Search

Abstract Lower limb amputation is a medical intervention which causes motor disability and may compromise quality of life. Several factors determine patients’ health outcomes, including an appropriate prosthetic provision and an effective rehabilitation program, necessitating a thorough quantitative observation through different data sources. In this context, the role of interoperability becomes essential, facilitating the reuse of real-world data through the provision of structured and easily accessible databases. This study introduces a comprehensive 10-year dataset encompassing clinical features, mobility measurements, and prosthetic knees of 1006 trans-femoral amputees during 1962 hospital stays for rehabilitation. The dataset is made available in both comma-separated values (CSV) format and HL7 Fast Healthcare Interoperability Resources (FHIR)-based representation, ensuring broad utility and compatibility for researchers and healthcare practitioners. This initiative contributes to advancing community understanding of post-amputation rehabilitation and underscores the significance of interoperability in promoting seamless data sharing for meaningful insights into healthcare outcomes.

Abstract This study aimed to validate a wearable device’s walking speed estimation pipeline, considering complexity, speed, and walking bout duration. The goal was to provide recommendations on the use of wearable devices for real-world mobility analysis. Participants with Parkinson’s Disease, Multiple Sclerosis, Proximal Femoral Fracture, Chronic Obstructive Pulmonary Disease, Congestive Heart Failure, and healthy older adults (n = 97) were monitored in the laboratory and the real-world (2.5 h), using a lower back wearable device. Two walking speed estimation pipelines were validated across 4408/1298 (2.5 h/laboratory) detected walking bouts, compared to 4620/1365 bouts detected by a multi-sensor reference system. In the laboratory, the mean absolute error (MAE) and mean relative error (MRE) for walking speed estimation ranged from 0.06 to 0.12 m/s and − 2.1 to 14.4%, with ICCs (Intraclass correlation coefficients) between good (0.79) and excellent (0.91). Real-world MAE ranged from 0.09 to 0.13, MARE from 1.3 to 22.7%, with ICCs indicating moderate (0.57) to good (0.88) agreement. Lower errors were observed for cohorts without major gait impairments, less complex tasks, and longer walking bouts. The analytical pipelines demonstrated moderate to good accuracy in estimating walking speed. Accuracy depended on confounding factors, emphasizing the need for robust technical validation before clinical application. Trial registration: ISRCTN – 12246987.

BackgroundWrist-worn inertial sensors are used in digital health for evaluating mobility in real-world environments. Preceding the estimation of spatiotemporal gait parameters within long-term recordings, gait detection is an important step to identify regions of interest where gait occurs, which requires robust algorithms due to the complexity of arm movements. While algorithms exist for other sensor positions, a comparative validation of algorithms applied to the wrist position on real-world data sets across different disease populations is missing. Furthermore, gait detection performance differences between the wrist and lower back position have not yet been explored but could yield valuable information regarding sensor position choice in clinical studies. ObjectiveThe aim of this study was to validate gait sequence (GS) detection algorithms developed for the wrist position against reference data acquired in a real-world context. In addition, this study aimed to compare the performance of algorithms applied to the wrist position to those applied to lower back–worn inertial sensors. MethodsParticipants with Parkinson disease, multiple sclerosis, proximal femoral fracture (hip fracture recovery), chronic obstructive pulmonary disease, and congestive heart failure and healthy older adults (N=83) were monitored for 2.5 hours in the real-world using inertial sensors on the wrist, lower back, and feet including pressure insoles and infrared distance sensors as reference. In total, 10 algorithms for wrist-based gait detection were validated against a multisensor reference system and compared to gait detection performance using lower back–worn inertial sensors. ResultsThe best-performing GS detection algorithm for the wrist showed a mean (per disease group) sensitivity ranging between 0.55 (SD 0.29) and 0.81 (SD 0.09) and a mean (per disease group) specificity ranging between 0.95 (SD 0.06) and 0.98 (SD 0.02). The mean relative absolute error of estimated walking time ranged between 8.9% (SD 7.1%) and 32.7% (SD 19.2%) per disease group for this algorithm as compared to the reference system. Gait detection performance from the best algorithm applied to the wrist inertial sensors was lower than for the best algorithms applied to the lower back, which yielded mean sensitivity between 0.71 (SD 0.12) and 0.91 (SD 0.04), mean specificity between 0.96 (SD 0.03) and 0.99 (SD 0.01), and a mean relative absolute error of estimated walking time between 6.3% (SD 5.4%) and 23.5% (SD 13%). Performance was lower in disease groups with major gait impairments (eg, patients recovering from hip fracture) and for patients using bilateral walking aids. ConclusionsAlgorithms applied to the wrist position can detect GSs with high performance in real-world environments. Those periods of interest in real-world recordings can facilitate gait parameter extraction and allow the quantification of gait duration distribution in everyday life. Our findings allow taking informed decisions on alternative positions for gait recording in clinical studies and public health. Trial RegistrationISRCTN Registry 12246987; https://www.isrctn.com/ISRCTN12246987 International Registered Report Identifier (IRRID)RR2-10.1136/bmjopen-2021-050785

Abstract Background Although digital mobility outcomes (DMOs) can be readily calculated from real-world data collected with wearable devices and ad-hoc algorithms, technical validation is still required. The aim of this paper is to comparatively assess and validate DMOs estimated using real-world gait data from six different cohorts, focusing on gait sequence detection, foot initial contact detection (ICD), cadence (CAD) and stride length (SL) estimates. Methods Twenty healthy older adults, 20 people with Parkinson’s disease, 20 with multiple sclerosis, 19 with proximal femoral fracture, 17 with chronic obstructive pulmonary disease and 12 with congestive heart failure were monitored for 2.5 h in the real-world, using a single wearable device worn on the lower back. A reference system combining inertial modules with distance sensors and pressure insoles was used for comparison of DMOs from the single wearable device. We assessed and validated three algorithms for gait sequence detection, four for ICD, three for CAD and four for SL by concurrently comparing their performances (e.g., accuracy, specificity, sensitivity, absolute and relative errors). Additionally, the effects of walking bout (WB) speed and duration on algorithm performance were investigated. Results We identified two cohort-specific top performing algorithms for gait sequence detection and CAD, and a single best for ICD and SL. Best gait sequence detection algorithms showed good performances (sensitivity > 0.73, positive predictive values > 0.75, specificity > 0.95, accuracy > 0.94). ICD and CAD algorithms presented excellent results, with sensitivity > 0.79, positive predictive values > 0.89 and relative errors

