A Device for Local or Remote Monitoring of Hand Rehabilitation Sessions for Rheumatic Patients

Supervised classification of bradykinesia in Parkinson's disease from smartphone videos

BACKGROUND

Slowness of movement, known as bradykinesia, is the core clinical sign of Parkinson's and fundamental to its diagnosis. Clinicians commonly assess bradykinesia by making a visual judgement of the patient tapping finger and thumb together repetitively. However, inter-rater agreement of expert assessments has been shown to be only moderate, at best.

AIM

We propose a low-cost, contactless system using smartphone videos to automatically determine the presence of bradykinesia.

METHODS

We collected 70 videos of finger-tap assessments in a clinical setting (40 Parkinson's hands, 30 control hands). Two clinical experts in Parkinson's, blinded to the diagnosis, evaluated the videos to give a grade of bradykinesia severity between 0 and 4 using the Unified Pakinson's Disease Rating Scale (UPDRS). We developed a computer vision approach that identifies regions related to hand motion and extracts clinically-relevant features. Dimensionality reduction was undertaken using principal component analysis before input to classification models (Naïve Bayes, Logistic Regression, Support Vector Machine) to predict no/slight bradykinesia (UPDRS = 0-1) or mild/moderate/severe bradykinesia (UPDRS = 2-4), and presence or absence of Parkinson's diagnosis.

RESULTS

A Support Vector Machine with radial basis function kernels predicted presence of mild/moderate/severe bradykinesia with an estimated test accuracy of 0.8. A Naïve Bayes model predicted the presence of Parkinson's disease with estimated test accuracy 0.67.

CONCLUSION

The method described here presents an approach for predicting bradykinesia from videos of finger-tapping tests. The method is robust to lighting conditions and camera positioning. On a set of pilot data, accuracy of bradykinesia prediction is comparable to that recorded by blinded human experts.

Home-based telerehabilitation software systems for remote supervising: a systematic review

OBJECTIVES

In the past decade, with the ever-increasing growth of information and communication technologies, telerehabilitation, especially home-based rehabilitation (HBR), has been widely considered by researchers. Many software systems are developed to address HBR programs, which includes various functionalities. The aim of this study is to review the functional features of these systems designed for remote supervising of HBR programs.

METHODS

Scopus, PubMed, EMBASE, ISI Web of Science, Cochrane Library, IEEE Xplore Digital Library, and ProQuest databases were searched for English-language articles published between January 2008 and February 2018 to retrieve studies reported an home-based telerehabilitation software system aiming to remotely supervise HBR program.

RESULTS

A total of fifty studies that reported twenty-two unique systems met the inclusion criteria. Various functional features were identified including but not limited to exercise plan management, report/statistics generating, patient education, and task scheduling. Disorders or diseases addressed by these systems could mainly be grouped into five categories: musculoskeletal, neurological, respiratory, cardiovascular, and other health-related problems. Usability and acceptability, and clinical/patient outcomes were the most reported outcomes and data analysis was used by the majority of included studies to measure the outcomes.

CONCLUSIONS

Systems developed for supervising of HBR program are diverse. However, preliminary results of this review revealed that these systems share more or less common functionalities. However, further research is needed to determine the requirements, structure, and effectiveness of these systems in real-life settings.

Robust and Accurate Capture of Human Joint Pose Using an Inertial Sensor

Wearable inertial measurement units (IMU) measuring acceleration, earth magnetic field, and gyroscopic measurements can be considered for capturing human skeletal postures in real time. Number of movement disorders require accurate and robust estimation of the human joint pose. Though these movements are inherently slow, the accuracy of estimation is vital as many subtle moment patterns, such as tremor are useful to capture under many assessments scenarios. Also, as the end user is a patient with movement disabilities, the practical wearability aspects impose stringent requirements such as the use of minimal number of sensors as well as positioning them in conformable areas of the human body; particularly for longer term monitoring. Estimating skeletal and limb orientations to describe human posture dynamically via model-based approaches poses numerous challenges. In this paper, we convey that the use of measurement conversion ideas-a representation signifying a linear characterization of an inherently non linear estimation problem, pragmatically improves the overall estimation of the limb orientation. A quaternion, as opposed to the Euler angle-based approach is adopted to avoid Gimbal lock scenarios. We also lay a systematic basis for quaternion normalization, typically performed in the pre-filtering stage, by introducing an optimization-based mathematical justification. A robust version of the extended Kalman filter is configured to amalgamate the underlying ideas in enhancing the overall system performance while providing a structured and a comprehensive approach to IMU-based real time human pose estimation problem, particularly in a movement disability capture context.

