Projects

UNITE

Smart, Connected, and Coordinated Maternal Care for Underserved Communities

Smart, Connected, and Coordinated Maternal Care for Underserved Communities Contact Person:

Nikil Dutt

Other PIs/Investigators/PhD students:

Yuqing Guo
Amir Rahmani
Marco Levorato
Margaret Schneider
Stephanie Reich
Gillian Hayes
Pamela Pimentel
Sina Labbaf
Milad Asgari
Priscilla Kehoe
Julie Rousseau
Jessica Oviatt

Partners:
MOMS Orange County, Saint Joseph Hospital in Orange, Children and Families Commission of OC, Community Health Initiative of OC, University of Turku, and TYKS Hospital

Funding Agency:

NSF Smart and Connected Communities (S&CC) program

Project Summary:

UNITE (UNderserved communITiEs) presents 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 performs 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 builds 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 also trains the next generation of healthcare providers to deploy socio-economically relevant Internet-of-Things (IoT) technology in a cost-effective and user-friendly manner.

Publications:

– Iman Azimi, Olugbenga Oti, Sina Labbaf, Hannakaisa Niela-Vilen, Anna Axelin, Nikil Dutt, Pasi Liljeberg, and Amir M. Rahmani, “Personalized Maternal Sleep Quality Assessment: An Objective IoT-based Longitudinal Study”, IEEE Access, 2019
– Holly Borg, Hannah Vasquez, Michelle Heredia, Melissa Navarrete, Nikil Dutt, Amir M. Rahmani, and Yuqing Guo, “A Self-Management Model: Using Wearable Devices for Continuous Monitoring during the Perinatal Period”, National Perinatal Association Annual Conference Perinatal Care and the 4th Trimester” (NPA’20), 2020
– Lucretia Williams, Gillian R. Hayes, Yuqing Guo, Amir M. Rahmani, Nikil Dutt, “HCI and mHealth Wearable Tech: A Multidisciplinary Research Challenge”, ACM CHI Conference on Human Factors in Computing Systems, Case Study (CHI’20-Case Study), 2020
_ Juho Laitala, Mingzhe Jiang, Elise Syrjälä, Emad Kasaeyan Naeini, Antti Airola, Amir M. Rahmani, Nikil D. Dutt, Pasi Liljeberg, “Robust ECG R-peak Detection Using LSTM”, The 35th ACM/SIGAPP Symposium On Applied Computing (SAC’20), 2019

IoCT-CARE

Internet of Cognitive Things for Personalized Healthcare

Internet of Cognitive Things for Personalized Healthcare Contact Person:

Nikil Dutt

Other PIs/Investigators/PhD students:

Amir Rahmani
Marco Levorato
Pasi Liljbeberg
Juha-Pekka Soininen
Sina Shahhosseini
Delaram Amiri

Partners:
University of Turku and VTT

Funding Agency:

NSF WiFIUS program

Project Summary:

Quality of Experience (QoE) is a key metric for the successful delivery of end-user services for IoT-enabled applications. Achieving consistent end-user QoE poses tremendous challenges in the face of resource constraints and dynamic variations at multiple scales of the IoT system stack: at the application, network, resource, and device levels. This proposal outlines a self-aware cognitive architecture – the Internet of Cognitive Things (IoCT) – that delivers acceptable QoE by adapting to dynamic variations in infrastructural compute, communication and resource needs, while also synergistically learning and adapting to end user behavior. The approach leverages edge (i.e., Fog) computing architectures to introduce intelligence and adaptability in integrated multi-scale IoT systems. The objective is to efficiently manage information acquisition, communication and processing across different scales of the IoT systems, while synergistically coupling learning of end-user behaviors to deliver efficient and customized services. The proposed IoCT system is the first example of architecture where a network of algorithms communicates and collaborates synergistically to achieve a system-wide objective. Cognition and edge computing architectures are leveraged to introduce intelligence and adaptability in integrated multi-scale IoT systems, through a Personal Holistic Cognitive Optimization (PHCO) framework. To this aim, the IoCT will adopt recently proposed learning and control techniques (i.e. Deep Q-Networks), and exploit self-awareness principles to achieve effective system optimization. The project leverages on-going collaboration with the Turku University Hospital to demonstrate a personalized ubiquitous healthcare framework using the Early Warning Score (EWS) system for human health monitoring. Healthcare spending accounts for almost 17% of the GDP in the US. In healthcare, effective monitoring and observation of patients plays a key role in detecting a deteriorating patient. This project’s exemplar application on efficient early detection of these life-threatening signs can potentially save lives through better quality of care, and timely delivery of critical/urgent health indicators. The framework and services are also applicable to a broad range of other IoT application domains.