Background: The General Medicine (GM) department has the highest patient volume and heterogeneity among other hospital specialties. Closely examining hospitalization data is crucial because patients come with various conditions or traits. Length of stay (LoS) in hospitals is often used as an efficiency indicator. It is influenced by various factors, including the patient's medical background, demographics, and type of diseases/signs/symptoms at the triage. LoS is a variable that can vary widely, making it difficult to estimate it promptly and accurately, but doing so is highly beneficial. Moreover, efficiently grouping and managing patients based on their expected LoS remains a significant challenge for healthcare organizations. Objectives: This study aimed to compare the predictive ability of nine Machine Learning (ML) regression models in estimating the actual number of LoS days using demographics and clinical information recorded at admission as independent variables. Methods: We analyzed data collected on patients hospitalized at the GM department of the Sant'Orsola-Malpighi University Hospital in Bologna, Italy, who were admitted through the Emergency Department. The data were collected from January 1, 2022, to October 26, 2022. Nine ML regression models were used to predict LoS by analyzing historical data and patient information. The models' performance was assessed through root mean squared prediction error (RMSPE) and mean absolute prediction error (MAPE). Moreover, we used K-means clustering to group patients' medical and organizational criticalities (such as diseases, signs, symptoms, and administrative problems) into four clusters. Feature Importance plots and SHAP (SHapley Additive exPlanations) values were employed to identify the more essential features and enhance the interpretability of the results. Results: We analyzed the LoS of 3757 eligible patients, which showed an average of 13 days and a standard deviation of 11.8 days. We randomly divided patients into a training cohort of 2630 (70 %) and a test cohort of 1127 (30 %). The predictive performance of the different models was between 11.00 and 16.16 days for RMSPE and between 7.52 and 10.78 days for MAPE. The eXtreme Gradient Boosting Regression (XGBR) model had the lowest prediction error, both in terms of RMSPE (11.00 days) and MAE (7.52 days). Sex, arrival via own vehicle/walk-in, ambulance arrival, light blue risk category, age 70 or older, and orange risk category are some of the top features. Conclusion: The ML models evaluated in this study reported good predictive performance, with the XGBR model exhibiting the lowest prediction error. This model holds the potential to aid physicians in administering appropriate clinical interventions for patients in the GM department. This model can also help healthcare services predict the resources necessary to better manage hospitalization.

Introduction Millions of people survive injuries to the central or peripheral nervous system for which neurorehabilitation is required. In addition to the physical and cognitive impairments, many neurorehabilitation patients experience pain, often not widely recognised and inadequately treated. This is particularly true for multiple sclerosis (MS) patients, for whom pain is one of the most common symptoms. In clinical practice, pain assessment is usually conducted based on a subjective estimate. This approach can lead to inaccurate evaluations due to the influence of numerous factors, including emotional or cognitive aspects. To date, no objective and simple to use clinical methods allow objective quantification of pain and the diagnostic differentiation between the two main types of pain (nociceptive vs neuropathic). Wearable technologies and artificial intelligence (AI) have the potential to bridge this gap by continuously monitoring patients’ health parameters and extracting meaningful information from them. Therefore, we propose to develop a new automatic AI-powered tool to assess pain and its characteristics during neurorehabilitation treatments using physiological signals collected by wearable sensors.Methods and analysis We aim to recruit 15 participants suffering from MS undergoing physiotherapy treatment. During the study, participants will wear a wristband for three consecutive days and be monitored before and after their physiotherapy sessions. Measurement of traditionally used pain assessment questionnaires and scales (ie, painDETECT, Doleur Neuropathique 4 Questions, EuroQoL-5-dimension-3-level) and physiological signals (photoplethysmography, electrodermal activity, skin temperature, accelerometer data) will be collected. Relevant parameters from physiological signals will be identified, and AI algorithms will be used to develop automatic classification methods.Ethics and dissemination The study has been approved by the local Ethical Committee (285-2022-SPER-AUSLBO). Participants are required to provide written informed consent. The results will be disseminated through contributions to international conferences and scientific journals, and they will also be included in a doctoral dissertation.Trial registration number NCT05747040.

IntroductionThe clinical assessment of mobility, and walking specifically, is still mainly based on functional tests that lack ecological validity. Thanks to inertial measurement units (IMUs), gait analysis is shifting to unsupervised monitoring in naturalistic and unconstrained settings. However, the extraction of clinically relevant gait parameters from IMU data often depends on heuristics-based algorithms that rely on empirically determined thresholds. These were mainly validated on small cohorts in supervised settings.MethodsHere, a deep learning (DL) algorithm was developed and validated for gait event detection in a heterogeneous population of different mobility-limiting disease cohorts and a cohort of healthy adults. Participants wore pressure insoles and IMUs on both feet for 2.5 h in their habitual environment. The raw accelerometer and gyroscope data from both feet were used as input to a deep convolutional neural network, while reference timings for gait events were based on the combined IMU and pressure insoles data.Results and discussionThe results showed a high-detection performance for initial contacts (ICs) (recall: 98%, precision: 96%) and final contacts (FCs) (recall: 99%, precision: 94%) and a maximum median time error of −0.02 s for ICs and 0.03 s for FCs. Subsequently derived temporal gait parameters were in good agreement with a pressure insoles-based reference with a maximum mean difference of 0.07, −0.07, and

Abstract Wearable devices are used in movement analysis and physical activity research to extract clinically relevant information about an individual’s mobility. Still, heterogeneity in protocols, sensor characteristics, data formats, and gold standards represent a barrier for data sharing, reproducibility, and external validation. In this study, we aim at providing an example of how movement data (from the real-world and the laboratory) recorded from different wearables and gold standard technologies can be organized, integrated, and stored. We leveraged on our experience from a large multi-centric study (Mobilise-D) to provide guidelines that can prove useful to access, understand, and re-use the data that will be made available from the study. These guidelines highlight the encountered challenges and the adopted solutions with the final aim of supporting standardization and integration of data in other studies and, in turn, to increase and facilitate comparison of data recorded in the scientific community. We also provide samples of standardized data, so that both the structure of the data and the procedure can be easily understood and reproduced.

Abstract Background Measuring mobility in daily life entails dealing with confounding factors arising from multiple sources, including pathological characteristics, patient specific walking strategies, environment/context, and purpose of the task. The primary aim of this study is to propose and validate a protocol for simulating real-world gait accounting for all these factors within a single set of observations, while ensuring minimisation of participant burden and safety. Methods The protocol included eight motor tasks at varying speed, incline/steps, surface, path shape, cognitive demand, and included postures that may abruptly alter the participants’ strategy of walking. It was deployed in a convenience sample of 108 participants recruited from six cohorts that included older healthy adults (HA) and participants with potentially altered mobility due to Parkinson’s disease (PD), multiple sclerosis (MS), proximal femoral fracture (PFF), chronic obstructive pulmonary disease (COPD) or congestive heart failure (CHF). A novelty introduced in the protocol was the tiered approach to increase difficulty both within the same task (e.g., by allowing use of aids or armrests) and across tasks. Results The protocol proved to be safe and feasible (all participants could complete it and no adverse events were recorded) and the addition of the more complex tasks allowed a much greater spread in walking speeds to be achieved compared to standard straight walking trials. Furthermore, it allowed a representation of a variety of daily life relevant mobility aspects and can therefore be used for the validation of monitoring devices used in real life. Conclusions The protocol allowed for measuring gait in a variety of pathological conditions suggests that it can also be used to detect changes in gait due to, for example, the onset or progression of a disease, or due to therapy. Trial registration: ISRCTN—12246987.

