OBJECTIVE: Nocturnal hypoglycemia is a known challenge for people with type 1 diabetes, especially for physically active individuals or those on multiple daily injections. We developed an evidential neural network (ENN) to predict at bedtime the probability and timing of nocturnal hypoglycemia (0-4 vs 4-8 h after bedtime) based on several glucose metrics and physical activity patterns. We utilized these predictions in silico to prescribe bedtime carbohydrates with a Smart Snack intervention specific to the predicted minimum nocturnal glucose and timing of nocturnal hypoglycemia. MATERIALS AND METHODS: We leveraged free-living datasets collected from 366 individuals from the T1DEXI Study and Glooko. Inputs to the ENN used to model nocturnal hypoglycemia were derived from demographic information, continuous glucose monitoring, and physical activity data. We assessed the accuracy of the ENN using area under the receiver operating curve, and the clinical impact of the Smart Snack intervention through simulations. RESULTS: The ENN achieved an area under the receiver operating curve of 0.80 and 0.71 to predict nocturnal hypoglycemic events during 0-4 and 4-8 h after bedtime, respectively, outperforming all evaluated baseline methods. Use of the Smart Snack intervention reduced probability of nocturnal hypoglycemia from 23.9 ± 14.1% to 14.0 ± 13.3% and duration from 7.4 ± 7.0% to 2.4 ± 3.3% in silico. DISCUSSION: Our findings indicate that the ENN-based Smart Snack intervention has the potential to significantly reduce the frequency and duration of nocturnal hypoglycemic events. CONCLUSION: A decision support system that combines prediction of minimum nocturnal glucose and proactive recommendations for bedtime carbohydrate intake might effectively prevent nocturnal hypoglycemia and reduce the burden of glycemic self-management.

Objective: To design an AI-powered tool to automatically assess the quality of phonocardiogram (PCG) recordings, and then identify S1 and S2 heart sounds using PCG recordings only. Methods We used PCG recordings from two datasets; a publicly available dataset (the 2016 PhysioNet/CinC Challenge), and a dataset that we collected as part of a clinical study we are conducting at Oregon Health & Science University (OHSU). We developed a logistic regression classifier to score PCG signal quality using semi-supervised learning and a two-layer perceptron artificial neural network classifier with con textual time-and frequency-domain input features to detect fundamental S1 and S2 heart sounds. We also analyzed the impact of input features on the accuracy of S1 and S2 segmentation. Results: Our segmentation method detects fundamental S1 and S2 heart sounds with a precision of 93% and distinguishes S1/S2 heart sounds with area under the curve (AUC) of 97.1%. Conclusions: Implementing a signal quality assessment tool allows for better segmentation performance as only suitable signals are processed by the S1/S2 sound detection and classification algorithms. Distance between sounds in time-domain are able to distinguish between S1 and S2 with accuracy of 87.4%; however, by adding the frequency-domain features, the accuracy significantly improved to 9 2.4%. Significance: S1 an d S2 heart sound segmentation is the first step in the processes of detecting and classifying heart abnormalities from a PCG. Our proposed method is simple and effective for segmentation for this task. Consequently, it can facilitate the performance of subsequent tasks including the detection of heart murmurs.

OBJECTIVE: Aimless movement or wandering may be a symptom of mild cognitive impairment (MCI) that arises as a consequence of confusion and forgetfulness. This paper presents a support vector machine (SVM) framework based on movement analysis for the prediction of the onset and progression of MCI. METHODS: Movement data of 22 subjects with MCI, and 22 other healthy subjects, living independently in smart homes were collected for ten years using motion sensors. Features were extracted from the sensor data using movement metrics, including cyclomatic complexity, detrended fluctuation analysis, fractal index, entropy, and room transitions. Two different SVM classification algorithms were trained using the features, first to predict the progression of MCI in the post-transition period, and second to predict the onset of MCI in the pre-transition phase. RESULTS: post-transition month. The features of cyclomatic complexity contributed significantly to the prediction results. CONCLUSION: Findings support the use of movement complexity measures and machine learning for monitoring cognitive behavior in an independent living environment.

Falls are a major health problem with one in three people over the age of 65 falling each year, oftentimes causing hip fractures, disability, reduced mobility, hospitalization and death. A major limitation in fall detection algorithm development is an absence of real-world falls data. Fall detection algorithms are typically trained on simulated fall data that contain a well-balanced number of examples of falls and activities of daily living. However, real-world falls occur infrequently, making them difficult to capture and causing severe data imbalance. People with multiple sclerosis (MS) fall frequently, and their risk of falling increases with disease progression. Because of their high fall incidence, people with MS provide an ideal model for studying falls. This paper describes the development of a context-aware fall detection system based on inertial sensors and time of flight sensors that is robust to imbalance, which is trained and evaluated on real-world falls in people with MS. The algorithm uses an auto-encoder that detects fall candidates using reconstruction error of accelerometer signals followed by a hyper-ensemble of balanced random forests trained using both acceleration and movement features. On a clinical dataset obtained from 25 people with MS monitored over eight weeks during free-living conditions, 54 falls were observed and our system achieved a sensitivity of 92.14%, and false-positive rate of 0.65 false alarms per day.

indoor tracking system that uses received signal strength (RSS) from radio frequency (RF) transceivers to estimate the location of a person. While many RSS-based tracking systems use a body-worn device or tag, this approach requires no such tag. The approach is based on the key principle that RF signals between wall-mounted transceivers reflect and absorb differently depending on a person's movement within their home. A hierarchical neural network hidden Markov model (NN-HMM) classifier estimates both movement patterns and stand vs. walk conditions to perform tracking accurately. The algorithm and features used are specifically robust to changes in RSS mean shifts in the environment over time allowing for greater than 90% region level classification accuracy over an extended testing period. In addition to tracking, the system also estimates the number of people in different regions. It is currently being developed to support independent living and long-term monitoring of seniors.