Predict Fall Risk Research Articles

Neuroimaging, Behavioral, and Gait Correlates of Fall Profile in Older Adults.

Prior research has suggested that measurements of brain functioning and performance on dual tasks (tasks which require simultaneous performance) are promising candidate predictors of fall risk among older adults. However, no prior study has investigated whether brain function measurements during dual task performance could improve prediction of fall risks and whether the type of subtasks used in the dual task paradigm affects the strength of the association between fall characteristics and dual task performance. In this study, 31 cognitively normal, community-dwelling older adults provided a self-reported fall profile (number of falls and fear of falling), completed a gait dual task (spell a word backward while walking on a GaitRite mat), and completed a supine dual task (rhythmic finger tapping with one hand while completing the AX continuous performance task (AX-CPT) with the other hand) during functional magnetic resonance imaging (fMRI). Gait performance, AX-CPT reaction time and accuracy, finger tapping cadence, and brain functioning in finger-tapping-related and AX-CPT-related brain regions all showed declines in the dual task condition compared to the single task condition. Dual-task gait, AX-CPT and finger tapping performance, and brain functioning were all independent predictors of fall profile. No particular measurement domain stood out as being the most strongly associated measure with fall variables. Fall characteristics are determined by multiple factors; brain functioning, motor task, and cognitive task performance in challenging dual-task conditions all contribute to the risk of falling.

Fall incidence in hospitalized patients and prediction of its risk factors using a weighted Poisson model

AimFalls in hospital as a major cause of disability and death threaten patients’ safety and quality of life. We studied fall incidence in hospital, and predicted its risk factors using weighted Poisson (WP) model versus other models.MethodThis cross-sectional study was performed on the patients referred to two central hospitals in Qazvin, Iran between 2017 and 2019. The data were collected using the Morse scale and fall reporting forms in the hospital patient safety units (288 falls). Factors including age, gender, time of fall, fall location, cause of fall and its complications, drugs administrated, disease history, post-fall care measures, presence of companion, and length of hospital stay were assessed. The WP model was compared with other models.ResultsFall incidence was 2.5 per 1000 patient days. Among them, 62.5% were elderly (mean age 65.7 ± 19.21 yr). Using the WP model, age, gender, fall location and fall cause, drugs administered, post-fall care measures (P < 0.001), and the presence of companion were identified as risk factors for falling (P < 0.001) Older females, those without a companion, and those without post-fall care measures and with medication history were at a higher risk. Falls from bed were the prevalent type of fall (IRR = 1.65). Falls in the internal ward were lower than in other wards (IRR = 0.67).ConclusionThe WP model is suggested as an appropriate model to predict fall risk factors. Fall rate may be reduced by combining information on risk factors with the strategies of training nurses or caregivers, or making possible changes in patients’ environment.

Subjective Evaluation of Balance by the Dizziness Handicap Inventory Does Not Predict Fall Risk in Older Adults Visiting Otolaryngology Clinics.

Subjective symptoms of dizziness in older adults are affected not only by objective data such as postural balance, but also by complex psychological factors. Published data analyzing how simultaneous evaluations of both objective and subjective assessments of balance can predict fall risk remain lacking. This study examined how fall risk can be predicted based on both objective data for balance and hearing and subjective symptoms of dizziness among older adults visiting otolaryngology clinics. Medical charts of 76 patients ≥65 years old with dizziness/vertigo who visited the otolaryngology clinic were reviewed. Objective data were evaluated by postural balance (posturographic data with eyes open and closed, and one-leg standing test), spontaneous nystagmus, and mean hearing levels. Subjective handicap associated with dizziness/vertigo was assessed using the Dizziness Handicap Inventory (DHI). Subjective mental status of anxiety and depression were assessed using the Hospital Anxiety and Depression Scale (HADS). Information on history (cardiovascular diseases) and fall accidents within the preceding year was collected using an in-house interview sheet. Objective data on postural balance did not correlate with subjective symptoms on DHI or HADS (P > .05, Pearson's correlation coefficient). Adjusted logistic regression modeling with the outcome of incident falls revealed that poor postural balance significantly predicted fall risk (P < .05; 4.9 [1.4-16.8] per 10-cm2 increment). Nystagmus tended to be associated with fall risk. In contrast, DHI score did not predict fall risk (P = .43; 1.0 [0.9-1.03]). Receiver operating characteristic analysis proposed a cut-off for postural sway with eyes closed >6.1 cm2 as optimal to predict falls in patients with nystagmus (AUC, 0.74; 95% confidence interval, 0.48-0.997). Poor postural balance is associated with increased fall risk after adjusting for subjective symptoms in older adults at otolaryngology clinics. Conversely, the self-perceived dizziness handicap of DHI score is an insufficient tool to evaluate their fall risk.