A joint project between the Academy of Finland and National Science Foundation (NSF), US.


Depression detection and help using Personicle

Holistic Stress Reduction in Adolescents through Multi-modal Personal Chronicles

Holistic Stress Reduction in Adolescents through Multi-modal Personal Chronicles Contact Person:

Jessica Borelli

Other PIs/Investigators/PhD students:

Amir Rahmani
Nikil Dutt
Ramesh Jain
Sina Labbaf
Amir Hossein Aqajari
Asal Yunusova
Alexander Rivera

Project Summary:

Emotional stress is a major factor contributing to the leading causes of death in the United States. Adolescence is a particularly risky period of development during which rates of mental disorders and mortality increase dramatically, changes which may in part be due to rapid shifts in physical and psychological development in the context of brain immaturing. Stress management and reduction are crucial capacities for adolescents since they often experience high-intensity negative emotions and lack the maturity required to exert top-down control over these intense emotional experiences. Effective stress management techniques for adolescents must meet them where they live — on their smartphones– and engage them as active participants in their health assessment/promotion. This proposal aims to develop a holistic stress reduction strategy combining emerging IoT technologies with a multi-modal lifelogging framework that enables psychologists and caregivers to identify the root causes of stress and build an evidence-based approach to monitoring stress and emotion in adolescents.

Publications:

Han, H. J., Labbaf, S., Borelli, J. L., Dutt, N. & Rahmani, A. M., “Objective stress monitoring based on wearable sensors in everyday settings,” Taylor & Francis Journal of Medical Engineering and Technology, 2020.

Personicle Open Source

Building Personal Chronicle

Building Personal Chronicle Contact Person:

Ramesh Jain

Other PIs/Investigators/PhD students:

Charles Boicey
Michael Carey
Nikil Dutt
Amir M. Rahmani
Jordan Oh
Ali Rostami
Namhyun Kim
Dongju (Alex) Seo

Partners:
Clearsense and Simula Research Laboratory

Project Summary:

Personicle is a Mobile App which in its current form collects and processes the location, place, mobile device-specific measures like Calendar, Ambient Light, phone usage, and measures like Heart Rate, Activity Level, and Sleep from wearable devices like Fitbit or smartwatches. The first release uses Android phones and Fitbit devices; soon iOS and other smart wearables will be used. Currently, data is collected at every 5-minute interval to create activities and events, that may be used by health systems.

Personalization requires precise personal models; however, every individual is unique.  The story of their life is comprised of events at various granularities in time and space. Personal chronicle, aka Personicle, captures this story through these events. Generally, for modeling a person, one requires five event streams: Daily Life Events, Personal Events, Personal Biological Events, Social Events related to the person, and Environmental Events around the person. 

UCI Personicle is an open-source software platform developed to automatically collect data from phones and other devices to create basic daily life events for a user, and then attach other data streams in order to create additional related events. The first version of Personicle is available for Android and Fitbit, with plans to release an iOS version soon. In the future, 

Personicle will also be able to bring in data from other wearable devices and sources to enrich event characteristics and attributes in Personicle. Ultimately, Personicle is expected to evolve into a basic open-source software platform that could be used to build personalized applications by various interested application developers, while allowing individual users to gain insight by examining their own event streams.