ObjectiveThis study aims to develop and compare different models to predict the Length of Stay (LoS) and the Prolonged Length of Stay (PLoS) of inpatients admitted through the emergency department (ED) in general patient settings. This aim is not only to promote any specific model but rather to suggest a decision-supporting tool (i.e., a prediction framework).MethodsWe analyzed a dataset of patients admitted through the ED to the “Sant”Orsola Malpighi University Hospital of Bologna, Italy, between January 1 and October 26, 2022. PLoS was defined as any hospitalization with LoS longer than 6 days. We deployed six classification algorithms for predicting PLoS: Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB), AdaBoost, K-Nearest Neighbors (KNN), and logistic regression (LoR). We evaluated the performance of these models with the Brier score, the area under the ROC curve (AUC), accuracy, sensitivity (recall), specificity, precision, and F1-score. We further developed eight regression models for LoS prediction: Linear Regression (LR), including the penalized linear models Least Absolute Shrinkage and Selection Operator (LASSO), Ridge and Elastic-net regression, Support vector regression, RF regression, KNN, and eXtreme Gradient Boosting (XGBoost) regression. The model performances were measured by their mean square error, mean absolute error, and mean relative error. The dataset was randomly split into a training set (70%) and a validation set (30%).ResultsA total of 12,858 eligible patients were included in our study, of whom 60.88% had a PloS. The GB classifier best predicted PloS (accuracy 75%, AUC 75.4%, Brier score 0.181), followed by LoR classifier (accuracy 75%, AUC 75.2%, Brier score 0.182). These models also showed to be adequately calibrated. Ridge and XGBoost regressions best predicted LoS, with the smallest total prediction error. The overall prediction error is between 6 and 7 days, meaning there is a 6–7 day mean difference between actual and predicted LoS.ConclusionOur results demonstrate the potential of machine learning-based methods to predict LoS and provide valuable insights into the risks behind prolonged hospitalizations. In addition to physicians' clinical expertise, the results of these models can be utilized as input to make informed decisions, such as predicting hospitalizations and enhancing the overall performance of a public healthcare system.

Abstract Background Idiopathic normal pressure hydrocephalus (iNPH) is a neurological condition with gait apraxia signs from its early manifestation. Ventriculoperitoneal shunt (VPS) is a surgical procedure available for treatment. The Cerebrospinal fluid Tap Test (CSF-TT) is a quick test used as selection criterion for VPS treatment. Its predictive capacity for VPS outcomes is still sub judice. This study is aimed to test the hypothesis that wearable motion sensors provide valid measures to manage iNPH patients with gait apraxia. Methods Forty-two participants of the Bologna PRO-Hydro observational cohort study were included in the analyses. The participants performed the Timed Up and Go (TUG) and the 18 m walking test (18mW) with inertial sensors at baseline, three days after the CSF-TT, and six months after VPS. 21 instrumental variables described gait and postural transitions from TUG and 18mW recordings. Furthermore, participants were clinically assessed with scales (clinical variables). We tested the hypothesis by analysing the concurrent validity of instrumental and clinical variables, their individual- and group-level responsiveness to VPS, and their predictive validity for VPS outcomes after CSF-TT. Results The instrumental variables showed moderate to high correlation with the clinical variables. After VPS, most clinical and instrumental variables showed statistically significant improvements that reflect a reduction of apraxic features of gait. Most instrumental variables, but only one clinical variable (i.e., Tinetti POMA), had predictive value for VPS outcomes (significant adjusted R2 in the range 0.12–0.70). Conclusions These results confirm that wearable inertial sensors may represent a valid tool to complement clinical evaluation for iNPH assessment and prognosis.

Introduction: Accurately assessing people’s gait, especially in real-world conditions and in case of impaired mobility, is still a challenge due to intrinsic and extrinsic factors resulting in gait complexity. To improve the estimation of gait-related digital mobility outcomes (DMOs) in real-world scenarios, this study presents a wearable multi-sensor system (INDIP), integrating complementary sensing approaches (two plantar pressure insoles, three inertial units and two distance sensors).Methods: The INDIP technical validity was assessed against stereophotogrammetry during a laboratory experimental protocol comprising structured tests (including continuous curvilinear and rectilinear walking and steps) and a simulation of daily-life activities (including intermittent gait and short walking bouts). To evaluate its performance on various gait patterns, data were collected on 128 participants from seven cohorts: healthy young and older adults, patients with Parkinson’s disease, multiple sclerosis, chronic obstructive pulmonary disease, congestive heart failure, and proximal femur fracture. Moreover, INDIP usability was evaluated by recording 2.5-h of real-world unsupervised activity.Results and discussion: Excellent absolute agreement (ICC >0.95) and very limited mean absolute errors were observed for all cohorts and digital mobility outcomes (cadence ≤0.61 steps/min, stride length ≤0.02 m, walking speed ≤0.02 m/s) in the structured tests. Larger, but limited, errors were observed during the daily-life simulation (cadence 2.72–4.87 steps/min, stride length 0.04–0.06 m, walking speed 0.03–0.05 m/s). Neither major technical nor usability issues were declared during the 2.5-h acquisitions. Therefore, the INDIP system can be considered a valid and feasible solution to collect reference data for analyzing gait in real-world conditions.

This paper aimed to analyse the spatio-temporal patterns of the diffusion of SARS-CoV-2, the virus causing coronavirus 2019 (COVID-19, in the city of Bologna, the capital and largest city of the Emilia-Romagna Region in northern Italy. The study took place from February 1st, 2020 to November 20th, 2021 and accounted for space, sociodemographic characteristics and health conditions of the resident population. A second goal was to derive a model for the level of risk of being infected by SARS-CoV-2 and to identify and measure the place-specific factors associated with the disease and its determinants. Spatial heterogeneity was tested by comparing global Poisson regression (GPR) and local geographically weighted Poisson regression (GWPR) models. The key findings were that different city areas were impacted differently during the first three epidemic waves. The area-to-area influence was estimated to exert its effect over an area with 4.7 km radius. Spatio-temporal heterogeneity patterns were found to be independent of the sociodemographic and the clinical characteristics of the resident population. Significant single-individual risk factors for detected SARS-CoV-2 infection cases were old age, hypertension, diabetes and co-morbidities. More specifically, in the global model, the average SARS-CoV-2 infection rate decreased 0.93-fold in the 21–65 years age group compared to the >65 years age group, whereas hypertension, diabetes, and any other co-morbidities (present vs absent), increased 1.28-, 1.39- and 1.15-fold, respectively. The local GWPR model had a better fit better than GPR. Due to the global geographical distribution of the pandemic, local estimates are essential for mitigating or strengthening security measures.

