Clinical classification of memory and cognitive impairment with multimodal digital biomarkers.

INTRODUCTION: Early detection of Alzheimer's disease and cognitive impairment is critical to improving the healthcare trajectories of aging adults, enabling early intervention and potential prevention of decline. METHODS: To evaluate multi-modal feature sets for assessing memory and cognitive impairment, feature selection and subsequent logistic regressions were used to identify the most salient features in classifying Rey Auditory Verbal Learning Test-determined memory impairment. RESULTS: Multimodal models incorporating graphomotor, memory, and speech and voice features provided the stronger classification performance (area under the curve = 0.83; sensitivity = 0.81, specificity = 0.80). Multimodal models were superior to all other single modality and demographics models. DISCUSSION: The current research contributes to the prevailing multimodal profile of those with cognitive impairment, suggesting that it is associated with slower speech with a particular effect on the duration, frequency, and percentage of pauses compared to normal healthy speech.

Fall risk stratification of community-living older people. Commentary on the world guidelines for fall prevention and management.

The Task Force on Global Guidelines for Falls in Older Adults has put forward a fall risk stratification tool for community-dwelling older adults. This tool takes the form of a flowchart and is based on expert opinion and evidence. It divides the population into three risk categories and recommends specific preventive interventions or treatments for each category. In this commentary, we share our insights on the design, validation, usability and potential impact of this fall risk stratification tool with the aim of guiding future research.

Development of Data-Driven Metrics for Balance Impairment and Fall Risk Assessment in Older Adults.

Ageing incurs a natural decline of postural control which has been linked to an increased risk of falling. Accurate balance assessment is important in identifying postural instability and informing targeted interventions to prevent falls in older adults. Inertial sensor (IMU) technology offers a low-cost means for objective quantification of human movement. This paper describes two studies carried out to advance the use of IMU-based balance assessments in older adults. Study 1 (N = 39) presents the development of two new IMU-derived balance measures. Study 2 (N = 248) reports a reliability analysis of IMU postural stability measures and validates the novel balance measures through comparison with clinical scales. We also report a statistical fall risk estimation algorithm based on IMU data captured during static balance assessments alongside a method of improving this fall risk estimate by incorporating standard clinical fall risk factor data. Results suggest that both new balance measures are sensitive to balance deficits captured by the Berg Balance Scale (BBS) and Timed Up and Go test. Results obtained from the fall risk classifier models suggest they are more accurate (67.9%) at estimating fall risk status than a model based on BBS (59.2%). While the accuracies of the reported models are lower than others reported in the literature, the simplicity of the assessment makes it a potentially useful screening tool for balance impairments and falls risk. The algorithms presented in this paper may be suitable for implementation on a smartphone and could facilitate unsupervised assessment in the home.

Estimating balance, cognitive function, and falls risk using wearable sensors and the sit-to-stand test.

The five times sit-to-stand test (FTSS) is an established functional test, used clinically as a measure of lower-limb strength, endurance and falls risk. We report a novel method to estimate and classify cognitive function, balance impairment and falls risk using the FTSS and body-worn inertial sensors. 168 community dwelling older adults received a Comprehensive Geriatric Assessment which included the Mini-Mental State Examination (MMSE) and the Berg Balance Scale (BBS). Each participant performed an FTSS, with inertial sensors on the thigh and torso, either at home or in the clinical environment. Adaptive peak detection was used to identify phases of each FTSS from torso or thigh-mounted inertial sensors. Features were then extracted from each sensor to quantify the timing, postural sway and variability of each FTSS. The relationship between each feature and MMSE and BBS was examined using Spearman's correlation. Intraclass correlation coefficients were used to examine the intra-session reliability of each feature. A Poisson regression model with an elastic net model selection procedure was used to estimate MMSE and BBS scores, while logistic regression and sequential forward feature selection was used to classify participants according to falls risk, cognitive decline and balance impairment. BBS and MMSE were estimated using cross-validation with low root mean squared errors of 2.91 and 1.50, respectively, while the cross-validated classification accuracies for balance impairment, cognitive decline, and falls risk were 81.96, 72.71, and 68.74%, respectively. The novel methods reported provide surrogate measures which may have utility in remote assessment of physical and cognitive function.