Personicle was conceived and initially developed at University of California, Irvine in the research group of Prof. Ramesh Jain. The concept of Personicle was first proposed by Prof. Ramesh Jain with his student Laleh Jalali in their work on Objective Self.  The first Initial version of Personicle was implemented for his doctoral research by Hyungik (Jordan) Oh. Later many other researchers at UCI as well as other places started collaborating on this idea and are contributing to its development. 

Dr. Charles Boicey showed his passionate interest in using Personicle to help people. His company, Clearsense, offered to help make the research version to a production version of open source Personicle. 

The current version of UCI Personicle is implemented and maintained by Clearsense.

Read more information on Personicle.com

Publications:

– Ramesh Jain, Laleh Jalali, Objective Self. IEEE MultiMedia 21(4): 100-110 (2014)
– Hyungik Oh, Ramesh Jain, From Multimedia Logs to Personal Chronicles. ACM Multimedia 2017: 881-889
– Hyungik Oh, Ramesh C. Jain, Detecting Events of Daily Living Using Multimodal Data. CoRR abs/1905.09402 (2019)
– Hyungik Oh, Jonathan Nguyen, Soundarya Soundararajan, Ramesh C. Jain, Multimodal Food Journaling. HealthMedia@MM 2018: 39-47

Personal model

Building Personal model for Health Navigation

Building Personal model for Health Navigation Contact Person:

Ramesh Jain

Other PIs/Investigators/PhD students:

Amir Rahmani
Nikil Dutt
Joran Oh
Ali Rostami
Dongju Seo

Project Summary:

Population based healthcare models, while helpful in treating diseases caused by external stimulus, have proven not so effective for chronic diseases where the functioning of our biological systems degrades over time. We need to collect high-resolution longitudinal data about the individual to model and predict the transitions of their individual health state over time. Event mining allows us to model the relationships between different events that occur during the course of an individual’s life. We can find the impact of different events on the users’ health by initializing the users’ model (personal model) from domain knowledge and model the nature of the relationships using the data collected in their personal logs (personicle).

Event mining can also be used to find previously unknown relationships by combining it with causal discovery algorithms.

Publications:

– Laleh Jalali, Ramesh Jain, Bringing Deep Causality to Multimedia Data Streams. ACM Multimedia 2015: 221-230
– N. Nag and R. Jain, A navigational approach to health: Actionable guid¬ance for improved quality of life. IEEE Computer, vol. 52, no. 4, pp. 12–20. April 2019.
– Nitish Nag, Vaibhav Pandey, Preston J. Putzel, Hari Bhimaraju, Srikanth Krishnan, Ramesh Jain, Cross-Modal Health State Estimation. ACM Multimedia 2018: 1993-2002

Food Computing

FoodLogging Platform

FoodLogging Platform Contact Person:

Ramesh Jain

Other PIs/Investigators/PhD students:

Amir Rahmani
Nikil Dutt
Joran Oh
Ali Rostami
Nitish Nag

Partners:
Lancaster University, NUS - National University of Singapore, TU Wien, University of Tokyo, and Kaloric

Project Summary:

Models are built using data. Most successful search, social media, and recommendation systems are built using personal models to provide people the right information, at the right time, in the right context, usually even before a user articulates his need. Food recommendation systems need to be built using the same approach. A personal food model is essential for recommending the right food item at the right time. It is also essential to predict the effect of food so the right suggestions can be made to avoid unpleasant situations. We need to build such models using food logs collected for the person. Many applications for foodlogging are being developed based on detecting the dish or item being consumed and finding nutritional elements based on ingredients in these items. Detecting items and the volumes consumed requires a multimodal platform and nutritional data sources for items prepared using specific ingredients and recipes.