Context Long-term adherence to physical activity (PA) interventions is challenging. The Lifestyle-integrated Functional Exercise programmes were adapted Lifestyle-integrated Functional Exercise (aLiFE) to include more challenging activities and a behavioural change framework, and then enhanced Lifestyle-integrated Functional Exercise (eLiFE) to be delivered using smartphones and smartwatches.Objectives To (1) compare adherence measures, (2) identify determinants of adherence and (3) assess the impact on outcome measures of a lifestyle-integrated programme.Design, setting and participants A multicentre, feasibility randomised controlled trial including participants aged 61–70 years conducted in three European cities.Interventions Six-month trainer-supported aLiFE or eLiFE compared with a control group, which received written PA advice.Outcome measures Self-reporting adherence per month using a single question and after 6-month intervention using the Exercise Adherence Rating Scale (EARS, score range 6–24). Treatment outcomes included function and disability scores (measured using the Late-Life Function and Disability Index) and sensor-derived physical behaviour complexity measure. Determinants of adherence (EARS score) were identified using linear multivariate analysis. Linear regression estimated the association of adherence on treatment outcome.Results We included 120 participants randomised to the intervention groups (aLiFE/eLiFE) (66.3±2.3 years, 53% women). The 106 participants reassessed after 6 months had a mean EARS score of 16.0±5.1. Better adherence was associated with lower number of medications taken, lower depression and lower risk of functional decline. We estimated adherence to significantly increase basic lower extremity function by 1.3 points (p

BackgroundFall risk in the elderly is a major public health issue due to the injury-related consequences and the risk of associated long-term disability. However, delivering preventive interventions in usual clinical practice still represents a challenge.AimTo evaluate the efficacy of a multiple-component combined with a multifactorial personalized intervention in reducing fall rates in a mixed population of community-dwelling elderly compared to usual care.DesignRandomized Controlled Trial (NCT03592420, clinicalTrials.gov).SettingOutpatients in two Italian centers.Population403 community-dwelling elderly at moderate-to-high fall risk, including subjects with Parkinson's Disease and stroke.MethodsAfter the randomization, the described interventions were administered to the intervention group (n = 203). The control group (n = 200) received usual care and recommendations to minimize fall risk factors. In addition, each participant received a fall diary, followed by 12 monthly phone calls. The primary endpoint was the total number of falls in each group over 12 months, while the secondary endpoints were other fall-related indicators recorded at one year. In addition, participants' functioning was assessed at baseline (T1) and 3-month (T3).Results690 falls were reported at 12 months, 48.8% in the intervention and 51.2% in the control group, with 1.66 (± 3.5) and 1.77 (± 3.2) mean falls per subject, respectively. Subjects with ≥ 1 fall and ≥2 falls were, respectively, 236 (58.6%) and 148 (36.7%). No statistically significant differences were observed between groups regarding the number of falls, the falling probability, and the time to the first fall. According to the subgroup analysis, no significant differences were reported. However, a statistically significant difference was found for the Mini-BESTest (p = 0.004) and the Fullerton Advanced Balance Scale (p = 0.006) for the intervention group, with a small effect size (Cohen's d 0.26 and 0.32, respectively), at T1 and T3 evaluations.ConclusionsThe intervention was ineffective in reducing the number of falls, the falling probability, and the time to the first fall at 12 months in a mixed population of community-dwelling elderly. A significant improvement for two balance indicators was recorded in the intervention group. Future studies are needed to explore different effects of the proposed interventions to reduce falls and consequences.

The photoplethysmographic (PPG) signal has been applied in various research fields, with promising results for its future clinical application. However, there are several sources of variability that, if not adequately controlled, can hamper its application in pervasive monitoring contexts. This study assessed and characterized the impact of several sources of variability, such as physical activity, age, sex, and health state on PPG signal quality and PPG waveform parameters (Rise Time, Pulse Amplitude, Pulse Time, Reflection Index, Delta T, and DiastolicAmplitude). We analyzed 31 24 h recordings by as many participants (19 healthy subjects and 12 oncological patients) with a wristband wearable device, selecting a set of PPG pulses labeled with three different quality levels. We implemented a Multinomial Logistic Regression (MLR) model to evaluate the impact of the aforementioned factors on PPG signal quality. We then extracted six parameters only on higher-quality PPG pulses and evaluated the influence of physical activity, age, sex, and health state on these parameters with Generalized Linear Mixed Effects Models (GLMM). We found that physical activity has a detrimental effect on PPG signal quality quality (94% of pulses with good quality when the subject is at rest vs. 9% during intense activity), and that health state affects the percentage of available PPG pulses of the best quality (at rest, 44% for healthy subjects vs. 13% for oncological patients). Most of the extracted parameters are influenced by physical activity and health state, while age significantly impacts two parameters related to arterial stiffness. These results can help expand the awareness that accurate, reliable information extracted from PPG signals can be reached by tackling and modeling different sources of inaccuracy.

This paper reports the architecture of a low-cost smart crutches system for mobile health applications. The prototype is based on a set of sensorized crutches connected to a custom Android application. Crutches were instrumented with a 6-axis inertial measurement unit, a uniaxial load cell, WiFi connectivity, and a microcontroller for data collection and processing. Crutch orientation and applied force were calibrated with a motion capture system and a force platform. Data are processed and visualized in real-time on the Android smartphone and are stored on the local memory for further offline analysis. The prototype’s architecture is reported along with the post-calibration accuracy for estimating crutch orientation (5° RMSE in dynamic conditions) and applied force (10 N RMSE). The system is a mobile-health platform enabling the design and development of real-time biofeedback applications and continuity of care scenarios, such as telemonitoring and telerehabilitation.

Fall detection has become an area of interest in recent years, as quick response to these events is critical to reduce the morbidity and mortality rate. In order to ensure proper fall detection, several technologies have been developed, including vision system, environmental detection systems, and wearable sensor based systems. However, in elderly or impaired people, it has been shown that the implementation of sensors in Assistive Devices for Walking, such as crutches or canes, can also be a promising alternative. In this work, a Support Vector Machine (SVM) based Fall Detection system is proposed, which uses the data provided by a Sensorized Tip which can be attached to different Assistive Devices for Walking (ADW). Unlike other approaches, the developed one is able to differentiate the fall of the ADW from the fall of the user. For that purpose, the developed Fall Detector uses two modules connected in series. The first one detects all falls, while the second differentiates between user and ADW falls. The proposed approach is validated in a set of experimental tests carried out by healthy volunteers that have simulated different falls. In addition, a comparative analysis is carried out by comparing the performance of the Sensorized Tip based Fall Detector and a state-of-the-art commercial accelerometer system. Results demonstrate that the proposed approach provides high Fall Detection Ratios (over 90%), similar or higher to wearable-sensor based approaches.

