Using Wearable Sensors and Machine Learning to Automatically Detect Freezing of Gait during a FOG-Provoking Test.

Freezing of gait (FOG) is a debilitating motor phenomenon that is common among individuals with advanced Parkinson's disease. Objective and sensitive measures are needed to better quantify FOG. The present work addresses this need by leveraging wearable devices and machine-learning methods to develop and evaluate automated detection of FOG and quantification of its severity. Seventy-one subjects with FOG completed a FOG-provoking test while wearing three wearable sensors (lower back and each ankle). Subjects were videotaped before (OFF state) and after (ON state) they took their antiparkinsonian medications. Annotations of the videos provided the "ground-truth" for FOG detection. A leave-one-patient-out validation process with a training set of 57 subjects resulted in 84.1% sensitivity, 83.4% specificity, and 85.0% accuracy for FOG detection. Similar results were seen in an independent test set (data from 14 other subjects). Two derived outcomes, percent time frozen and number of FOG episodes, were associated with self-report of FOG. Bother derived-metrics were higher in the OFF state than in the ON state and in the most challenging level of the FOG-provoking test, compared to the least challenging level. These results suggest that this automated machine-learning approach can objectively assess FOG and that its outcomes are responsive to therapeutic interventions.

Advantages of timing the duration of a freezing of gait-provoking test in individuals with Parkinson's disease.

Evaluating freezing of gait (FOG) and quantifying its severity in patients with Parkinson's disease (PD) is challenging; objective assessment is not sufficiently established. We aimed to improve the ability to objectively evaluate FOG severity by investigating the value of measuring the duration of the test and its components. Seventy-one patients with PD and FOG completed a previously validated FOG-provoking test. The test was performed under three conditions: (1) usual, single task; (2) dual task (walking while carrying a tray); and (3) triple task (walking while holding a tray and subtracting 7 s). FOG and festination were scored using standard procedures. We evaluated effect sizes based on both the original scoring and the test duration for the motor-cognitive cost and before and after anti-Parkinsonian medication intake. Additionally, video recording of the test and total time frozen were measured. As expected, the original test score and the test duration increased across the three conditions of the task and were higher in OFF than in the ON-medication state (p < 0.036). For motor-cognitive cost, higher effect sizes were observed for the test duration of each condition, compared to the original scoring in OFF state (0.85 vs. 0.68, respectively). Change in effect size category was more pronounced in the ON state vs. OFF (0.87 vs. 0.55, respectively). Test duration was the only independent predictor for the self-report of FOG severity and the total time frozen during the test. These findings suggest that quantifying the duration of each condition of the FOG-provoking test improves its sensitivity to medications and task complexity. Timing can be used to provide immediate, objective feedback of freezing severity, and a clear interpretation of a patient's performance.

Using the capabilities approach to understand inequality in primary health-care services for people with severe mental illness.

BACKGROUND: Epidemiological studies show disparities in the provision of physical health-care for people with severe mental illness. This observation includes countries with universal health insurance. However, there is limited in-depth data regarding the barriers preventing equality of physical health-care provision for this population. This study applied the capabilities approach to examine the interface between general practitioners and patients with severe mental illness. The capabilities approach provides a framework for health status which conceptualizes the internal and external factors relating to the available options (capabilities) and subsequent health outcomes (functioning). METHODS: Semi-structured in-depth interviews were conducted with 10 general practitioners and 15 patients with severe mental illness, and then thematically analyzed. RESULTS: We identified factors manifesting across three levels: personal, relational-societal, and organizational. At the personal level, the utilization of physical health services was impaired by the exacerbation of psychiatric symptoms. At the relational level, both patients and physicians described the importance of a long-term and trusting relationship, and provided examples demonstrating the implications of relational ruptures. Finally, two structural-level impediments were described by the physicians: the absence of continuous monitoring of patients with severe mental illness, and the shortfall in psychosocial interventions. CONCLUSION: The capability approach facilitated the identification of barriers preventing equitable health-care provision for patients with severe mental illness. Based on our findings, we propose a number of practical suggestions to improve physical health-care for this population: 1. A proactive approach in monitoring patients' health status and utilization of services. 2. Acknowledgment of people with severe mental illness as a vulnerable population at risk, that need increased time for physician-patient consultations. 3. Training and support for general practitioners. 4. Increase collaboration between general practitioners and mental-health professionals. 5. Educational programs for health professionals to reduce prejudice against people with severe mental illness.