Publications:

– Ruihan Xu, Luis Herranz, Shuqiang Jiang, Shuang Wang, Xinhang Song, Ramesh Jain, Geolocalized Modeling for Dish Recognition. IEEE Transactions on Multimedia 17(8): 1187-1199 (2015).
– Nitish Nag, Aditya Narendra Rao, Akash Kulhalli, Kushal Samir Mehta, Nishant Bhattacharya, Pratul Ramkumar, Aditya Bharadwaj, Dinkar Sitaram, Ramesh C. Jain, Flavour Enhanced Food Recommendation. MADiMa @ ACM Multimedia 2019: 60-66.
– Nitish Nag, Vaibhav Pandey, Ramesh C. Jain, Health Multimedia: Lifestyle Recommendations Based on Diverse Observations. ICMR 2017: 99-106.

Supporting and Sustaining Apache AsterixDB for the CISE Research Community

Supporting and Sustaining Apache AsterixDB for the CISE Research Community Contact Person:

Michael J. Carey

Other PIs/Investigators/PhD students:

Vassilis Tsotras
Ahmed Eldawy

Partners:
University of California, Riverside

Funding Agency:

NSF CCRI: ENS: Collaborative Research

Project Summary:

The origins of this work go back a decade, to 2009, when a team of database researchers from three UC campuses (UCI, UCR and UCSD) first embarked on the NSF-funded ASTERIX research project. Their goal at the time was to improve database storage and queries by bringing parallel database technology to bear on the emerging new (at the time) world of “Big Data.” The result, now an Apache project, is the only open-source parallel NoSQL database system available today.

Apache AsterixDB is a highly scalable Big Data Management System (BDMS) that stores, indexes and manages large volumes of structured and/or semi-structured data. At the same time, it supports a full query language with the expressiveness of SQL and more. This project continues Apache AsterixDB’s development as a resource for the NSF Computer and Information Science and Engineering (CISE) research community by working on a variety of enhancements, including improved text handling and query processing, additional standard-based geospatial data support, new user-defined function support for user-provided logic, and enhanced system storage and indexing capabilities.

The planned improvements will “benefit the broader public by providing a general-purpose foundation for extracting high-value insights from high-volume, low-value big data in areas such as public safety and health.”

Health State Estimation

Developing estimation techniques for determining health states

Developing estimation techniques for determining health states Contact Person:

Ramesh Jain

Other PIs/Investigators/PhD students:

Nitish Nag
Vaibhav Pandey

Project Summary:

Current Healthcare systems are focused on diseases, not health. We adopt and build on the perspective that a body is characterized by its health state. Disease is just a name give to an undesirable health state. This perspective is essential for chronic diseases where health state is slowly building up to the emergency situation. If we can track health state using inexpensive, maybe low precision but continuous sensors then we can understand deteriorating health state much before the emergency situation. Moreover, one can aspire to have a better health state as a goal to improve their quality of life. Health state is then use to provide correct lifestyle and medication (if needed) guidance to people to guide in achieving their health goals.

We are actively working on developing estimation techniques for determining health states.

Publications:

– Nitish Nag, Health State Estimation. CoRR abs/2003.09312 (2020)
– Vaibhav Pandey, Nitish Nag, Ramesh C. Jain, Continuous Health Interface Event Retrieval. CoRR abs/2004.07716 (2020)

iHurt

Intelligent and Automatic Pain Assessment Tool Employing Behavioral and Physiologic Indicators

Intelligent and Automatic Pain Assessment Tool Employing Behavioral and Physiologic Indicators Contact Person:

Amir M. Rahmani

Other PIs/Investigators/PhD students:

Kai Zheng
Nikil Dutt
Ariana Nelson
Pasi Liljeberg
Sanna Salanera
G.P. Li

Partners:
TYKS Hospital and UCI Medical Center

Funding Agency:

Academy of Finland

Project Summary:

Pain is an unpleasant sensory and emotional experience associated with actual or potential tissue damage or described in terms of such damage. It is a subjective sensation and patients’ self-report is considered the most reliable indicator of pain. However, assessment of pain is particularly difficult when the ability of the patient to communicate is limited or impossible e.g. during critical illness, under sedation and anesthesia or for infants. The objective of this project is to benefit from the offered features of the IoT and sensor networks to provide an automatic tool which can detect and assess pain employing behavioral and physiologic indicators such as facial muscle activity, heart rate, blood pressure, and breathing rate. The aim of this project is to develop a system based on the Internet of Things to detect and assess pain in a reliable and objective way by enabling the pain diagnoses in the case when the patient is unable to communicate and express the pain sensations.