Walking speed is an important clinical parameter because it sums up the ability to move and predicts adverse outcomes. However, usually measured inside the clinics, it can suffer from poor ecological validity. Wearable devices such as global positioning systems (GPS) can be used to measure real-world walking speed. Still, the accuracy of GPS systems decreases in environments with poor sky visibility. This work tests a solution based on a mass-market, real-time kinematic receiver (RTK), overcoming such limitations. Seven participants walked a predefined path composed of tracts with different sky visibility. The walking speed was calculated by the RTK and compared with a reference value calculated using an odometer and a stopwatch. Despite tracts with totally obstructed visibility, the correlation between the receiver and the reference system was high (0.82 considering all tracts and 0.93 considering high-quality tracts). Similarly, a Bland Altman analysis showed a minimal detectable change of 0.12 m/s in the general case and 0.07 m/s considering only high-quality tracts. This work demonstrates the feasibility and validity of the presented device for the measurement of real-world walking speed, even in tracts with high interference. These findings pave the way for clinical use of the proposed device to measure walking speed in the real world, thus enabling digital remote monitoring of locomotor function. Several populations may benefit from similar devices, including older people at a high risk of fall, people with neurological diseases, and people following a rehabilitation intervention.

Abstract Background Gait disturbances are typical of persons with idiopathic normal pressure hydrocephalus (iNPH) without signs distinctive from other neurodegenerative and vascular conditions. Cerebrospinal fluid tap-test (CSF-TT) is expected to improve the motor performance of iNPH patients and is a prognostic indicator in their surgical management. This observational prospective study aims to determine which spatio-temporal gait parameter(s), measured during instrumented motor tests, and clinical scale(s) may provide a relevant contribution in the evaluation of motor performance pre vs. post CSF-TT on iNPH patients with and without important vascular encephalopathy. Methods Seventy-six patients (20 with an associated vascular encephalopathy) were assessed before, and 24 and 72 h after the CSF-TT by a timed up and go test (TUG) and an 18 m walking test (18 mW) instrumented using inertial sensors. Tinetti Gait, Tinetti Balance, Gait Status Scale, and Grading Scale were fulfilled before and 72 h after the CSF-TT. Stride length, cadence and total time were selected as the outcome measures. Statistical models with mixed effects were implemented to determine the relevant contribution to response variables of each quantitative gait parameter and clinical scales. Results and conclusion From baseline to 72 h post CSF-TT patients improved significantly by increasing cadence in 18 mW and TUG (on average of 1.7 and 2.4 strides/min respectively) and stride length in 18 mW (on average of 3.1 cm). A significant reduction of gait apraxia was reflected by modifications in double support duration and in coordination index. Tinetti Gait, Tinetti Balance and Gait Status Scale were able to explain part of the variability of response variables not covered by instrumental data, especially in TUG. Grading Scale revealed the highest affinity with TUG total time and cadence when considering clinical scales alone. Patients with iNPH and an associated vascular encephalopathy showed worst performances compared to pure iNPH but without statistical significance. Gait improvement following CSF-TT was comparable in the two groups. Overall these results suggest that, in order to augment CSF-TT accuracy, is key to assess the gait pattern by analyzing the main spatio-temporal parameters and set post evaluation at 72 h. Trial registration Approved by ethics committee: CE 14131 23/02/2015.

Virtual reality (VR) has been used as a complementary therapy for managing psychological and physical symptoms in cancer patients. In palliative care, the evidence about the use of VR is still inadequate. This study aims to assess the effect of an immersive VR-based intervention conducted at home on anxiety, depression, and pain over 4days and to evaluate the short-term effect of VR sessions on cancer-related symptomatology. Participants were advanced cancer patients assisted at home who were provided with a VR headset for 4days. On days one and four, anxiety and depression were measured by the Hospital Anxiety and Depression Scale (HADS) and pain by the Brief Pain Inventory (BPI). Before and after each VR session, symptoms were collected by the Edmonton Symptom Assessment Scale (ESAS). Participants wore a smart wristband measuring physiological signals associated with pain, anxiety, and depression. Fourteen patients (mean age 47.2±14.2years) were recruited. Anxiety, depression (HADS), and pain (BPI) did not change significantly between days one and four. However, the ESAS items related to pain, depression, anxiety, well-being, and shortness of breath collected immediately after the VR sessions showed a significant improvement (p

This paper describes the second part of the PASSO (Parkinson smart sensory cues for older users) project, which designs and tests an innovative haptic biofeedback system based on a wireless body sensor network using a smartphone and different smartwatches specifically designed to rehabilitate postural disturbances in persons with Parkinson’s disease. According to the scientific literature on the use of smart devices to transmit sensory cues, vibrotactile feedback (particularly on the trunk) seems promising for improving people’s gait and posture performance; they have been used in different environments and are well accepted by users. In the PASSO project, we designed and developed a wearable device and a related system to transmit vibrations to a person’s body to improve posture and combat impairments like Pisa syndrome and camptocormia. Specifically, this paper describes the methodologies and strategies used to design, develop, and test wearable prototypes and the mHealth system. The results allowed a multidisciplinary comparison among the solutions, which led to prototypes with a high degree of usability, wearability, accessibility, and effectiveness. This mHealth system is now being used in pilot trials with subjects with Parkinson’s disease to verify its feasibility among patients.

Photoplethysmographic (PPG) signals are mainly employed for heart rate estimation but are also fascinating candidates in the search for cardiovascular biomarkers. However, their high susceptibility to motion artifacts can lower their morphological quality and, hence, affect the reliability of the extracted information. Low reliability is particularly relevant when signals are recorded in a real-world context, during daily life activities. We aim to develop two classifiers to identify PPG pulses suitable for heart rate estimation (Basic-quality classifier) and morphological analysis (High-quality classifier). We collected wrist PPG data from 31 participants over a 24 h period. We defined four activity ranges based on accelerometer data and randomly selected an equal number of PPG pulses from each range to train and test the classifiers. Independent raters labeled the pulses into three quality levels. Nineteen features, including nine novel features, were extracted from PPG pulses and accelerometer signals. We conducted ten-fold cross-validation on the training set (70%) to optimize hyperparameters of five machine learning algorithms and a neural network, and the remaining 30% was used to test the algorithms. Performances were evaluated using the full features and a reduced set, obtained downstream of feature selection methods. Best performances for both Basic- and High-quality classifiers were achieved using a Support Vector Machine (Acc: 0.96 and 0.97, respectively). Both classifiers outperformed comparable state-of-the-art classifiers. Implementing automatic signal quality assessment methods is essential to improve the reliability of PPG parameters and broaden their applicability in a real-world context.