Telemedicine for patients with rheumatic diseases: Systematic review and proposal for research agenda

OBJECTIVE

To systematically review the scientific literature regarding tele-rheumatology and draw conclusions about feasibility, effectiveness, and patient satisfaction.

METHODS

PubMed, Scopus, and Cochrane database searches were performed (April 2016) using relevant MeSH and keyword terms for telemedicine and rheumatic diseases. Articles were selected if reporting outcomes for feasibility, effectiveness, and patient satisfaction and methodologically appraised using the Cochrane Collaboration's tool for assessing risk of bias and a modified version of CONSORT 2010 Statement.

RESULTS

A total of 177 articles were screened, 23 were selected for the present review but only 9 were RCTs. Five studies reported on feasibility, 14 effectiveness, and 9 satisfaction rates for different tele-rheumatology interventions grouped in synchronous (remotely delivered consultation) and asynchronous (remote disease activity assessment; tele-monitoring of treatment strategies or rehabilitation; and remotely delivered self-management programs). Seven studies (30.4%) were on rheumatoid arthritis, 2 (8.7%) were on systemic sclerosis (1 including also rheumatoid arthritis patients), 5 (21.7%) on fibromyalgia, 2 (8.7%) on osteoarthritis, 3 (13.0%) on juvenile idiopathic arthritis and 4 (17.4%) on mixed disease cohorts. Interventions and outcomes heterogeneity prevented meta-analysis of results. Overall, feasibility and patient satisfaction rates were high or very high across intervention types. Effectiveness was equal or higher than standard face-to-face approach in controlled trials which, however, were affected by small sample size and lack of blinding participants according to appraisal tools.

CONCLUSION

Telemedicine may provide a well-accepted way to remotely deliver consultation, treatment and monitoring disease activity in rheumatology. Higher quality RCTs demonstrating effectiveness of different tele-rheumatology interventions are needed.

Home tele-rehabilitation for rheumatic patients: impact and satisfaction of care analysis

Introduction

In this paper, we evaluated patients’ perspectives on the use of a system for home tele-rehabilitation, designed for subjects with low computer literacy suffering hand impairment due to rheumatic diseases.

Methods

After a clinical trial assessing device effectiveness, the Psychosocial Impact of Assistive Devices Scale (PIADS), Quebec User Evaluation of Satisfaction with Assistive Technology (QUEST) and Individually Prioritised Problem Assessment (IPPA) questionnaires were administered to evaluate the system’s impact on each patient’s life, and the results were correlated with clinical indices. Patients were asked to continue self-administered rehabilitation with common objects. One year later, a semi-structured telephone interview gathered data on their experience.

Results

The system received a positive QUEST score (4.5 ± 0.3) and a modest PIADS score (0.84 ± 0.8) due to the small impact on adaptability and self-esteem. The IPPA (3.7 ± 3.4) revealed improvement in the ability to perform tasks considered important, which was significantly correlated ( r = 0.60; p < 0.02) with the clinical Health Assessment Questionnaire (HAQ) index improvement. The interviews revealed a positive engagement effect, enhanced by the need to develop skills to be able to use the device (technological challenge) and by the perception of more attention by the medical staff. This may explain the significant dropout rate (80%) from the post-trial rehabilitation of the patients who used the device.

Discussion

The system was largely accepted by the patients. The results suggest that the need for information on their rehabilitation progress and the technological challenge deserves further study to make patients more autonomous in cases of continuous rehabilitation.