Differentiating fallers from nonfallers using nonlinear variability analyses of data from a low-cost portable footswitch device: a feasibility study

Purpose: Falls are one of the main causes of injuries in older adults. This study evaluated a low-cost footswitch device that was designed to measure gait variability and investigates whether there are any relationships between variability metrics and clinical balance tests for individuals with a history of previous falls. Methods: Sixteen older adults completed a history of falls questionnaire, three functional tests related to fall risk, and walked on a treadmill with the footswitch device. We extracted the stride times from the device and applied two nonlinear variability analyses: coefficient of variation and detrended fluctuation analysis. Results: The temporal variables and variability metrics from the footswitch device correlated with gold-standard measurements based on ground reaction force data. One variability metric (detrended fluctuation analysis) showed a significant relationship with the presence of past falls with a sensitivity of 43%. Conclusion: This feasibility study demonstrates the basis for using low-cost footswitch devices to predict fall risk.

Predictive validity of three home fall hazard assessment tools for older adults in Thailand.

This study aimed to examine the predictive validity of two internationally well-known instruments, the Modified Home Falls and Accidents Screening Tool (Modified HOME FAST) and the Modified Home Falls and Accidents Screening Tool-Self Report (Modified HOME FAST-SR), and the newly developed Thai Home Falls Hazard Assessment Tool (Thai-HFHAT) (69 items) in predicting falls among older Thai adults. It also aimed to examine the predictive validity of the two abbreviated versions (44 and 27 items) of the Thai-HFHAT, which were developed post hoc to accommodate older adults’ limited literacy and poor vision and to facilitate the identification of high-impact home fall hazards that are prevalent in the Thailand context. A prospective cohort study was conducted among 450 participants aged 60 years and above who were assessed by the aforementioned tools at baseline, for which data on fall incidence were then collected during the one-year follow-up. The Cox proportional hazard model was applied to estimate hazard ratios (HRs); then, Harrell’s C-statistics and receiver operating characteristic (ROC) analyses were conducted to identify the best cutoff point, sensitivity and specificity for each instrument. The results showed that the fall hazard rate was 2.04 times per 1,000 person-days. Taking into account both the predictive validity and applicability, the Thai-HFHAT (44 items) was found to be the most suitable screening tool due to its highest sensitivity and specificity (93% and 72%) at the cutoff score of 18. In conclusion, our study showed that these internationally validated home fall hazard assessment tools were quite applicable for Thailand, but further tailoring the tools into a specific local context yielded even more highly valid tools in predicting fall risk among older Thai adults. Although these findings were well reproducible by inferring from the internal validation results, further external validation in the independent population is necessary.

Can dual-task paradigms predict Falls better than single task? – A systematic literature review

With about one third of adults aged 65 years and older being reported worldwide to fall each year, and an even higher prevalence with advancing age, aged-related falls and the associated disabilities and mortality are a major public health concern. In this context, identification of fall risk in healthy older adults is a key component of fall prevention. Since dual-task outcomes rely on the interaction between cognition and motor control, some studies have demonstrated the role of dual-task walking performance or costs in predicting future fallers. However, based on previous reviews on the topic, (1) discriminative and (2) predictive powers of dual tasks involving gait and a concurrent task are still a matter of debate, as is (3) their superiority over single tasks in terms of fall-risk prediction. Moreover, less attention has been paid to dual tasks involving postural control and transfers (such as gait initiation and turns) as motor tasks. In the present paper, we therefore systematically reviewed recent literature over the last 7 years in order to answer the three above mentioned questions regarding the future of lab-based dual tasks (involving posture, gait initiation, gait and turning) as easily applicable tests for identifying healthy older adult fallers. Despite great heterogeneity among included studies, we emphasized, among other things, the promising added value of dual tasks including turns and other transfers, such as in the Timed Up and Go test, for prediction of falls. Further investigation of these is thus warranted.