Background: Behavioral change is the key to alter individuals' lifestyle from sedentary to active. The aim was to assess the feasibility of delivering a Lifestyle-integrated Functional Exercise programme and evaluate the delivery of the intervention by use of digital technology (eLiFE) to prevent functional decline in 61–70 year-old adults.Methods: This multicentre, feasibility randomized controlled trial was run in three countries (Norway, Germany, and the Netherlands). Out of 7,500 potential participants, 926 seniors (12%) were screened and 180 participants randomized to eLiFE (n = 61), aLiFE (n = 59), and control group (n = 60). eLiFE participants used an application on smartphones and smartwatches while aLiFE participants used traditional paper-based versions of the same lifestyle-integrated exercise intervention. Participants were followed for 12 months, with assessments at baseline, after a 6 month active trainer-supported intervention, and after a further 6 months of unsupervised continuation of the programme.Results: At 6 months, 87% of participants completed post-test, and 77% completed the final assessment at 12 months. Participants were willing to be part of the programme, with compliance and reported adherence relatively high. Despite small errors during start-up in the technological component, intervention delivery by use of technology appeared acceptable. No serious adverse events were related to the interventions. All groups improved regarding clinical outcomes over time, and complexity metrics show potential as outcome measure in young seniors.Conclusion: This feasibility RCT provides evidence that an ICT-based lifestyle-integrated exercise intervention, focusing on behavioral change, is feasible and safe for young seniors.Clinical Trial Registration:ClinicalTrials.gov, identifier: NCT03065088. Registered on 14 February 2017.

Physical activity has a strong influence on mental and physical health and is essential in healthy ageing and wellbeing for the ever-growing elderly population. Wearable sensors can provide a reliable and economical measure of activities of daily living (ADLs) by capturing movements through, e.g., accelerometers and gyroscopes. This study explores the potential of using classical machine learning and deep learning approaches to classify the most common ADLs: walking, sitting, standing, and lying. We validate the results on the ADAPT dataset, the most detailed dataset to date of inertial sensor data, synchronised with high frame-rate video labelled data recorded in a free-living environment from older adults living independently. The findings suggest that both approaches can accurately classify ADLs, showing high potential in profiling ADL patterns of the elderly population in free-living conditions. In particular, both long short-term memory (LSTM) networks and Support Vector Machines combined with ReliefF feature selection performed equally well, achieving around 97% F-score in profiling ADLs.

Wearable sensing technology is a new way to deliver corrective feedback. It is highly applicable to gait rehabilitation for persons with Parkinson’s disease (PD) because feedback potentially engages spared neural function. Our study characterizes participants’ motor adaptation to feedback signaling a deviation from their normal cadence during prolonged walking, providing insight into possible novel therapeutic devices for gait re-training. Twenty-eight persons with PD (15 with freezing, 13 without) and 13 age-matched healthy elderly (HE) walked for two 30-minute sessions. When their cadence varied, they heard either intelligent cueing (IntCue: bouts of ten beats indicating normal cadence) or intelligent feedback (IntFB: verbal instruction to increase or decrease cadence). We created a model that compares the effectiveness of the two conditions by quantifying the number of steps needed to return to the target cadence for every deviation. The model fits the short-term motor responses to the external step inputs (collected with wearable sensors). We found some significant difference in motor adaptation among groups and subgroups for the IntCue condition only. Both conditions were instead able to identify different types of responders among persons with PD, although showing opposite trends in their speed of adaptation. Increasing rather than decreasing the pace appeared to be more difficult for both groups. In fact, under IntFB the PD group required about seven steps to increase their cadence, whereas they only needed about three steps to decrease their cadence. However, it is important to note that this difference was not significant; perhaps future work could include more participants and/or more sessions, increasing the total number of deviations for analysis. Notably, a significant negative correlation, r = −0.57 (p-value = 0.008), was found between speed of adaptation and number of deviations during IntCue, but not during IntFB, suggesting that, for people who struggle with gait, such as those with PD, verbal instructions rather than metronome beats might be more effective at restoring normal cadence. Clinicians and biofeedback developers designing novel therapeutic devices could apply our findings to determine the optimal timing for corrective feedback, optimizing gait rehabilitation while minimizing the risk of cue-dependency.

Falling is a significant health problem. Fall detection, to alert for medical attention, has been gaining increasing attention. Still, most of the existing studies use falls simulated in a laboratory environment to test the obtained performance. We analyzed the acceleration signals recorded by an inertial sensor on the lower back during 143 real-world falls (the most extensive collection to date) from the FARSEEING repository. Such data were obtained from continuous real-world monitoring of subjects with a moderate-to-high risk of falling. We designed and tested fall detection algorithms using features inspired by a multiphase fall model and a machine learning approach. The obtained results suggest that algorithms can learn effectively from features extracted from a multiphase fall model, consistently overperforming more conventional features. The most promising method (support vector machines and features from the multiphase fall model) obtained a sensitivity higher than 80%, a false alarm rate per hour of 0.56, and an F-measure of 64.6%. The reported results and methodologies represent an advancement of knowledge on real-world fall detection and suggest useful metrics for characterizing fall detection systems for real-world use.

Freezing of gait (FOG) is a disabling symptom that is common among patients with advanced Parkinson’s disease (PD). External cues such as rhythmic auditory stimulation can help PD patients experiencing freezing to resume walking. Wearable systems for automatic freezing detection have been recently developed. However, these systems detect a FOG episode after it has happened. Instead, in this study, a new approach for the prediction of FOG (before it actually happens) is presented. Prediction of FOG might enable preventive cueing, reducing the likelihood that FOG will occur. Moreover, understanding the causes and circumstances of FOG is still an open research problem. Hence, a quantitative characterization of movement patterns just before FOG (the pre-FOG phase) is of great importance. In this study, wearable inertial sensors were used to identify and quantify the characteristics of gait during the pre-FOG phase and compare them with the characteristics of gait that do not precede FOG. The hypothesis of this study is based on the threshold-based model of FOG, which suggests that before FOG occurs, there is a degradation of the gait pattern. Eleven PD subjects were analyzed. Six features extracted from movement signals recorded by inertial sensors showed significant differences between gait and pre-FOG. A classification algorithm was developed in order to test if it is feasible to predict FOG (i.e., detect it before it happens). The aim of the classification procedure was to identify the pre-FOG phase. Results confirm that there is a degradation of gait occurring before freezing. Results also provide preliminary evidence on the feasibility of creating an automatic algorithm to predict FOG. Although some limitations are present, this study shows promising findings for characterizing and identifying pre-FOG patterns, another step toward a better understanding, prediction, and prevention of this disabling symptom.