Unsupervised Assessment of Balance and Falls Risk Using a Smartphone and Machine Learning.

Assessment of health and physical function using smartphones (mHealth) has enormous potential due to the ubiquity of smartphones and their potential to provide low cost, scalable access to care as well as frequent, objective measurements, outside of clinical environments. Validation of the algorithms and outcome measures used by mHealth apps is of paramount importance, as poorly validated apps have been found to be harmful to patients. Falls are a complex, common and costly problem in the older adult population. Deficits in balance and postural control are strongly associated with falls risk. Assessment of balance and falls risk using a validated smartphone app may lessen the need for clinical assessments which can be expensive, requiring non-portable equipment and specialist expertise. This study reports results for the real-world deployment of a smartphone app for self-directed, unsupervised assessment of balance and falls risk. The app relies on a previously validated algorithm for assessment of balance and falls risk; the outcome measures employed were trained prior to deployment on an independent data set. Results for a sample of 594 smartphone assessments from 147 unique phones show a strong association between self-reported falls history and the falls risk and balance impairment scores produced by the app, suggesting they may be clinically useful outcome measures. In addition, analysis of the quantitative balance features produced seems to suggest that unsupervised, self-directed assessment of balance in the home is feasible.

Reliability of inertial sensor based spatiotemporal gait parameters for short walking bouts in community dwelling older adults.

BACKGROUND: When performing quantitative analysis of gait in older adults we need to strike a balance between capturing sufficient data for reliable measurement and avoiding issues such as fatigue. The optimal bout duration is that which contains sufficient gait cycles to enable a reliable and representative estimate of gait performance. RESEARCH QUESTION: How does the number of gait cycles in a walking bout influence reliability of spatiotemporal gait parameters measured using body-worn inertial sensors in a cohort of community dwelling older adults? METHODS: One hundred and fifteen (115) community dwelling older adults executed three 30-metre walk trials in a single measurement session. Bilateral gait data were collected using two inertial sensors attached to each participant's right and left shank, and gait events detected from the medio-lateral angular velocity signal. The number of gait cycles selected from each walking trial was varied from 3 to 16. Intraclass correlation coefficients (ICC(2,k)) were calculated to evaluate the reliability of each spatiotemporal gait parameter according to the number of gait cycles included in the analysis. RESULTS: The specified algorithm and the clipping procedure for extracting short bouts of gait data seem appropriate for assessing older adults, providing reliable spatiotemporal measures from three gait cycles (three strides per leg) and good reliability for most parameters describing gait variability and gait asymmetry after six gait cycles (six strides per leg). SIGNIFICANCE: A combination of using bilateral sensor data and adaptive thresholds for gait event detection enable reliable measures of spatiotemporal gait parameters over short walking bouts (minimum six gait cycles) in community dwelling older adults. This opens new possibilities in the use of wearable sensors in gait assessment based on short walking tasks. We recommend the number of gait cycles should be reported along with the calculated measures as reference values.

Predicting Fall Counts Using Wearable Sensors: A Novel Digital Biomarker for Parkinson's Disease.

People with Parkinson's disease (PD) experience significant impairments to gait and balance; as a result, the rate of falls in people with Parkinson's disease is much greater than that of the general population. Falls can have a catastrophic impact on quality of life, often resulting in serious injury and even death. The number (or rate) of falls is often used as a primary outcome in clinical trials on PD. However, falls data can be unreliable, expensive and time-consuming to collect. We sought to validate and test a novel digital biomarker for PD that uses wearable sensor data obtained during the Timed Up and Go (TUG) test to predict the number of falls that will be experienced by a person with PD. Three datasets, containing a total of 1057 (671 female) participants, including 71 previously diagnosed with PD, were included in the analysis. Two statistical approaches were considered in predicting falls counts: the first based on a previously reported falls risk assessment algorithm, and the second based on elastic net and ensemble regression models. A predictive model for falls counts in PD showed a mean R2 value of 0.43, mean error of 0.42 and a mean correlation of 30% when the results were averaged across two independent sets of PD data. The results also suggest a strong association between falls counts and a previously reported inertial sensor-based falls risk estimate. In addition, significant associations were observed between falls counts and a number of individual gait and mobility parameters. Our preliminary research suggests that the falls counts predicted from the inertial sensor data obtained during a simple walking task have the potential to be developed as a novel digital biomarker for PD, and this deserves further validation in the targeted clinical population.

