SugarMate

A Review of Recurrent Neural Network-Based Methods in Computational Physiology

Artificial intelligence and machine learning techniques have progressed dramatically and become powerful tools required to solve complicated tasks, such as computer vision, speech recognition, and natural language processing. Since these techniques have provided promising and evident results in these fields, they emerged as valuable methods for applications in human physiology and healthcare. General physiological recordings are time-related expressions of bodily processes associated with health or morbidity. Sequence classification, anomaly detection, decision making, and future status prediction drive the learning algorithms to focus on the temporal pattern and model the nonstationary dynamics of the human body. These practical requirements give birth to the use of recurrent neural networks (RNNs), which offer a tractable solution in dealing with physiological time series and provide a way to understand complex time variations and dependencies. The primary objective of this article is to provide an overview of current applications of RNNs in the area of human physiology for automated prediction and diagnosis within different fields. Finally, we highlight some pathways of future RNN developments for human physiology.

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

Diabetes mellitus is characterized by elevated blood glucose levels, however patients with diabetes may also develop hypoglycemia due to treatment. There is an increasing demand for non-invasive blood glucose monitoring and trends detection amongst people with diabetes and healthy individuals, especially athletes. Wearable devices and non-invasive sensors for blood glucose monitoring have witnessed considerable advances. This review is an update on recent contributions utilizing novel sensing technologies over the past five years which include electrocardiogram, electromagnetic, bioimpedance, photoplethysmography, and acceleration measures as well as bodily fluid glucose sensors to monitor glucose and trend detection. We also review methods that use machine learning algorithms to predict blood glucose trends, especially for high risk events such as hypoglycemia. Convolutional and recurrent neural networks, support vector machines, and decision trees are examples of such machine learning algorithms. Finally, we address the key limitations and challenges of these studies and provide recommendations for future work.

Patient-Generated Data Analytics of Health Behaviors of People Living With Type 2 Diabetes: Scoping Review

Background

Complications due to type 2 diabetes (T2D) can be mitigated through proper self-management that can positively change health behaviors. Technological tools are available to help people living with, or at risk of developing, T2D to manage their condition, and such tools provide a large repository of patient-generated health data (PGHD). Analytics can provide insights into the health behaviors of people living with T2D.

Objective

The aim of this review is to investigate what can be learned about the health behaviors of those living with, or at risk of developing, T2D through analytics from PGHD.

Methods

A scoping review using the Arksey and O’Malley framework was conducted in which a comprehensive search of the literature was conducted by 2 reviewers. In all, 3 electronic databases (PubMed, IEEE Xplore, and ACM Digital Library) were searched using keywords associated with diabetes, behaviors, and analytics. Several rounds of screening using predetermined inclusion and exclusion criteria were conducted, after which studies were selected. Critical examination took place through a descriptive-analytical narrative method, and data extracted from the studies were classified into thematic categories. These categories reflect the findings of this study as per our objective.

Results

We identified 43 studies that met the inclusion criteria for this review. Although 70% (30/43) of the studies examined PGHD independently, 30% (13/43) combined PGHD with other data sources. Most of these studies used machine learning algorithms to perform their analysis. The themes identified through this review include predicting diabetes or obesity, deriving factors that contribute to diabetes or obesity, obtaining insights from social media or web-based forums, predicting glycemia, improving adherence and outcomes, analyzing sedentary behaviors, deriving behavior patterns, discovering clinical correlations from behaviors, and developing design principles.

Conclusions

The increased volume and availability of PGHD have the potential to derive analytical insights into the health behaviors of people living with T2D. From the literature, we determined that analytics can predict outcomes and identify granular behavior patterns from PGHD. This review determined the broad range of insights that can be examined through PGHD, which constitutes a unique source of data for these applications that would not be possible through the use of other data sources.