Publications:

– Emad Kasaeyan Naeini, Mingzhe Jiang, Elise Syrjälä, Michael-David Calderon, Riitta Mieronkoski, Kai Zheng, Nikil Dutt, Pasi Liljeberg, Sanna Salanterä, Ariana Nelson, Amir M Rahmani, “A Prospective Study Evaluating a Pain Assessment Tool in Postoperative Environment: A Protocol for Algorithm Testing and Enhancement,” JMIR Research Protocols Jorunal, 2020.
– Mingzhe Jiang, Riitta Mieronkoski, Elise Syrjälä, Arman Anzanpour, Virpi Terävä, Amir M. Rahmani, Sanna Salanterä, Riku Aantaa, Nora Hagelberg, and Pasi Liljeberg, “Acute pain intensity monitoring with the classification of multiple physiological parameters,” Springer – -Journal of Clinical Monitoring and Computing (Springer-JCMC), 2018.
– Geng Yang, Mingzhe Jiang, Wei Ouyang, Guangchao Ji, Amir M. Rahmani, Pasi Liljeberg, and Hannu Tenhunen, “IoT-based Remote Pain Monitoring System: from Device to Cloud Platform,” IEEE Journal of Biomedical and Health Informatics (IEEE-JBHI), 2017.
– Emad Kasaeyan, Sina Shahhosseini, Ajan Subramanian, Tingjue Yin, Amir M. Rahmani, and Nikil Dutt, “An Edge-Assisted and Smart System for Real-Time Pain Monitoring,” IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE’19), 2019, USA.
– Mingzhe Jiang, Riitta Mieronkoski, Amir M. Rahmani, Nora Hagelberg, Sanna Salanterä, and Pasi Liljeberg, “Ultra-Short-Term Analysis of Heart Rate Variability for Real-time Acute Pain Monitoring with Wearable Electronics,” IEEE International Conference on Bioinformatics and Biomedicine (BIBM’17), 2017, USA.

Sleep EEG for TBI

Novel computation and acquisition of sleep EEG as a biomarker of traumatic brain injury (TBI)

Novel computation and acquisition of sleep EEG as a biomarker of traumatic brain injury (TBI) Contact Person:

Hung Cao

Other PIs/Investigators/PhD students:

Nikil Dutt
Amir M. Rahmani
Miranda Lim
Manoj Vishwanath
Ikhwan Shin
Salar Jafarlou

Project Summary:

The central goal of this collaborative project is to innovate novel computational approaches in order to understand persistently disrupted brain physiology sustained after mild traumatic brain injury (mTBI). Unique translational approaches will utilize massive electroencephalography (EEG) data during sleep and wakefulness in mice with TBI, in direct comparison with massive data collected from overnight polysomnography (PSG – EEG and other physiological signals) from human subjects with TBI. The investigative team will test novel approaches to EEG data preprocessing and normalization and apply transfer learning from mouse to human EEG data, in order to generate the most relevant, cross-species brain biomarkers of TBI.

Publications:

– Manoj Vishwanath, Salar Jafarlou, Ikhwan Shin, Miranda M. Lim, Nikil Dutt, Amir M. Rahmani, Hung Cao, “Investigation of Machine Learning Approaches for Traumatic Brain Injury Classification via EEG Assessment in Mice”, MDPI Sensors 2020, 2020.
– Manoj Vishwanath, Salar Jafarlou, Ikhwan Shin, Nikil Dutt, Amir M. Rahmani, Miranda Lim, Hung Cao, “Classification of Mild Traumatic Brain Injury in a Mouse Model Using Machine Learning Approaches”, 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2020.