Falls Risk Assessment Tools for Hospitals: An Evidence-Based Approach

To implement and evaluate a best practice model for reducing hospital falls that incorporates the UK clinical guideline to cease using a traditional fall risk prediction tool (FRAT) for all patients aged 65 years or older; and patients aged 50-64 years who are judged by a clinician to be at higher risk of falling because of an underlying condition, compared with usual care.

Prediction of fall events during admission using eXtreme gradient boosting: a comparative validation study

As the performance of current fall risk assessment tools is limited, clinicians face significant challenges in identifying patients at risk of falling. This study proposes an automatic fall risk prediction model based on eXtreme gradient boosting (XGB), using a data-driven approach to the standardized medical records. This study analyzed a cohort of 639 participants (297 fall patients and 342 controls) from Chang Gung Memorial Hospital, Chiayi Branch, Taiwan. A derivation cohort of 507 participants (257 fall patients and 250 controls) was collected for constructing the prediction model using the XGB algorithm. A comparative validation of XGB and the Morse Fall Scale (MFS) was conducted with a prospective cohort of 132 participants (40 fall patients and 92 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models. This machine learning method provided a higher sensitivity than the standard method for fall risk stratification. In addition, the most important predictors found (Department of Neuro-Rehabilitation, Department of Surgery, cardiovascular medication use, admission from the Emergency Department, and bed rest) provided new information on in-hospital fall event prediction and the identification of patients with a high fall risk.

Slip-Fall Predictors in Community-Dwelling, Ambulatory Stroke Survivors: A Cross-sectional Study.

Considering the multifactorial nature and the often-grave consequences of falls in people with chronic stroke (PwCS), determining measurements that best predict fall risk is essential for identifying those who are at high risk. We aimed to determine measures from the domains of the International Classification of Functioning, Disability and Health (ICF) that can predict laboratory-induced slip-related fall risk among PwCS. Fifty-six PwCS participated in the experiment in which they were subjected to an unannounced slip of the paretic leg while walking on an overground walkway. Prior to the slip, they were given a battery of tests to assess fall risk factors. Balance was assessed using performance-based tests and instrumented measures. Other fall risk factors assessed were severity of sensorimotor impairment, muscle strength, physical activity level, and psychosocial factors. Logistic regression analysis was performed for all variables. The accuracy of each measure was examined based on its sensitivity and specificity for fall risk prediction. Of the 56 participants, 24 (43%) fell upon slipping while 32 (57%) recovered their balance. The multivariate logistic regression analysis model identified dynamic gait stability, hip extensor strength, and the Timed Up and Go (TUG) score as significant laboratory-induced slip-fall predictors with a combined sensitivity of 75%, a specificity of 79.2%, and an overall accuracy of 77.3%. The results indicate that fall risk measures within the ICF domains-body, structure, and function (dynamic gait stability and hip extensor strength) and activity limitation (TUG)-could provide a sensitive laboratory-induced slip-fall prediction model in PwCS.Video Abstract available for more insights from the authors (see the Video, Supplemental Digital Content 1, available at: http://links.lww.com/JNPT/A323).

Identification of important factors in an inpatient fall risk prediction model to improve the quality of care using EHR and electronic administrative data: A machine-learning approach

BackgroundInpatient falls, many resulting in injury or death, are a serious problem in hospital settings. Existing falls risk assessment tools, such as the Morse Fall Scale, give a risk score based on a set of factors, but don’t necessarily signal which factors are most important for predicting falls. Artificial intelligence (AI) methods provide an opportunity to improve predictive performance while also identifying the most important risk factors associated with hospital-acquired falls. We can glean insight into these risk factors by applying classification tree, bagging, random forest, and adaptive boosting methods applied to Electronic Health Record (EHR) data. ObjectiveThe purpose of this study was to use tree-based machine learning methods to determine the most important predictors of inpatient falls, while also validating each via cross-validation. Materials and methodsA case-control study was designed using EHR and electronic administrative data collected between January 1, 2013 to October 31, 2013 in 14 medical surgical units. The data contained 38 predictor variables which comprised of patient characteristics, admission information, assessment information, clinical data, and organizational characteristics. Classification tree, bagging, random forest, and adaptive boosting methods were used to identify the most important factors of inpatient fall-risk through variable importance measures. Sensitivity, specificity, and area under the ROC curve were computed via ten-fold cross validation and compared via pairwise t-tests. These methods were also compared to a univariate logistic regression of the Morse Fall Scale total score. ResultsIn terms of AUROC, bagging (0.89), random forest (0.90), and boosting (0.89) all outperformed the Morse Fall Scale (0.86) and the classification tree (0.85), but no differences were measured between bagging, random forest, and adaptive boosting, at a p-value of 0.05. History of Falls, Age, Morse Fall Scale total score, quality of gait, unit type, mental status, and number of high fall risk increasing drugs (FRIDs) were considered the most important features for predicting inpatient fall risk. ConclusionsMachine learning methods have the potential to identify the most relevant and novel factors for the detection of hospitalized patients at risk of falling, which would improve the quality of patient care, and to more fully support healthcare provider and organizational leadership decision-making. Nurses would be able to enhance their judgement to caring for patients at risk for falls. Our study may also serve as a reference for the development of AI-based prediction models of other iatrogenic conditions. To our knowledge, this is the first study to report the importance of patient, clinical, and organizational features based on the use of AI approaches.