90% Accuracy for Photoplethysmography-Based Non-Invasive Blood Glucose Prediction by Deep Learning with Cohort Arrangement and Quarterly Measured HbA1c

Previously published photoplethysmography-(PPG) based non-invasive blood glucose (NIBG) measurements have not yet been validated over 500 subjects. As illustrated in this work, we increased the number subjects recruited to 2538 and found that the prediction accuracy (the ratio in zone A of Clarke's error grid) reduced to undesirable 60.6%. We suspect the low prediction accuracy induced by larger sample size might arise from the physiological diversity of subjects, and one possibility is that the diversity might originate from medication. Therefore, we split the subjects into two cohorts for deep learning: with and without medication (1682 and 856 recruited subjects, respectively). In comparison, the cohort training for subjects without any medication had approximately 30% higher prediction accuracy over the cohort training for those with medication. Furthermore, by adding quarterly (every 3 months) measured glycohemoglobin (HbA1c), we were able to significantly boost the prediction accuracy by approximately 10%. For subjects without medication, the best performing model with quarterly measured HbA1c achieved 94.3% prediction accuracy, RMSE of 12.4 mg/dL, MAE of 8.9 mg/dL, and MAPE of 0.08, which demonstrates a very promising solution for NIBG prediction via deep learning. Regarding subjects with medication, a personalized model could be a viable means of further investigation.

Utilizing passive sensing data to provide personalized psychological care in low-resource settings

Background: With the growing ubiquity of smartphones and wearable devices, there is an increased potential of collecting passive sensing data in mobile health. Passive data such as physical activity, Global Positioning System (GPS), interpersonal proximity, and audio recordings can provide valuable insight into the lives of individuals. In mental health, these insights can illuminate behavioral patterns, creating exciting opportunities for mental health service providers and their clients to support pattern recognition and problem identification outside of formal sessions. In the Sensing Technologies for Maternal Depression Treatment in Low Resource Settings (StandStrong) project, our aim was to build an mHealth application to facilitate the delivery of psychological treatments by lay counselors caring for adolescent mothers with depression in Nepal. Methods: This paper describes the development of the StandStrong platform comprising the StandStrong Counselor application, and a cloud-based processing system, which can incorporate any tool that generates passive sensing data. We developed the StandStrong Counselor application that visualized passively collected GPS, proximity, and activity data. In the app, GPS data displays as heat maps, proximity data as charts showing the mother and child together or apart, and mothers' activities as activity charts. Lay counselors can use the StandStrong application during counseling sessions to discuss mothers' behavioral patterns and clinical progress over the course of a five-week counseling intervention. Achievement Awards based on collected data can also be automatically generated and sent to mothers. Additionally, messages can be sent from counselors to mother's personal phones through the StandStrong platform. Discussion: The StandStrong platform has the potential to improve the quality and effectiveness of psychological services delivered by non-specialists in diverse global settings.

Utilizing passive sensing data to provide personalized psychological care in low-resource settings

Background: With the growing ubiquity of smartphones and wearable devices, there is an increased potential of collecting passive sensing data in mobile health. Passive data such as physical activity, Global Positioning System (GPS), interpersonal proximity, and audio recordings can provide valuable insight into the lives of individuals. In mental health, these insights can illuminate behavioral patterns, creating exciting opportunities for mental health service providers and their clients to support pattern recognition and problem identification outside of formal sessions. In the Sensing Technologies for Maternal Depression Treatment in Low Resource Settings (StandStrong) project, our aim was to build an mHealth application to facilitate the delivery of psychological treatments by lay counselors caring for adolescent mothers with depression in Nepal. Methods: This paper describes the development of the StandStrong platform comprising the StandStrong Counselor application, and a cloud-based processing system, which can incorporate any tool that generates passive sensing data. We developed the StandStrong Counselor application that visualized passively collected GPS, proximity, and activity data. In the app, GPS data displays as heat maps, proximity data as charts showing the mother and child together or apart, and mothers' activities as activity charts. Lay counselors can use the StandStrong application during counseling sessions to discuss mothers' behavioral patterns and clinical progress over the course of a five-week counseling intervention. Awards based on collected data also can be automatically generated and sent to mothers. Additionally, messages can be sent from counselors to mother's personal phones through the StandStrong platform. Discussion: The StandStrong platform has the potential to improve the quality and effectiveness of psychological services delivered by non-specialists in diverse global settings.