Detecting subtle mobility changes among older adults: the Quantitative Timed Up and Go test.

BACKGROUND: The Quantitative Timed Up and Go (QTUG) test uses wearable sensors, containing a triaxial accelerometer and an add-on triaxial gyroscope, to quantify performance during the TUG test with potential to capture more minor changes in mobility. AIMS: To examine the responsiveness, minimum detectable change (MDC) and observed effect size of QTUG in a cohort of socially active adults aged 50 years and over participating in a structured community exercise program. METHODS: 54 participants (91% females, mean age 63.6 ± 6.5 years) completed repeated QTUG testing under single- and dual-task conditions. Responsiveness of the QTUG was assessed by correlation of change in standard TUG with QTUG change (Pearson's correlation coefficient). MDC and effect sizes (standardized mean difference and Cohen's d) were also calculated for QTUG. RESULTS: There was a strong positive correlation between change in the standard TUG and change in QTUG (single task r = 0.91, p < 0.001). MDC in QTUG was calculated as 0.77 (Sd, 1.39; ICC 0.96) seconds (single task) and 2.33 (Sd 2.18; ICC 0.85) seconds (dual task). Several QTUG parameters showed improvements in mean values with small effect sizes (sit -to-stand transition time d = 0.418; walk time d = 0.398; cadence d = 0.306, swing time d = 0.314; step time d = 0.479; gait velocity d = 0.365; time to reach turn d = 0.322) under single-task conditions and with a moderate effect size (d = 0.549) in time taken to turn under the dual-task condition. CONCLUSION: Initial evidence of QTUG's responsiveness to change in mobility in active middle to older age adults has been demonstrated with small to moderate effect sizes observed in specific QTUG parameters.

Short Bouts of Gait Data and Body-Worn Inertial Sensors Can Provide Reliable Measures of Spatiotemporal Gait Parameters from Bilateral Gait Data for Persons with Multiple Sclerosis.

Wearable devices equipped with inertial sensors enable objective gait assessment for persons with multiple sclerosis (MS), with potential use in ambulatory care or home and community-based assessments. However, gait data collected in non-controlled settings are often fragmented and may not provide enough information for reliable measures. This paper evaluates a novel approach to (1) determine the effects of the length of the walking task on the reliability of calculated measures and (2) identify digital biomarkers for gait assessments from fragmented data. Thirty-seven participants (37) diagnosed with relapsing-remitting MS (EDSS range 0 to 4.5) executed two trials, walking 20 m each, with inertial sensors attached to their right and left shanks. Gait events were identified from the medio-lateral angular velocity, and short bouts of gait data were extracted from each trial, with lengths varying from 3 to 9 gait cycles. Intraclass correlation coefficients (ICCs) evaluate the degree of agreement between the two trials of each participant, according to the number of gait cycles included in the analysis. Results show that short bouts of gait data, including at least six gait cycles of bilateral data, can provide reliable gait measurements for persons with MS, opening new perspectives for gait assessment using fragmented data (e.g., wearable devices, community assessments). Stride time variability and asymmetry, as well as stride velocity variability and asymmetry, should be further explored as digital biomarkers to support the monitoring of symptoms of persons with neurological diseases.

Digital assessment of falls risk, frailty, and mobility impairment using wearable sensors.