Fetal and Maternal Care

IoT-based Wearables for Antepartum and Intrapartum Assessment in the Home Setting to Promote Fetal and Maternal Care

IoT-based Wearables for Antepartum and Intrapartum Assessment in the Home Setting to Promote Fetal and Maternal Care Contact Person:

Hung Cao

Other PIs/Investigators/PhD students:

Nikil Dutt
Amir M. Rahmani
Yuqing Guo
Bernard Choi
Zhou Li
Khuong Vo
Afshan Hameed

Project Summary:

This project develops novel tools and leverage cutting-edge technologies in bioelectronics and data science to improve fetal and maternal care for early prenatal, antepartum and intrapartum periods. Specifically, it develops novel abdominal patches with secure telecommunication for fetal ECG monitoring, novel wearables and schemes to continuously monitor maternal blood pressure (mBP), and an app and secured cloud to collect and analyze data.

D-CCC

Digital Health for Future of Community-Centered Care

Digital Health for Future of Community-Centered Care Contact Person:

Amir M. Rahmani

Other PIs/Investigators/PhD students:

Adey Nyamathi
Nikil Dutt
Pramod Khargonekar

Funding Agency:

NSF – Future of Work at the Human-Technology Frontier program

Project Summary:

The adhoc nature of the healthcare system in the USA necessitates an organized and affordable platform to increase the reach and services to the majority of the population. Currently, caregivers provide critical medical assistance in a community setting, particularly for elderly, disabled and vulnerable populations. Several states including California employ a community healthcare worker (CHW) initiative as an alternative to registered health care professionals to extend the reach of home-delivered services. While there is a critical need to scale and personalize these services, it faces significant challenges in the face of the increasing number of elderly, disabled and vulnerable communities requiring medical assistance, coupled with low wages for caregivers and rapidly increasing demands for skilled labor. The existing community-centered care (CCC) model is led by registered nurses (RNs) who train and supervise the CHWs, who in turn provide the necessary care for the community. This CCC model suffers from an inability to scale in a cost-effective manner while providing personalized and quality care for the community. The project proposes the digital health enabled community-centered care (D-CCC) model to transform the manual, restricted, and unstructured state of the current community healthcare landscape into a scalable, digital, and automated space.

Family Caregiver

A Monitoring-Intervention System for Dementia Caregivers Using Wearable IoT

A Monitoring-Intervention System for Dementia Caregivers Using Wearable IoT Contact Person:

Jung-Ah Lee

Other PIs/Investigators/PhD students:

Amir Rahmani
Nikil Dutt
Sina Labbaf
Anthony Park
Grace (Eunae) Ju

Partners:
Alzheimer’s Association Orange County Chapter, Alzheimer’s Orange County, Family Caregiver Resource Center, Council of Aging, Korean Community Services Health Center, and Southland Integrated Services, Inc

Project Summary:

Our program aims to build caregiving and stress-management skills in family caregivers of persons with dementia or mild cognitive impairment. The study involves remote monitoring using wearable sensors, home visits, and follow-ups. This research is led by Dr. Jung-Ah Lee (https://faculty.sites.uci.edu/caregiverstudy/).

Publications:

– Jung-Ah Lee, Anthony Park, and Amir M. Rahmani, “Sleep Duration and Quality in Dementia Caregivers: Wearable Iot Technology,” Western Institute of Nursing’s 52nd Annual Communicating Nursing Research Conference (WINURSING’20), 2020, USA.
– Jung-Ah Lee, Sina Labbaf, Amir M. Rahmani, Priscilla Kehoe, and Nikil Dutt, “Wearable Internet-of-Things Technology: An Immigrant Dementia Caregivers Pilot Intervention,” The Alzheimer’s Association International Conference (AAIC’19), 2019, USA.
– Jung-Ah Lee, Kajung Hong, Jessica Borelli, and Amir M. Rahmani, “A Culturally Sensitive Dementia Family Caregiver Pilot Study,” Western Institute of Nursing’s 52nd Annual Communicating Nursing Research Conference (WINURSING’19), 2019, USA.