Weaker Braking Force, A New Marker of Worse Gait Stability in Alzheimer Disease.

Background: Braking force is a gait marker associated with gait stability. This study aimed to determine the alteration of braking force and its correlation with gait stability in Alzheimer disease (AD).Methods: A total of 32 AD patients and 32 healthy controls (HCs) were enrolled in this study. Gait parameters (braking force, gait variability, and fall risk) in the walking tests of Free walk, Barrier, and Count backward were measured by JiBuEn® gait analysis system. Gait variability was calculated by the coefficient of variation (COV) of stride time, stance time, and swing time.Results: The braking force of AD was significantly weaker than HCs in three walking tests (P < 0.001, P < 0.001, P = 0.007). Gait variability of AD showed significant elevation than HCs in the walking of Count backward (COVstride: P = 0.013; COVswing: P = 0.006). Fall risk of AD was significantly higher than HCs in three walking tests (P = 0.001, P = 0.001, P = 0.001). Braking force was negatively associated with fall risks in three walking tests (P < 0.001, P < 0.001, P < 0.001). There were significant negative correlations between braking force and gait variability in the walking of Free walk (COVstride: P = 0.018; COVswing: P = 0.013) and Barrier (COVstride: P = 0.002; COVswing: P = 0.001), but not Count backward (COVstride: P = 0.888; COVswing: P = 0.555).Conclusion: Braking force was weaker in AD compared to HCs, reflecting the worse gait stability of AD. Our study suggests that weakening of braking force may be a new gait marker to indicate cognitive and motor impairment and predict fall risk in AD.

Machine Learning Predicts the Fall Risk of Total Hip Arthroplasty Patients Based on Wearable Sensor Instrumented Performance Tests

BackgroundThe prevalence of falls affects the wellbeing of aging adults and places an economic burden on the healthcare system. Integration of wearable sensors into existing fall risk assessment tools enables objective data collection that describes the functional ability of patients. In this study, supervised machine learning was applied to sensor-derived metrics to predict the fall risk of patients following total hip arthroplasty. MethodsAt preoperative, 2-week, and 6-week postoperative appointments, patients (n = 72) were instrumented with sensors while they performed the timed-up-and-go walking test. Preoperative and 2-week postoperative data were used to form the feature sets and 6-week total times were used as labels. Support vector machine and linear discriminant analysis classifier models were developed and tested on various combinations of feature sets and feature reduction schemes. Using a 10-fold leave-some-subjects-out testing scheme, the accuracy, sensitivity, specificity, and area under the receiver-operator curve (AUC) were evaluated for all models. ResultsA high performance model (accuracy = 0.87, sensitivity = 0.97, specificity = 0.46, AUC = 0.82) was obtained with a support vector machine classifier using sensor-derived metrics from only the preoperative appointment. An overall improved performance (accuracy = 0.90, sensitivity = 0.93, specificity = 0.59, AUC = 0.88) was achieved with a linear discriminant analysis classifier when 2-week postoperative data were added to the preoperative data. ConclusionThe high accuracy of the fall risk prediction models is valuable for patients, clinicians, and the healthcare system. High-risk patients can implement preventative measures and low-risk patients can be directed to enhanced recovery care programs.

