Search

Among Parkinson’s disease (PD) symptoms, freezing of gait (FoG) is one of the most debilitating. To assess FoG, current clinical practice mostly employs repeated evaluations over weeks and months based on questionnaires, which may not accurately map the severity of this symptom. The use of a non-invasive system to monitor the activities of daily living (ADL) and the PD symptoms experienced by patients throughout the day could provide a more accurate and objective evaluation of FoG in order to better understand the evolution of the disease and allow for a more informed decision-making process in making adjustments to the patient’s treatment plan. This paper presents a new algorithm to detect FoG with a machine learning approach based on Support Vector Machines (SVM) and a single tri-axial accelerometer worn at the waist. The method is evaluated through the acceleration signals in an outpatient setting gathered from 21 PD patients at their home and evaluated under two different conditions: first, a generic model is tested by using a leave-one-out approach and, second, a personalised model that also uses part of the dataset from each patient. Results show a significant improvement in the accuracy of the personalised model compared to the generic model, showing enhancement in the specificity and sensitivity geometric mean (GM) of 7.2%. Furthermore, the SVM approach adopted has been compared to the most comprehensive FoG detection method currently in use (referred to as MBFA in this paper). Results of our novel generic method provide an enhancement of 11.2% in the GM compared to the MBFA generic model and, in the case of the personalised model, a 10% of improvement with respect to the MBFA personalised model. Thus, our results show that a machine learning approach can be used to monitor FoG during the daily life of PD patients and, furthermore, personalised models for FoG detection can be used to improve monitoring accuracy. [ABSTRACT FROM AUTHOR]

Aims: The study aims were to evaluate the validity of two commercially available swimming activity monitors for quantifying temporal and kinematic swimming variables. Methods: Ten national level swimmers (5 male, 5 female; 15.3±1.3years; 164.8±12.9cm; 62.4±11.1kg; 425±66 FINA points) completed a set protocol comprising 1,500m of swimming involving all four competitive swimming strokes. Swimmers wore the Finis Swimsense and the Garmin Swim activity monitors throughout. The devices automatically identified stroke type, swim distance, lap time, stroke count, stroke rate, stroke length and average speed. Video recordings were also obtained and used as a criterion measure to evaluate performance. Results: A significant positive correlation was found between the monitors and video for the identification of each of the four swim strokes (Garmin: X2 (3) = 31.292, p<0.05; Finis:X2 (3) = 33.004, p<0.05). No significant differences were found for swim distance measurements. Swimming laps performed in the middle of a swimming interval showed no significant difference from the criterion (Garmin: bias -0.065, 95% confidence intervals -3.828–6.920; Finis bias -0.02, 95% confidence intervals -3.095–3.142). However laps performed at the beginning and end of an interval were not as accurately timed. Additionally, a statistical difference was found for stroke count measurements in all but two occasions (p<0.05). These differences affect the accuracy of stroke rate, stroke length and average speed scores reported by the monitors, as all of these are derived from lap times and stroke counts. Conclusions: Both monitors were found to operate with a relatively similar performance level and appear suited for recreational use. However, issues with feature detection accuracy may be related to individual variances in stroke technique. It is reasonable to expect that this level of error would increase when the devices are used by recreational swimmers rather than elite swimmers. Further development to improve accuracy of feature detection algorithms, specifically for lap time and stroke count, would also increase their suitability within competitive settings. [ABSTRACT FROM AUTHOR]

Introduction: Physical activity is an essential aspect of a healthy lifestyle for both physical and mental health states. As step count is one of the most utilized measures for quantifying physical activity it is important that activity-monitoring devices be both sensitive and specific in recording actual steps taken and disregard non-stepping body movements. The objective of this study was to assess the specificity of five activity monitors during a variety of prescribed non-stepping activities. Methods: Participants wore five activity monitors simultaneously for a variety of prescribed activities including deskwork, taking an elevator, taking a bus journey, automobile driving, washing and drying dishes; functional reaching task; indoor cycling; outdoor cycling; and indoor rowing. Each task was carried out for either a specific duration of time or over a specific distance. Activity monitors tested were the ActivPAL micro™, NL-2000™ pedometer, Withings Smart Activity Monitor Tracker (Pulse O2)™, Fitbit One™ and Jawbone UP™. Participants were video-recorded while carrying out the prescribed activities and the false positive step count registered on each activity monitor was obtained and compared to the video. Results: All activity monitors registered a significant number of false positive steps per minute during one or more of the prescribed activities. The Withings™ activity performed best, registering a significant number of false positive steps per minute during the outdoor cycling activity only (P = 0.025). The Jawbone™ registered a significant number of false positive steps during the functional reaching task and while washing and drying dishes, which involved arm and hand movement (P < 0.01 for both). The ActivPAL™ registered a significant number of false positive steps during the cycling exercises (P < 0.001 for both). Conclusion: As a number of false positive steps were registered on the activity monitors during the non-stepping activities, the authors conclude that non-stepping physical activities can result in the false detection of steps. This can negatively affect the quantification of physical activity with regard to step count as an output. The Withings™ activity monitor performed best with regard to specificity during the activities of daily living tested. [ABSTRACT FROM AUTHOR]

Introduction: Physical activity is a vitally important part of a healthy lifestyle, and is of major benefit to both physical and mental health. A daily step count of 10,000 steps is recommended globally to achieve an appropriate level of physical activity. Accurate quantification of physical activity during conditions reflecting those needed to achieve the recommended daily step count of 10,000 steps is essential. As such, we aimed to assess four commercial activity monitors for their sensitivity/accuracy in a prescribed walking route that reflects a range of surfaces that would typically be used to achieve the recommended daily step count, in two types of footwear expected to be used throughout the day when aiming to achieve the recommended daily step count, and in a timeframe required to do so. Methods: Four commercial activity monitors were worn simultaneously by participants (n = 15) during a prescribed walking route reflective of surfaces typically encountered while achieving the daily recommended 10,000 steps. Activity monitors tested were the Garmin Vivofit ™, New Lifestyles’ NL-2000 ™ pedometer, Withings Smart Activity Monitor Tracker (Pulse O2) ™, and Fitbit One ™. Results: All activity monitors tested were accurate in their step detection over the variety of different surfaces tested (natural lawn grass, gravel, ceramic tile, tarmacadam/asphalt, linoleum), when wearing both running shoes and hard-soled dress shoes. Conclusion: All activity monitors tested were accurate in their step detection sensitivity and are valid monitors for physical activity quantification over the variety of different surfaces tested, when wearing both running shoes and hard-soled dress shoes, and over a timeframe necessary for accumulating the recommended daily step count of 10,000 steps. However, it is important to consider the accuracy of activity monitors, particularly when physical activity in the form of stepping activities is prescribed as an intervention in the treatment or prevention of a disease state. [ABSTRACT FROM AUTHOR]