Falls are among the most frequent and costly population health issues, costing $50bn each year in the US. In current clinical practice, falls (and associated fall risk) are often self-reported after the "first fall", delaying primary prevention of falls and development of targeted fall prevention interventions. Current methods for assessing falls risk can be subjective, inaccurate, have low inter-rater reliability, and do not address factors contributing to falls (poor balance, gait speed, transfers, turning). 8521 participants (72.7 ± 12.0 years, 5392 female) from six countries were assessed using a digital falls risk assessment protocol. Data consisted of wearable sensor data captured during the Timed Up and Go (TUG) test along with self-reported questionnaire data on falls risk factors, applied to previously trained and validated classifier models. We found that 25.8% of patients reported a fall in the previous 12 months, of the 74.6% of participants that had not reported a fall, 21.5% were found to have a high predicted risk of falls. Overall 26.2% of patients were predicted to be at high risk of falls. 29.8% of participants were found to have slow walking speed, while 19.8% had high gait variability and 17.5% had problems with transfers. We report an observational study of results obtained from a novel digital fall risk assessment protocol. This protocol is intended to support the early identification of older adults at risk of falls and inform the creation of appropriate personalized interventions to prevent falls. A population-based approach to management of falls using objective measures of falls risk and mobility impairment, may help reduce unnecessary outpatient and emergency department utilization by improving risk prediction and stratification, driving more patients towards clinical and community-based falls prevention activities.

Impact of Exercise Intervention in Parkinson's Disease can be Quantified Using Inertial Sensor Data and Clinical Tests.

Parkinson's Disease (PD) has the second-highest prevalence rate of all neurodegenerative disorders. It effects approximately 1% of the population over the age of 60, with this proportion rising further, in more elderly cohorts. PD manifests as several motor and non-motor disfunctions, which develop progressively over time. Gait and mobility problems are amongst the most debilitating symptoms for people with PD. They severely affect a person's ability to carry out daily activities of living and can lead to a decreased quality of life. However, recent research has shown exercise intervention to be effective in improving gait, and overall functional mobility, in persons with PD. In this paper, we study the effect of an exercise intervention, comprised of three separate methods of exercise - all which have been shown previously to be effective individually - on a cohort with early-to-moderate stage PD. We also examine the ability of the Timed Up and Go (TUG) test - instrumented with inertial sensors (QTUG) - and the Unified Parkinson's Disease Rating Scale (UPDRS) Part III in measuring the response to the exercise intervention. We found that TUG time and the QTUG-derived frailty index - along with many additional parameters derived from QTUG - showed a significant change between baseline and post-intervention, while the UPDRS Part III score did not. The direction of the changes in the QTUG parameters also align with the expected exercise effect from the literature. Our results suggest QTUG may be a more sensitive measure than UPDRS Part III for assessing the effect of exercise intervention on functional mobility in people with early-to-moderate stage PD.

Investigating normal day to day variations of postural control in a healthy young population using Wii balance boards.

The quantification of postural control (PC) provides the opportunity to understand the function and integration of the sensorimotor subsystems. The increased availability of portable sensing technology, such as Wii Balance Boards (WBB), has afforded the capacity to capture data pertaining to motor function, outside of the laboratory and clinical setting. However, prior to its use in long-term monitoring, it is crucial to understand natural daily PC variation. Twenty-four young adults conducted repeated static PC assessments over 20 consecutive weekdays, using WBBs. 16/24 participants (eyes open) and 11/24 participants (eyes closed) exhibited statistically significant differences (p <; 0.05) between their initial `once-off' measure and their daily measures of PC. This study showed that variations in PC exist in a healthy population, a once-off measure may not be representative of true performance and this inherent variation should be considered when implementing long-term monitoring protocols.

Longitudinal assessment of falls in patients with Parkinson's disease using inertial sensors and the Timed Up and Go test.