A Novel Approach for Fall Risk Prediction Using the Inertial Sensor Data From the Timed-Up-and-Go Test in a Community Setting

Post-stroke patients usually suffer from a higher fall risk. Identifying potential fallers and giving them proper attention could reduce their chance of a fall that results in severe injuries and decreased quality of life. In this study, we introduced a novel approach for fall risk prediction that evaluates Short-form Berg Balance Scale scores via inertial measurement unit data measured from a 3-meter timed-up-and-go test. This approach used sensor technology and was thus easy to implement, and allowed a quantitative analysis of both gait and balance. The results showed that elastic net logistic regression achieved the best performance with 85% accuracy and 88% area under the curve compared with support vector machine, least absolute shrinkage and selection operator (LASSO), and stepwise logistic regression. This paper provides a framework for using sensor-based features together with a feature-selection strategy for screening and predicting the fall risk of post-stroke patients in a convenient setup with high accuracy. The findings of this study will not only enable the assessment of fall risk among post-stroke patients in a cost-effective manner but also provide decision-making support for community care providers and medical professionals in the form of sensor-based data on gait performance.

Changes In Dual-task Gait Speed Following A 10-week Golf Program In Older Adults

PURPOSE: To examine the change in dual-tasking ability during gait in response to a golf exercise program in healthy, older adults. BACKGROUND: The ability of older adults to perform dual-tasking during gait has been studied as a predictor of fall risk. Therefore, it is important to investigate exercise programs that not only improve fitness and balance in older adults, but also enhance the ability to dual-task. METHODS: Fifteen healthy, older adults without previous golf experience were enrolled in a golf program with fitness testing before and after the intervention. One participant had to drop out of the study due to a work-related injury at week 8. Dual-task performance was measured using a fast-gait task while counting backwards by threes on a ProtokineticsTM walking mat. Cognitive cost was determined by normalizing the dual-task responses to a seated counting task. Paired t tests were run to determine significance. Results are presented as mean±SD. Cohen’s d effect sizes were calculated and reported as small=0.2, medium=0.5, and large=0.8. RESULTS: Gait speed during the dual-task was significantly increased following the golf program with a large effect size (1.75±0.19m/s to 1.91±0.22m/s; p=0.007; d=0.85). This increase in gait speed coincided with increases in both average stride length (2.3%; p=0.061; d=0.55) and average cadence (5.8%; p=0.059; d=0.55). Cognitive dual cost did not change between pre and post testing but trended towards improving (40.94%; p=0.207; d=0.35). CONCLUSION: Golf is a unique, multimodal activity that has a beneficial impact on fitness in healthy, older adults. This study demonstrated that a golf program can improve the ability to perform dual tasking. Participants were able to increase their gait speed without compromising the amount of numbers they could recite correctly. The participants trended towards an improved correct response rate following the program as shown by the improvement in cognitive dual cost. Golf should be encouraged as a physical activity program for older adults. Supported by R&A Grant GHA0012017.

Development and validation of a robotic multifactorial fall-risk predictive model: A one-year prospective study in community-dwelling older adults.