The One-Leg Stance (OLS) test is a widely adopted tool for the clinical assessment of balance in the elderly and in subjects with neurological disorders. It was previously showed that the ability to control anticipatory postural adjustments (APAs) prior to lifting one leg is significantly impaired by idiopathic Parkinson’s disease (iPD). However, it is not known how APAs are affected by other types of parkinsonism, such as frontal gait disorders (FGD). In this study, an instrumented OLS test based on wearable inertial sensors is proposed to investigate both the initial anticipatory phase and the subsequent unipedal balance. The sensitivity and the validity of the test have been evaluated. Twenty-five subjects with iPD presenting freezing of gait (FOG), 33 with iPD without FOG, 13 with FGD, and 32 healthy elderly controls were recruited. All subjects wore three inertial sensors positioned on the posterior trunk (L4–L5), and on the left and right frontal face of the tibias. Participants were asked to lift a foot and stand on a single leg as long as possible with eyes open, as proposed by the mini-BESTest. Temporal parameters and trunk acceleration were extracted from sensors and compared among groups. The results showed that, regarding the anticipatory phase, the peak of mediolateral trunk acceleration was significantly reduced compared to healthy controls (p 0.74), demonstrating the method’s validity. Our findings support the validity of the proposed method for assessing the OLS test and its sensitivity in distinguishing among the tested groups. The instrumented test discriminated between healthy controls and people with parkinsonism and among the three groups with parkinsonism. The objective characterization of the initial anticipatory phase represents an interesting improvement compared to most clinical OLS tests.

Falls are a major cause of injuries and deaths in older adults. Even when no injury occurs, about half of all older adults who fall are unable to get up without assistance. The extended period of lying on the floor often leads to medical complications, including muscle damage, dehydration, anxiety and fear of falling. Wearable sensor systems incorporating accelerometers and/or gyroscopes are designed to prevent long lies by automatically detecting and alerting care providers to the occurrence of a fall. Research groups have reported up to 100% accuracy in detecting falls in experimental settings. However, there is a lack of studies examining accuracy in the real-world setting. In this study, we examined the accuracy of a fall detection system based on real-world fall and non-fall data sets. Five young adults and 19 older adults went about their daily activities while wearing tri-axial accelerometers. Older adults experienced 10 unanticipated falls during the data collection. Approximately 400 hours of activities of daily living were recorded. We employed a machine learning algorithm, Support Vector Machine (SVM) classifier, to identify falls and non-fall events. We found that our system was able to detect 8 out of the 10 falls in older adults using signals from a single accelerometer (waist or sternum). Furthermore, our system did not report any false alarm during approximately 28.5 hours of recorded data from young adults. However, with older adults, the false positive rate among individuals ranged from 0 to 0.3 false alarms per hour. While our system showed higher fall detection and substantially lower false positive rate than the existing fall detection systems, there is a need for continuous efforts to collect real-world data within the target population to perform fall validation studies for fall detection systems on bigger real-world fall and non-fall datasets.

Physical capability (PC) is conventionally evaluated through performance-based clinical assessments. We aimed to transform a battery of sensor-based functional tests into a clinically applicable assessment tool. We used Exploratory Factor Analysis (EFA) to uncover the underlying latent structure within sensor-based measures obtained in a population-based study. Three hundred four community-dwelling older adults (163 females, 80.9 ± 6.4 years), underwent three functional tests (Quiet Stand, QS, 7-meter Walk, 7MW and Chair Stand, CST) wearing a smartphone at the lower back. Instrumented tests provided 73 sensor-based measures, out of which EFA identified a fifteen-factor model. A priori knowledge and the associations with health-related measures supported the functional interpretation and construct validity analysis of the factors, and provided the basis for developing a conceptual model of PC. For example, the “Walking Impairment„ domain obtained from the 7MW test was significantly associated with measures of leg muscle power, gait speed, and overall lower extremity function. To the best of our knowledge, this is the first time that a battery of functional tests, instrumented through a smartphone, is used for outlining a sensor-based conceptual model, which could be suitable for assessing PC in older adults and tracking its changes over time.

In this work, a flexible and extensive digital platform for Smart Homes is presented, exploiting the most advanced technologies of the Internet of Things, such as Radio Frequency Identification, wearable electronics, Wireless Sensor Networks, and Artificial Intelligence. Thus, the main novelty of the paper is the system-level description of the platform flexibility allowing the interoperability of different smart devices. This research was developed within the framework of the operative project HABITAT (Home Assistance Based on the Internet of Things for the Autonomy of Everybody), aiming at developing smart devices to support elderly people both in their own houses and in retirement homes, and embedding them in everyday life objects, thus reducing the expenses for healthcare due to the lower need for personal assistance, and providing a better life quality to the elderly users.

Assessment of physical performance by standard clinical tests such as the 30-sec Chair Stand (30CST) and the Timed Up and Go (TUG) may allow early detection of functional decline, even in high-functioning populations, and facilitate preventive interventions. Inertial sensors are emerging to obtain instrumented measures that can provide subtle details regarding the quality of the movement while performing such tests. We compared standard clinical with instrumented measures of physical performance in their ability to distinguish between high and very high functional status, stratified by the Late-Life Function and Disability Instrument (LLFDI). We assessed 160 participants from the PreventIT study (66.3 ± 2.4 years, 87 females, median LLFDI 72.31, range: 44.33–100) performing the 30CST and TUG while a smartphone was attached to their lower back. The number of 30CST repetitions and the stopwatch-based TUG duration were recorded. Instrumented features were computed from the smartphone embedded inertial sensors. Four logistic regression models were fitted and the Areas Under the Receiver Operating Curve (AUC) were calculated and compared using the DeLong test. Standard clinical and instrumented measures of 30CST both showed equal moderate discriminative ability of 0.68 (95%CI 0.60–0.76), p = 0.97. Similarly, for TUG: AUC was 0.68 (95%CI 0.60–0.77) and 0.65 (95%CI 0.56–0.73), respectively, p = 0.26. In conclusion, both clinical and instrumented measures, recorded through a smartphone, can discriminate early functional decline in healthy adults aged 61–70 years.