OBJECTIVE: To examine the predictive validity of a TUG test for falls risk, quantified using body-worn sensors (QTUG) in people with Parkinson's Disease (PD). We also sought to examine the inter-session reliability of QTUG sensor measures and their association with the Unified Parkinson's Disease Rating Scale (UPDRS) motor score. APPROACH: A six-month longitudinal study of 15 patients with Parkinson's disease. Participants were asked to complete a weekly diary recording any falls activity for six months following baseline assessment. Participants were assessed monthly, using a Timed Up and Go test, quantified using body-worn sensors, placed on each leg below the knee. MAIN RESULTS: The results suggest that the QTUG falls risk estimate recorded at baseline is 73.33% (44.90, 92.21) accurate in predicting falls within 90 days, while the Timed Up and Go time at baseline was 46.67% (21.27, 73.41) accurate. The Timed Up and Go time and QTUG falls risk estimate were strongly correlated with UPDRS motor score. Fifty-two of 59 inertial sensor parameters exhibited excellent inter-session reliability, five exhibited moderate reliability, while two parameters exhibited poor reliability. SIGNIFICANCE: The results suggest that QTUG is a reliable tool for the assessment of gait and mobility in Parkinson's disease and, furthermore, that it may have utility in predicting falls in patients with Parkinson's disease.

Fall Risk Assessment Through Automatic Combination of Clinical Fall Risk Factors and Body-Worn Sensor Data.

Falls are the leading global cause of accidental death and disability in older adults and are the most common cause of injury and hospitalization. Accurate, early identification of patients at risk of falling, could lead to timely intervention and a reduction in the incidence of fall-related injury and associated costs. We report a statistical method for fall risk assessment using standard clinical fall risk factors (N = 748). We also report a means of improving this method by automatically combining it, with a fall risk assessment algorithm based on inertial sensor data and the timed-up-and-go test. Furthermore, we provide validation data on the sensor-based fall risk assessment method using a statistically independent dataset. Results obtained using cross-validation on a sample of 292 community dwelling older adults suggest that a combined clinical and sensor-based approach yields a classification accuracy of 76.0%, compared to either 73.6% for sensor-based assessment alone, or 68.8% for clinical risk factors alone. Increasing the cohort size by adding an additional 130 subjects from a separate recruitment wave (N = 422), and applying the same model building and validation method, resulted in a decrease in classification performance (68.5% for combined classifier, 66.8% for sensor data alone, and 58.5% for clinical data alone). This suggests that heterogeneity between cohorts may be a major challenge when attempting to develop fall risk assessment algorithms which generalize well. Independent validation of the sensor-based fall risk assessment algorithm on an independent cohort of 22 community dwelling older adults yielded a classification accuracy of 72.7%. Results suggest that the present method compares well to previously reported sensor-based fall risk assessment methods in assessing falls risk. Implementation of objective fall risk assessment methods on a large scale has the potential to improve quality of care and lead to a reduction in associated hospital costs, due to fewer admissions and reduced injuries due to falling.

Assessment and classification of early-stage multiple sclerosis with inertial sensors: comparison against clinical measures of disease state.

A cross-sectional study on patients with early-stage multiple sclerosis (MS) was conducted to examine the reliability of manual and automatic mobility measures derived from shank-mounted inertial sensors during the Timed Up and Go (TUG) test, compared to control subjects. Furthermore, we aimed to determine if disease status [as measured by the Multiple Sclerosis Impact Scale (MSIS-20) and the Expanded Disability Status Score (EDSS)] can be explained by measurements obtained using inertial sensors. We also aimed to determine if patients with early-stage MS could be automatically distinguished from healthy controls subjects, using inertial parameters recorded during the TUG test. The mobility of 38 patients (aged 25-65 years, 14 M, 24 F), diagnosed with relapsing-remitting MS and 33 healthy controls (14 M, 19 F, age 50-65), was assessed using the TUG test, while patients wore inertial sensors on each shank. Reliability analysis showed that 36 of 53 mobility parameters obtained during the TUG showed excellent intrasession reliability, while nine of 53 showed moderate reliability. This compared favorably with the reliability of the mobility parameters in healthy controls. Exploratory regression models of the EDSS and MSIS-20 scales were derived, using mobility parameters and an elastic net procedure in order to determine which mobility parameters influence disease state. A cross-validated elastic net regularized regression model for MSIS-20 yielded a mean square error (MSE) of 1.1 with 10 degrees of freedom (DoF). Similarly, an elastic net regularized regression model for EDSS yielded a cross-validated MSE of 1.3 with 10 DoF. Classification results show that the mobility parameters of participants with early-stage MS could be distinguished from controls with 96.90% accuracy. Results suggest that mobility parameters derived from MS patients while completing the TUG test are reliable, are associated with disease state in MS, and may have utility in screening for early-stage MS.