BackgroundFalls in the elderly are a major public health concern because of their high incidence, the involvement of many risk factors, the considerable post-fall morbidity and mortality, and the health-related and social costs. Given that many falls are preventable, the early identification of older adults at risk of falling is crucial in order to develop tailored interventions to prevent such falls. To date, however, the fall-risk assessment tools currently used in the elderly have not shown sufficiently high predictive validity to distinguish between subjects at high and low fall risk. Consequently, predicting the risk of falling remains an unsolved issue in geriatric medicine. This one-year prospective study aims to develop and validate, by means of a cross-validation method, a multifactorial fall-risk model based on clinical and robotic parameters in older adults.MethodsCommunity-dwelling subjects aged ≥ 65 years were enrolled. At the baseline, all subjects were evaluated for history of falling and number of drugs taken daily, and their gait and balance were evaluated by means of the Timed “Up & Go” test (TUG), Gait Speed (GS), Short Physical Performance Battery (SPPB) and Performance-Oriented Mobility Assessment (POMA). They also underwent robotic assessment by means of the hunova robotic device to evaluate the various components of balance. All subjects were followed up for one-year and the number of falls was recorded. The models that best predicted falls—on the basis of: i) only clinical parameters; ii) only robotic parameters; iii) clinical plus robotic parameters—were identified by means of a cross-validation method.ResultsOf the 100 subjects initially enrolled, 96 (62 females, mean age 77.17±.49 years) completed the follow-up and were included. Within one year, 32 participants (33%) experienced at least one fall (“fallers”), while 64 (67%) did not (“non-fallers”). The best classifier model to emerge from cross-validated fall-risk estimation included eight clinical variables (age, sex, history of falling in the previous 12 months, TUG, Tinetti, SPPB, Low GS, number of drugs) and 20 robotic parameters, and displayed an area under the receiver operator characteristic (ROC) curve of 0.81 (95% CI: 0.72–0.90). Notably, the model that included only three of these clinical variables (age, history of falls and low GS) plus the robotic parameters showed similar accuracy (ROC AUC 0.80, 95% CI: 0.71–0.89). In comparison with the best classifier model that comprised only clinical parameters (ROC AUC: 0.67; 95% CI: 0.55–0.79), both models performed better in predicting fall risk, with an estimated Net Reclassification Improvement (NRI) of 0.30 and 0.31 (p = 0.02), respectively, and an estimated Integrated Discrimination Improvement (IDI) of 0.32 and 0.27 (p<0.001), respectively. The best model that comprised only robotic parameters (the 20 parameters identified in the final model) achieved a better performance than the clinical parameters alone, but worse than the combination of both clinical and robotic variables (ROC AUC: 0.73, 95% CI 0.63–0.83).ConclusionA multifactorial fall-risk assessment that includes clinical and hunova robotic variables significantly improves the accuracy of predicting the risk of falling in community-dwelling older people. Our data suggest that combining clinical and robotic assessments can more accurately identify older people at high risk of falls, thereby enabling personalized fall-prevention interventions to be undertaken.

Metrics extracted from a single wearable sensor during sit-stand transitions relate to mobility impairment and fall risk in people with multiple sclerosis

BackgroundApproximately half of the 2.3 million people with multiple sclerosis (PwMS) will fall in any three-month period. Currently clinicians rely on self-report measures or simple functional assessments, administered at discrete time points, to assess fall risk. Wearable inertial sensors are a promising technology for increasing the sensitivity of clinical assessments to accurately predict fall risk, but current accelerometer-based approaches are limited. Research questionWill metrics derived from wearable accelerometers during a 30-second chair stand test (30CST) correlate with clinical measures of disease severity, balance confidence and fatigue in PwMS, and can these metrics be used to accurately discriminate fallers from non-fallers? MethodsThirty-eight PwMS (21 fallers) completed self-report outcome measures then performed the 30CST while triaxial acceleration data were collected from inertial sensors adhered to the thigh and chest. Accelerometer metrics were derived for the sit-to-stand and stand-to-sit transitions and relationships with clinical metrics were assessed. Finally, the metrics were used to develop a logistic regression model to classify fall status. ResultsAccelerometer-derived metrics were significantly associated with multiple clinical metrics that capture disease severity, balance confidence and fatigue. Performance of a logistic regression for classifying fall status was enhanced by including accelerometer features (accuracy 74%, AUC 0.78) compared to the standard of care (accuracy 68%, AUC 0.74) or patient reported outcomes (accuracy 71%, AUC 0.75). SignificanceAccelerometer derived metrics were associated with clinically relevant measures of disease severity, fatigue and balance confidence during a balance challenging task. Inertial sensors could feasibly be utilized to enhance the accuracy of functional assessments to identify fall risk in PwMS. Simplicity of these accelerometer-based metrics could facilitate deployment for community-based monitoring.

Impact of Altering Data Granularity Levels on Predictive Modelling: A Case Study of Fall Risk Prediction in Older Persons.

Classification systems are widely used in medicine for knowledge representation. The hierarchical relationships between concepts in a classification system can be exploited in prediction models by looking for the optimal predictive granularity level. In this study, we used the Anatomical Therapeutic Chemical (ATC) classification system to cluster medications in the context of predicting medication-related falls in older persons. We compared the performance of fall risk prediction by describing medications at varying granularity levels of the ATC classification system. We found that the level of abstraction significantly affects the predictive performance in terms of both discrimination (measured by the receiver operating characteristic curve AUC-ROC) and calibration. An implication of these findings to the researchers is that data representation at different granularity levels can influence the predictive performance. The optimal granularity level can be determined by experimentation.

