Ronald M Aarts | Searcharxiv

arXiv2020

Characterizing and Detecting Freezing of Gait using Multi-modal Physiological Signals

Freezing-of-gait a mysterious symptom of Parkinsons disease and defined as a sudden loss of ability to move forward. Common treatments of freezing episodes are currently of moderate efficacy and can likely be improved through a reliable freezing evaluation. Basic-science studies about the characterization of freezing episodes and a 24/7 evidence-support freezing detection system can contribute to the reliability of the evaluation in daily life. In this study, we analyzed multi-modal features from brain, eye, heart, motion, and gait activity from 15 participants with idiopathic Parkinsons disease and 551 freezing episodes induced by turning in place. Statistical analysis was first applied on 248 of the 551 to determine which multi-modal features were associated with freezing episodes. Features significantly associated with freezing episodes were ranked and used for the freezing detection. We found that eye-stabilization speed during turning and lower-body trembling measure significantly associated with freezing episodes and used for freezing detection. Using a leave-one-subject-out cross-validation, we obtained a sensitivity of 97%+/-3%, a specificity of 96%+/-7%, a precision of 73%+/-21%, a Matthews correlation coefficient of 0.82+/-0.15, and an area under the Precision-Recall curve of 0.94+/-0.05. According to the Precision-Recall curves, the proposed freezing detection method using the multi-modal features performed better than using single-modal features.

eess.SP↗

arXiv2018

Estimating blood pressure trends and the nocturnal dip from photoplethysmograph

Objective: Evaluate a method for the estimation of the nocturnal systolic blood pressure (SBP) dip from 24-hour blood pressure trends using a wrist-worn photoplethysmography (PPG) sensor and a deep neural network in free-living individuals, comparing the deep neural network to traditional machine learning and non-machine learning baselines. Approach: A wrist-worn PPG sensor was worn by 106 healthy individuals for 226 days during which 5111 reference values for blood pressure (BP) were obtained with a 24-hour ambulatory BP monitor and matched with the PPG sensor data. Features based on heart rate variability and pulse morphology were extracted from the PPG waveforms. Long- and short term memory (LSTM) networks, dense networks, random forests and linear regression models were trained and evaluated in their capability of tracking trends in BP, as well as the estimation of the SBP dip. Main results: Best performance for estimating the SBP dip were obtained with a deep LSTM neural network with a root mean squared error (RMSE) of 3.12$\pm$2.20 $Δ$mmHg and a correlation of 0.69 $(p=3*10^{-5})$. This dip was derived from trend estimates of BP which had an RMSE of 8.22$\pm$1.49 mmHg for systolic and 6.55$\pm$1.39 mmHg for diastolic BP (DBP). While other models had similar performance for the tracking of relative BP, they did not perform as well as the LSTM for the SBP dip. Significance: The work provides first evidence for the unobtrusive estimation of the nocturnal SBP dip, a highly prognostic clinical parameter. It is also the first to evaluate unobtrusive BP measurement in a large data set of unconstrained 24-hour measurements in free-living individuals and provides evidence for the utility of LSTM models in this domain.

physics.med-ph↗