Design and Development of Diabetes Management System Using Machine Learning

This paper describes the design and implementation of a software system to improve the management of diabetes using a machine learning approach and to demonstrate and evaluate its effectiveness in controlling diabetes. The proposed approach for this management system handles the various factors that affect the health of people with diabetes by combining multiple artificial intelligence algorithms. The proposed framework factors the diabetes management problem into subgoals: building a Tensorflow neural network model for food classification; thus, it allows users to upload an image to determine if a meal is recommended for consumption; implementing K-Nearest Neighbour (KNN) algorithm to recommend meals; using cognitive sciences to build a diabetes question and answer chatbot; tracking user activity, user geolocation, and generating pdfs of logged blood sugar readings. The food recognition model was evaluated with cross-entropy metrics that support validation using Neural networks with a backpropagation algorithm. The model learned features of the images fed from local Ghanaian dishes with specific nutritional value and essence in managing diabetics and provided accurate image classification with given labels and corresponding accuracy. The model achieved specified goals by predicting with high accuracy, labels of new images. The food recognition and classification model achieved over 95% accuracy levels for specific calorie intakes. The performance of the meal recommender model and question and answer chatbot was tested with a designed cross-platform user-friendly interface using Cordova and Ionic Frameworks for software development for both mobile and web applications. The system recommended meals to meet the calorific needs of users successfully using KNN (with k = 5) and answered questions asked in a human-like way. The implemented system would solve the problem of managing activity, dieting recommendations, and medication notification of diabetics.

Wearable Digital Sensors to Identify Risks of Postpartum Depression and Personalize Psychological Treatment for Adolescent Mothers: Protocol for a Mixed Methods Exploratory Study in Rural Nepal

BACKGROUND

There is a high prevalence of untreated postpartum depression among adolescent mothers with the greatest gap in services in low- and middle-income countries. Recent studies have demonstrated the potential of nonspecialists to provide mental health services for postpartum depression in these low-resource settings. However, there is inconsistency in short-term and long-term benefits from the interventions. Passive sensing data generated from wearable digital devices can be used to more accurately distinguish which mothers will benefit from psychological services. In addition, wearable digital sensors can be used to passively collect data to personalize care for mothers. Therefore, wearable passive sensing technology has the potential to improve outcomes from psychological treatments for postpartum depression.

OBJECTIVE

This study will explore the use of wearable digital sensors for two objectives: First, we will pilot test using wearable sensors to generate passive sensing data that distinguish adolescent mothers with depression from those without depression. Second, we will explore how nonspecialists can integrate data from passive sensing technologies to better personalize psychological treatment.

METHODS

This study will be conducted in rural Nepal with participatory involvement of adolescent mothers and health care stakeholders through a community advisory board. The first study objective will be addressed by comparing behavioral patterns of adolescent mothers without depression (n=20) and with depression (n=20). The behavioral patterns will be generated by wearable digital devices collecting data in 4 domains: (1) the physical activity of mothers using accelerometer data on mobile phones, (2) the geographic range and routine of mothers using GPS (Global Positioning System) data collected from mobile phones, (3) the time and routine of adolescent mothers with their infants using proximity data collected from Bluetooth beacons, and (4) the verbal stimulation and auditory environment for mothers and infants using episodic audio recordings on mobile phones. For the second objective, the same 4 domains of data will be collected and shared with nonspecialists who are delivering an evidence-based behavioral activation intervention to the depressed adolescent mothers. Over 5 weeks of the intervention, we will document how passive sensing data are used by nonspecialists to personalize the intervention. In addition, qualitative data on feasibility and acceptability of passive data collection will be collected for both objectives.

RESULTS

To date, a community advisory board comprising young women and health workers engaged with adolescent mothers has been established. The study is open for recruitment, and data collection is anticipated to be completed in November 2019.

CONCLUSIONS

Integration of passive sensing data in public health and clinical programs for mothers at risk of perinatal mental health problems has the potential to more accurately identify who will benefit from services and increase the effectiveness by personalizing psychological interventions.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/14734.