Stability of daily home-based measures of postural control over an 8-week period in highly functioning older adults.

PURPOSE: The focus of this study was to monitor daily objective measures of standing postural control over an 8-week period, recorded in a person's home, in a population of healthy older adults. Establishing natural patterns of variation in the day-to-day signal, occurring in the relative absence of functional decline or disease, would enable us to determine thresholds for changes in postural control from baseline that could be considered clinically important. METHODS: Eighteen community-dwelling older adults (3 M, 15 F, 72 ± 6 years) participated in a home-based trial where each day they were asked to complete a technology-enabled routine consisting of a short questionnaire, as well as a quiet standing balance trial. Centre of pressure (COP) excursions were calculated over the course of each daily balance trial to generate variables such as postural sway length and mean sway frequency. RESULTS: The data demonstrated large differences between subjects in centre of pressure measures (coefficients of variation ranging 37-107 %, depending on the variable). Each participant also exhibited variations in their day-to-day trials (e.g. coefficients of variation across 8 weeks ranging ~17-56 %, within person for mean COP distance). Inter- and intra-subject differences were not strongly related to functional tests, suggesting that these variations were not necessarily aberrant movement patterns, but are seemingly representative of natural movement variability. CONCLUSIONS: The idea of applying a group-focused approach at an individual level may result in misclassifying important changes for a particular individual. Early detection of deterioration can only be achieved through the creation of individual trajectories for each person, that are inherently self referential.

Classification of frailty and falls history using a combination of sensor-based mobility assessments.

Frailty is an important geriatric syndrome strongly linked to falls risk as well as increased mortality and morbidity. Taken alone, falls are the most common cause of injury and hospitalization and one of the principal causes of death and disability in older adults worldwide. Reliable determination of older adults' frailty state in concert with their falls risk could lead to targeted intervention and improved quality of care. We report a mobile assessment platform employing inertial and pressure sensors to quantify the balance and mobility of older adults using three physical assessments (timed up and go (TUG), five times sit to stand (FTSS) and quiet standing balance). This study examines the utility of each individual assessment, and the novel combination of assessments, to screen for frailty and falls risk in older adults.Data were acquired from inertial and pressure sensors during TUG, FTSS and balance assessments using a touchscreen mobile device, from 124 community dwelling older adults (mean age 75.9 ± 6.6 years, 91 female). Participants were given a comprehensive geriatric assessment which included questions on falls and frailty. Methods based on support vector machines (SVM) were developed using sensor-derived features from each physical assessment to classify patients at risk of falls risk and frailty.In classifying falls history, combining sensor data from the TUG, Balance and FTSS tests to a single classifier model per gender yielded mean cross-validated classification accuracy of 87.58% (95% CI: 84.47-91.03%) for the male model and 78.11% (95% CI: 75.38-81.10%) for the female model. These results compared well or exceeded those for classifier models for each test taken individually. Similarly, when classifying frailty status, combining sensor data from the TUG, balance and FTSS tests to a single classifier model per gender, yielded mean cross-validated classification accuracy of 93.94% (95% CI: 91.16-96.51%) for the male model and 84.14% (95% CI: 82.11-86.33%) for the female model (mean 89.04%) which compared well or exceeded results for physical tests taken individually.Results suggest that the combination of these three tests, quantified using body-worn inertial sensors, could lead to improved methods for assessing frailty and falls risk.

Frailty status can be accurately assessed using inertial sensors and the TUG test.