\u201cStudy protocol for the \u226565\u2009years NOrthern jutland Cohort of Fall risk Assessment with Objective measurements (the NOCfao study)\u201d

BackgroundAccidental falls are common among community-dwellers, probably due to the level of physical activity and impaired postural stability. Today, fall risk prediction tools’ discriminative validity are only moderate. In order to increase the accuracy, multiple variables such as highly validated objective field measurements of physical activity and impaired postural stability should be adressed in order to predict falls. The main aim of this paper is to describe the ≥65 years NOrthern jutland Cohort of Fall risk Assessment with Objective measurements (NOCfao) investigating the association between physical activity and impaired postural stability and the risk of fall episodes among community-dwelling older adults.MethodsThe study consists of a baseline session where the participants are asked to respond to three questionnaires, perform physical tests (i.e., measuring strength in the upper and lower extremities, balance, and walking speed), participate in an assessment of pain sensitivity, and to wear an ankle mounted pedometer for measuring physical activity for 5 days. Subsequently, the fall incidences and the circumstances surrounding the falls during the previous 1 to 2 months will be recorded throughout a one-year follow-up period.DiscussionThis study will add to the present-day understanding of the association between physical activity and impaired postural stability and the risk of fall episodes among community-dwelling older adults. These data will provide valid and reliable information on the relationship between these variables and their significance for community-dwelling older adults.Trial registrationClinicalTrials.gov identifier: NCT2995317. Registered December 13th, 2016.

Comparison of Machine Learning Models to Predict Risk of Falling in Osteoporosis Elderly

Abstract Falls are a multifactorial cause of injuries for older people. Subjects with osteoporosis are more vulnerable to falls. The focus of this study is to investigate the performance of the different machine learning models built on spatiotemporal gait parameters to predict falls particularly in subjects with osteoporosis. Spatiotemporal gait parameters and prospective registration of falls were obtained from a sample of 110 community dwelling older women with osteoporosis (age 74.3 ± 6.3) and 143 without osteoporosis (age 68.7 ± 6.8). We built four different models, Support Vector Machines, Neuronal Networks, Decision Trees, and Dynamic Bayesian Networks (DBN), for each specific set of parameters used, and compared them considering their accuracy, precision, recall and F-score to predict fall risk. The F-score value shows that DBN based models are more efficient to predict fall risk, and the best result obtained is when we use a DBN model using the experts’ variables with FSMC’s variables, mixed variables set, obtaining an accuracy of 80%, and recall of 73%. The results confirm the feasibility of computational methods to complement experts’ knowledge to predict risk of falling within a period of time as high as 12 months.

Physical Activity Mediates the Relationship between Gait Function and Fall Incidence after Total Knee Arthroplasty.

The present study aims to examine (1) the preoperative factors that can predict postoperative falls, (2) whether postoperative physical activity (PA) mediates the relationship between fall incidence and gait function, and (3) whether postoperative PA levels are associated with fall risk in total knee arthroplasty (TKA) patients. Ninety-six patients (mean age: 72.0 ± 6.1 years) who were observed postoperatively for 6 months were selected. Timed up and go (TUG) was assessed as an indicator of gait function. Fall incidence and PA were investigated for 6 months post-TKA. The body mass index, history of preoperative falls, knee pain, knee extensor strength, range of motion in knee flexion, and modified gait efficacy scale were evaluated. Additionally, postoperative PA levels were categorized into three groups-low: <3,000, moderate: 3,000 to 4,000, and high: ≥4,000 steps/day. The relative fall incidence rate was calculated according to the total number of falls normalized for every 1,000 steps/day for 6 months postoperatively. Twenty-five (26.0%) of the 96 patients had at least one fall. The TUG, knee pain, and knee extensor strength were identified preoperatively as significant variables affecting postoperative falls. The mediated effects model revealed that postoperative fall incidence was predicted by preoperative TUG and postoperative PA. Postoperative PA was significantly associated with preoperative TUG. Moreover, both the preoperative TUG and postoperative PA were selected as significant variables for predicting fall incidence. Thus, postoperative PA mediates the relationship between gait function and fall incidence after TKA. Furthermore, the relative fall incidence rate associated with a low PA level was significantly higher than that associated with moderate and high PA levels. In conclusion, preoperative assessments of TUG performance, muscle strength, and knee pain were effective in predicting fall risk. Additionally, an increase in PA could contribute to reducing fall risk in TKA patients. Therefore, our results suggest that preoperative screening for fall predictors and managing postoperative PA could reduce the fall incidence in TKA patients.