapists, and technology specialists, offered insights on implementation through structured consultations. Nine studies with 306 participants mainly examined chronic stroke patients. The strongest evidence came from force-plate biofeedback across three studies, with effect sizes d = 0.52-0.84, showing consistent gains in sway velocity linked to a lower fall risk (r = 0.52-0.71). A 0.5 cm/s reduction in sway velocity correlated with about an 18% decrease in fall likelihood. Nevertheless, considerable methodological differences-such as equipment costs from $100 to $50,000 and varying measurement protocols-restrict clinical use. Stakeholders emphasized key factors: stroke survivors appreciated visual feedback ("seeing inside my own balance"), while clinicians highlighted the need to address time constraints and documentation. The review led to a resource-based implementation framework and consensus guidelines for standardized protocols. COP interventions show promising potential for addressing the hidden issue of post-stroke falls, with force-plate biofeedback being ready for careful clinical application.Success hinges on shifting from generic approaches to personalized rehabilitation that reveals and addresses subtle balance problems. The combination of moderate to large effect sizes and stakeholder-approved implementation strategies provides a clear path to transform these ongoing fall risks into confident community mobility. Nevertheless, realizing this potential requires coordinated efforts to standardize measurements, develop practical trials, and implement strategies across systems, balancing scientific rigor with clinical realities.