UNITE: Smart, Connected, and Coordinated Maternal Care for Underserved Communities
This project presents UNITE (UNderserved communITiEs): a community engagement model that is smart, deploying ubiquitous monitoring and lifelogging; connected, bringing together a diverse cast of community members including mothers, families, care providers, and outreach resources; and coordinated, using technology to proactively reach out to the community and use personalized intervention and education for improved self-management by the women. The UNITE project champions a model that is scalable in size, portable across different ethnic communities, and promises improved outcomes through better self-management and community enhanced motivational factors. The UNITE project will perform a controlled study using a community of underserved Orange County mothers together with non-profit agencies, hospitals, and local support organizations to evaluate the efficacy of this new community-enhanced self-management approach, and its impact on community building. The project will build larger communities of healthcare providers, insurance providers, and governmental agencies that can work in concert to enhance the well-being and lifestyles of mothers and families across a diverse spectrum of socio-economically disadvantaged groups. The UNITE project will also train the next generation of healthcare providers to deploy socio-economically relevant Internet-of-Things (IoT) technology in a cost-effective and user-friendly manner.
The UNITE project will exploit wearable IoT devices, lifelogging, context recognition, and health monitoring to build holistic digital phenotypes of the maternal care community using multi-modal data capture via two technical thrusts. The first technical thrust will develop a community-enhanced personalized monitoring and recommendation system. The system will leverage advanced signal processing and stochastic control techniques coupled with recent advances in matrix completion and graph signal processing to close the loop between observations, data processing and model building. By exploiting the additional dimension provided by the community surrounding the individual mothers, the project will design smart mining algorithms for cause assessment through personalized models in the context of the larger community. The second technical thrust will enable self-management via a Registered Nurse (RN)-in-the-loop smart monitoring-intervention system that will continuously monitor maternal-related physiological signs as well as behavioral information and social lifestyle of mothers using a wearable IoT-based body area network, offering personalized feedback (e.g., notification, warning, recommendation) on the mother's physical and mental health status as well as detailed data for health professionals. The self-management in the second thrust will be improved and incentivized through the first thrust's personalized community-enhanced recommendation system, and will result in technology-enhanced community care coordination and education. Through these technical thrusts, the UNITE system will exploit ubiquitous monitoring and develop a recommendation system capable of dynamically supporting a healthy lifestyle of a mother during pregnancy. The leading design principle is that the community surrounding the individual mother enhances monitoring and interventions, enabling more personalized recommendations that motivate better self-management.
-
Performance PeriodOctober 2018 - September 2022
-
University of California-Irvine
-
Award Number1831918
-
Lead PINikil Dutt
-
Co-PIMarco Levorato
-
Co-PIYuqing Guo
-
Co-PIAmir Rahmani
Project Material
- Longitudinal changes in objective sleep parameters during pregnancy
- Maternal Social Loneliness Detection Using Passive Sensing Through Continuous Monitoring in Everyday Settings: Longitudinal Study
- DynaFuse: Dynamic Fusion for Resource Efficient Multimodal Machine Learning Inference
- ZotCare: a flexible, personalizable, and affordable mhealth service provider
- Active Reinforcement Learning for Personalized Stress Monitoring in Everyday Settings
- An energy-efficient semi-supervised approach for on-device photoplethysmogram signal quality assessment
- Personalized Graph Attention Network for Multivariate Time-series Change Analysis: A Case Study on Long-term Maternal Monitoring
- Comparing prenatal and postpartum stress among women with previous adverse pregnancy outcomes and normal obstetric histories: A longitudinal cohort study
- Pregnant in a Pandemic: Connecting Perceptions of Uplifts and Hassles to Mental Health
- A Micro-Level Analysis of Physiological Responses to COVID-19: Continuous Monitoring of Pregnant Women in California
- Personalized Stress Monitoring using Wearable Sensors in Everyday Settings
- Data Collection and Labeling of Real-Time IoT-Enabled Bio-Signals in Everyday Settings for Mental Health Improvement
- Long-Term IoT-Based Maternal Monitoring: System Design and Evaluation
- Pregnant women’s daily patterns of well-being before and during the COVID-19 pandemic in Finland: Longitudinal monitoring through smartwatch technology
- Exercise and Stress in At-Risk Women during Pregnancy and Postpartum
- A Technology-Based Pregnancy Health and Wellness Intervention (Two Happy Hearts): Case Study
- pyEDA: An Open-Source Python Toolkit for Pre-processing and Feature Extraction of Electrodermal Activity
- Lightweight Photoplethysmography Quality Assessment for Real-time IoT-based Health Monitoring using Unsupervised Anomaly Detection
- Objective stress monitoring based on wearable sensors in everyday settings
- HCI and mHealth Wearable Tech: A Multidisciplinary Research Challenge
- Sleep Tracking of a Commercially Available Smart Ring and Smartwatch Against Medical-Grade Actigraphy in Everyday Settings: Instrument Validation Study
- A Real-time PPG Quality Assessment Approach for Healthcare Internet-of-Things
- Personalized Maternal Sleep Quality Assessment: An Objective IoT-based Longitudinal Study
Dutt's research is in the area of embedded systems and computer-aided design, with a specific focus on the exploration, evaluation and design of domain-specific embedded systems spanning both software and hardware. His group has developed a novel architectural description language that facilitates rapid exploration of programmable embedded systems, as well as automatic generation of software toolkits supporting embedded systems development (including optimizing compilers and simulators). Other projects within his group include cross-layer design and optimization of reliable, distributed embedded systems, memory architecture exploration for embedded systems, and brain-inspired architectures and computing.