Difficulty with turning is a major contributor to mobility disability and falls in people with movement disorders, such as Parkinson’s disease (PD). Turning often results in freezing and/or falling in patients with PD. However, asking a patient to execute a turn in the clinic often does not reveal their impairments. Continuous monitoring of turning with wearable sensors during spontaneous daily activities may help clinicians and patients determine who is at risk of falls and could benefit from preventative interventions. In this study, we show that continuous monitoring of natural turning with wearable sensors during daily activities inside and outside the home is feasible for people with PD and elderly people. We developed an algorithm to detect and characterize turns during gait, using wearable inertial sensors. First, we validate the turning algorithm in the laboratory against a Motion Analysis system and against a video analysis of 21 PD patients and 19 control (CT) subjects wearing an inertial sensor on the pelvis. Compared to Motion Analysis and video, the algorithm maintained a sensitivity of 0.90 and 0.76 and a specificity of 0.75 and 0.65, respectively. Second, we apply the turning algorithm to data collected in the home from 12 PD and 18 CT subjects. The algorithm successfully detects turn characteristics, and the results show that, compared to controls, PD subjects tend to take shorter turns with smaller turn angles and more steps. Furthermore, PD subjects show more variability in all turn metrics throughout the day and the week.

BACKGROUND:Falls are a common, serious threat to the health and self-confidence of the elderly. Assessment of fall risk is an important aspect of effective fall prevention programs. OBJECTIVES AND METHODS:In order to test whether it is possible to outperform current prognostic tools for falls, we analyzed 1010 variables pertaining to mobility collected from 976 elderly subjects (InCHIANTI study). We trained and validated a data-driven model that issues probabilistic predictions about future falls. We benchmarked the model against other fall risk indicators: history of falls, gait speed, Short Physical Performance Battery (Guralnik et al. 1994), and the literature-based fall risk assessment tool FRAT-up (Cattelani et al. 2015). Parsimony in the number of variables included in a tool is often considered a proxy for ease of administration. We studied how constraints on the number of variables affect predictive accuracy. RESULTS:The proposed model and FRAT-up both attained the same discriminative ability; the area under the Receiver Operating Characteristic (ROC) curve (AUC) for multiple falls was 0.71. They outperformed the other risk scores, which reported AUCs for multiple falls between 0.64 and 0.65. Thus, it appears that both data-driven and literature-based approaches are better at estimating fall risk than commonly used fall risk indicators. The accuracy-parsimony analysis revealed that tools with a small number of predictors (~1-5) were suboptimal. Increasing the number of variables improved the predictive accuracy, reaching a plateau at ~20-30, which we can consider as the best trade-off between accuracy and parsimony. Obtaining the values of these ~20-30 variables does not compromise usability, since they are usually available in comprehensive geriatric assessments.

The popularity of using wearable inertial sensors for physical activity classification has dramatically increased in the last decade due to their versatility, low form factor, and low power requirements. Consequently, various systems have been developed to automatically classify daily life activities. However, the scope and implementation of such systems is limited to laboratory-based investigations. Furthermore, these systems are not directly comparable, due to the large diversity in their design (e.g., number of sensors, placement of sensors, data collection environments, data processing techniques, features set, classifiers, cross-validation methods). Hence, the aim of this study is to propose a fair and unbiased benchmark for the field-based validation of three existing systems, highlighting the gap between laboratory and real-life conditions. For this purpose, three representative state-of-the-art systems are chosen and implemented to classify the physical activities of twenty older subjects (76.4 ± 5.6 years). The performance in classifying four basic activities of daily life (sitting, standing, walking, and lying) is analyzed in controlled and free living conditions. To observe the performance of laboratory-based systems in field-based conditions, we trained the activity classification systems using data recorded in a laboratory environment and tested them in real-life conditions in the field. The findings show that the performance of all systems trained with data in the laboratory setting highly deteriorates when tested in real-life conditions, thus highlighting the need to train and test the classification systems in the real-life setting. Moreover, we tested the sensitivity of chosen systems to window size (from 1 s to 10 s) suggesting that overall accuracy decreases with increasing window size. Finally, to evaluate the impact of the number of sensors on the performance, chosen systems are modified considering only the sensing unit worn at the lower back. The results, similarly to the multi-sensor setup, indicate substantial degradation of the performance when laboratory-trained systems are tested in the real-life setting. This degradation is higher than in the multi-sensor setup. Still, the performance provided by the single-sensor approach, when trained and tested with real data, can be acceptable (with an accuracy above 80%).

BackgroundThe search for disease-modifying treatments for Parkinson's disease advances, however necessary markers for early detection of the disease are still lacking. There is compelling evidence that changes of postural stability occur at very early clinical stages of Parkinson's disease, making it tempting to speculate that changes in sway performance may even occur at a prodromal stage, and may have the potential to serve as a prodromal marker for the disease.Methodology/principal findingsBalance performance was tested in 20 individuals with an increased risk of Parkinson's disease, 12 Parkinson's disease patients and 14 controls using a cross-sectional approach. All individuals were 50 years or older. Investigated groups were similar with respect to age, gender, and height. An accelerometer at the centre of mass at the lower spine quantified sway during quiet semitandem stance with eyes open and closed, as well as with and without foam. With increasing task difficulty, individuals with an increased risk of Parkinson's disease showed an increased variability of trunk acceleration and a decrease of smoothness of sway, compared to both other groups. These differences reached significance in the most challenging condition, i.e. the eyes closed with foam condition.Conclusions/significanceIndividuals with an increased risk of Parkinson's disease have subtle signs of a balance deficit under most challenging conditions. This preliminary finding should motivate further studies on sway performance in individuals with an increased risk of Parkinson's disease, to evaluate the potential of this symptom to serve as a biological marker for prodromal Parkinson's disease.

Despite extensive preventive efforts, falls continue to be a major source of morbidity and mortality among elderly. Real-time detection of falls and their urgent communication to a telecare center may enable rapid medical assistance, thus increasing the sense of security of the elderly and reducing some of the negative consequences of falls. Many different approaches have been explored to automatically detect a fall using inertial sensors. Although previously published algorithms report high sensitivity (SE) and high specificity (SP), they have usually been tested on simulated falls performed by healthy volunteers. We recently collected acceleration data during a number of real-world falls among a patient population with a high-fall-risk as part of the SensAction-AAL European project. The aim of the present study is to benchmark the performance of thirteen published fall-detection algorithms when they are applied to the database of 29 real-world falls. To the best of our knowledge, this is the first systematic comparison of fall detection algorithms tested on real-world falls. We found that the SP average of the thirteen algorithms, was (mean ± std) 83.0% ± 30.3% (maximum value = 98%). The SE was considerably lower (SE = 57.0% ± 27.3%, maximum value = 82.8%), much lower than the values obtained on simulated falls. The number of false alarms generated by the algorithms during 1-day monitoring of three representative fallers ranged from 3 to 85. The factors that affect the performance of the published algorithms, when they are applied to the real-world falls, are also discussed. These findings indicate the importance of testing fall-detection algorithms in real-life conditions in order to produce more effective automated alarm systems with higher acceptance. Further, the present results support the idea that a large, shared real-world fall database could, potentially, provide an enhanced understanding of the fall process and the information needed to design and evaluate a high-performance fall detector.