Assessing Elevated Blood Glucose Levels Through Blood Glucose Evaluation and Monitoring Using Machine Learning and Wearable Photoplethysmography Sensors: Algorithm Development and Validation.

BACKGROUND: Diabetes mellitus is the most challenging and fastest-growing global public health concern. Approximately 10.5% of the global adult population is affected by diabetes, and almost half of them are undiagnosed. The growing at-risk population exacerbates the shortage of health resources, with an estimated 10.6% and 6.2% of adults worldwide having impaired glucose tolerance and impaired fasting glycemia, respectively. All current diabetes screening methods are invasive and opportunistic and must be conducted in a hospital or laboratory by trained professionals. At-risk participants might remain undetected for years and miss the precious time window for early intervention to prevent or delay the onset of diabetes and its complications. OBJECTIVE: We aimed to develop an artificial intelligence solution to recognize elevated blood glucose levels (≥7.8 mmol/L) noninvasively and evaluate diabetic risk based on repeated measurements. METHODS: This study was conducted at KK Women's and Children's Hospital in Singapore, and 500 participants were recruited (mean age 38.73, SD 10.61 years; mean BMI 24.4, SD 5.1 kg/m2). The blood glucose levels for most participants were measured before and after consuming 75 g of sugary drinks using both a conventional glucometer (Accu-Chek Performa) and a wrist-worn wearable. The results obtained from the glucometer were used as ground-truth measurements. We performed extensive feature engineering on photoplethysmography (PPG) sensor data and identified features that were sensitive to glucose changes. These selected features were further analyzed using an explainable artificial intelligence approach to understand their contribution to our predictions. RESULTS: Multiple machine learning models were trained and assessed with 10-fold cross-validation, using participant demographic data and critical features extracted from PPG measurements as predictors. A support vector machine with a radial basis function kernel had the best detection performance, with an average accuracy of 84.7%, a sensitivity of 81.05%, a specificity of 88.3%, a precision of 87.51%, a geometric mean of 84.54%, and F score of 84.03%. CONCLUSIONS: Our findings suggest that PPG measurements can be used to identify participants with elevated blood glucose measurements and assist in the screening of participants for diabetes risk.

Detection of Freezing of Gait Using Convolutional Neural Networks and Data From Lower Limb Motion Sensors.

Parkinson's disease (PD) is a chronic, non-reversible neurodegenerative disorder, and freezing of gait (FOG) is one of the most disabling symptoms in PD as it is often the leading cause of falls and injuries that drastically reduces patients' quality of life. In order to monitor continuously and objectively PD patients who suffer from FOG and enable the possibility of on-demand cueing assistance, a sensor-based FOG detection solution can help clinicians manage the disease and help patients overcome freezing episodes. Many recent studies have leveraged deep learning models to detect FOG using signals extracted from inertial measurement unit (IMU) devices. Usually, the latent features and patterns of FOG are discovered from either the time or frequency domain. In this study, we investigated the use of the time-frequency domain by applying the Continuous Wavelet Transform to signals from IMUs placed on the lower limbs of 63 PD patients who suffered from FOG. We built convolutional neural networks to detect the FOG occurrences, and employed the Bayesian Optimisation approach to obtain the hyper-parameters. The results showed that the proposed subject-independent model was able to achieve a geometric mean of 90.7% and a F1 score of 91.5%.

Effect of music-based movement therapy on the freezing of gait in patients with Parkinson's disease: A randomized controlled trial.

Background: Progression of freezing of gait (FOG), a common pathological gait in Parkinson's disease (PD), has been shown to be an important risk factor for falls, loss of independent living ability, and reduced quality of life. However, previous evidence indicated poor efficacy of medicine and surgery in treating FOG in patients with PD. Music-based movement therapy (MMT), which entails listening to music while exercising, has been proposed as a treatment to improve patients' motor function, emotions, and physiological activity. In recent years, MMT has been widely used to treat movement disorders in neurological diseases with promising results. Results from our earlier pilot study revealed that MMT could relieve FOG and improve the quality of life for patients with PD. Objective: To explore the effect of MMT on FOG in patients with PD. Materials and methods: This was a prospective, evaluator-blinded, randomized controlled study. A total of 81 participants were randomly divided into music-based movement therapy group (MMT, n = 27), exercise therapy group (ET, n = 27), and control group (n = 27). Participants in the MMT group were treated with MMT five times (1 h at a time) every week for 4 weeks. Subjects in the ET group were intervened in the same way as the MMT group, but without music. Routine rehabilitation treatment was performed on participants in all groups. The primary outcome was the change of FOG in patients with PD. Secondary evaluation indicators included FOG-Questionnaire (FOG-Q) and the comprehensive motor function. Results: After 4 weeks of intervention, the double support time, the cadence, the max flexion of knee in stance, the max hip extension, the flexion moment of knee in stance, the comprehensive motor function (UPDRS Part III gait-related items total score, arising from chair, freezing of gait, postural stability, posture, MDS-UPDRS Part II gait-related items total score, getting out of bed/a car/deep chair, walking and balance, freezing), and the FOG-Q in the MMT group were lower than that in the control group and ET group (p < 0.05). The gait velocity, the max ankle dorsiflexion in stance, ankle range of motion (ROM) during push-off, ankle ROM over gait cycle, the knee ROM over gait cycle, and the max extensor moment in stance (ankle, knee) in the MMT group were higher than that in the control group and ET group (p < 0.05). However, no significant difference was reported between the control group and ET group (p > 0.05). The stride length and hip ROM over gait cycle in the MMT group were higher than that in the control group (p < 0.05), and the max knee extension in stance in the MMT group was lower than that in the control group (p < 0.05). Nevertheless, there was no significant difference between the ET group and MMT group (p > 0.05) or control group (p > 0.05). Conclusion: MMT improved gait disorders in PD patients with FOG, thereby improving their comprehensive motor function.

Convolutional Neural Network for Freezing of Gait Detection Leveraging the Continuous Wavelet Transform on Lower Extremities Wearable Sensors Data.

Freezing of Gait is the most disabling gait disturbance in Parkinson's disease. For the past decade, there has been a growing interest in applying machine learning and deep learning models to wearable sensor data to detect Freezing of Gait episodes. In our study, we recruited sixty-seven Parkinson's disease patients who have been suffering from Freezing of Gait, and conducted two clinical assessments while the patients wore two wireless Inertial Measurement Units on their ankles. We converted the recorded time-series sensor data into continuous wavelet transform scalograms and trained a Convolutional Neural Network to detect the freezing episodes. The proposed model achieved a generalisation accuracy of 89.2% and a geometric mean of 88.8%.