BACKGROUND: frailty is an important geriatric syndrome linked to increased mortality, morbidity and falls risk. METHODS: a total of 399 community-dwelling older adults were assessed using Fried's frailty phenotype and the timed up and go (TUG) test. Tests were quantified using shank-mounted inertial sensors. We report a regression-based method for assessment of frailty using inertial sensor data obtained during TUG. For comparison, frailty was also assessed using the same method based on grip strength and manual TUG time. RESULTS: using inertial sensor data, participants were classified as frail or non-frail with mean accuracy of 75.20% (stratified by gender). Using TUG time alone, frailty status was classified correctly with mean classification accuracy of 71.82%. Similarly, using grip strength alone, the frailty status was classified correctly with mean classification accuracy of 77.65%. Stratifying sensor data by gender yielded significantly (p<0.05) increased accuracy in classifying frailty when compared with equivalent manual TUG time-based models. CONCLUSION: results suggest that a simple protocol involving assessment using a well-known mobility test (Timed Up and Go (TUG)) and inertial sensors can be a fast and effective means of automatic, non-expert assessment of frailty.

A comparison of cross-sectional and prospective algorithms for falls risk assessment.

Falls are the most common cause of injury and hospitalization and one of the principal causes of death and disability in older adults worldwide. Accurate identification of patients at risk of falls could lead to timely medical intervention, reducing the incidence of falls related injuries along with associated costs. The current best practice for studies of falls and falls risk recommends the use of prospective follow-up data. However, the majority of studies reporting sensor based methods for assessment of falls risk employ cross-sectional falls data (falls history). The purpose of this study was to compare the performance of sensor based falls risk assessment algorithms derived from cross-sectional (N=909) and prospective (N=259) datasets in terms of false positive rate. The utility of any classification algorithm is clearly limited by a high false positive rate. An estimate of the false positive rate for both cross-sectional and prospective algorithms was determined using an inertial sensor data set of 611 TUG tests from 55 healthy control subjects, with no history of falls. We aimed to determine which falls risk assessment algorithm is more effective at classifying falls risk in healthy control subjects. The cross-sectional algorithm correctly classified 94.11% of tests, while the prospective algorithm, correctly classified 79.38% of tests. Results suggest that sensor based falls risk assessment algorithms generated using cross-sectional falls data, may be more effective than those generated using prospective data in classifying healthy controls and reducing associated false positives.

Quantitative assessment of multiple sclerosis using inertial sensors and the TUG test.

Multiple sclerosis (MS) is a progressive neurological disorder affecting between 2 and 2.5 million people globally. Tests of mobility form part of clinical assessments of MS. Quantitative assessment of mobility using inertial sensors has the potential to provide objective, longitudinal monitoring of disease progression in patients with MS. The mobility of 21 patients (aged 25-59 years, 8 M, 13 F), diagnosed with relapsing-remitting MS was assessed using the Timed up and Go (TUG) test, while patients wore shank-mounted inertial sensors. This exploratory, cross-sectional study aimed to examine the reliability of quantitative measures derived from inertial sensors during the TUG test, in patients with MS. Furthermore, we aimed to determine if disease status (as measured by the Multiple Sclerosis Impact Scale (MSIS-29) and the Expanded Disability Status Score (EDSS)) can be predicted by assessment using a TUG test and inertial sensors. Reliability analysis showed that 32 of 52 inertial sensors parameters obtained during the TUG showed excellent intrasession reliability, while 11 of 52 showed moderate reliability. Using the inertial sensors parameters, regression models of the EDSS and MSIS-29 scales were derived using the elastic net procedure. Using cross validation, an elastic net regularized regression model of MSIS yielded a mean square error (MSE) of 334.6 with 25 degrees of freedom (DoF). Similarly, an elastic net regularized regression model of EDSS yielded a cross-validated MSE of 1.5 with 6 DoF. Results suggest that inertial sensor parameters derived from MS patients while completing the TUG test are reliable and may have utility in assessing disease state as measured using EDSS and MSIS.