HillSide

Supporting adolescents struggling with emotional regulation using wearable technologies

Supporting adolescents struggling with emotional regulation using wearable technologies Contact Person:

Melissa Pinto

Other PIs/Investigators/PhD students:

Ramesh Jain
Amir Rahmani
Nikil Dutt
Amy Greenblatt
Adam Silberman

Partners:
Hillside of Atlanta

Project Summary:

Emotion regulation skills are critical for adaptation to stressful life events and are particularly important in adolescence, as it is traditionally a time of emotional volatility. Difficulties in emotional regulation are associated with problems performing daily activities, poor mental health, and suicide—a leading cause of death among young people in the United States. Changes in daily activity and physiology have shown to correspond with fluctuations in one’s emotional experience. Wearable sensor technology and mobile applications now make it possible to continuously capture and create a record of one’s daily activities and physiological responses. We are fortunate to have a research partnership with Hillside Inc., a preeminent behavioral health treatment center in Atlanta, Georgia, that treats adolescents struggling with emotional regulation. Data captured by Personicle will be used to describe patterns of behavior and physiological responses as they relate to adolescents’ emotional experiences. Identification, monitoring, and intervention to help adolescents improve emotional regulation in real-time, as they become dysregulated, is predicated on our ability to characterize these patterns of adolescents’ emotional experiences. Findings will inform our future work that will focus on increasing adolescents’ ability to attune to behavioral and physiological cues, serving as prompts for adolescents to use emotion regulation skills.

PERSONILCE for mental health promotion during COVID-19

Holistic Stress Reduction in the Era of COVID-19 through Multimodal Personal Chronicles in College Students

Holistic Stress Reduction in the Era of COVID-19 through Multimodal Personal Chronicles in College Students Contact Person:

Jessica Borelli

Other PIs/Investigators/PhD students:

Amir Rahmani
Nikil Dutt
Ramesh Jain
Sina Labbaf
Amir Hossein Aqajari
Asal Yunusova
Alexander Rivera

Project Summary:

The COVID-19 pandemic has introduced a variety of challenging circumstances on college campuses, including the need for social distancing (resulting in the potential for social isolation and loneliness), anxiety regarding infection, and uncertainty regarding the future. Chronic stress exposure leads to long-term adverse mental health outcomes such as depression, anxiety, self-harm, suicidality, and addiction. Emerging adulthood is a risky period of development during which rates of mental disorders increase dramatically, changes which may in part be due to rapid shifts in roles, a lack of structure in daily routines, and relative immaturity of brain structures. Stress management and reduction are crucial capacities for young adults since they often experience high-intensity negative emotions and lack the maturity required to exert top-down control over these intense emotional experiences. This project builds capacity in a holistic stress reduction strategy combining emerging wearable Internet of Things (IoT) technologies with a multi-modal lifelogging framework.

PERSONICLE for tracking COVID-19 infection

Remote social interaction monitoring to predict the risk of novel coronavirus infection in the UCI community

Remote social interaction monitoring to predict the risk of novel coronavirus infection in the UCI community Contact Person:

Daniel Parker

Other PIs/Investigators/PhD students:

Ramesh Jain
Amir Rahmani
Nikil Dutt
Sanghyuk Shin
Saahir Khan

Project Summary:

In this project, we will investigate how COVID-19 risk is shaped by social contacts and geographic activity spaces in the University of California, Irvine (UCI) community. We hypothesize that there will be fatigue associated with social distancing efforts over time, whereby people cease to isolate themselves from others, resulting in a growth in the average number of social contacts and in the geographic spaces that are traversed daily. We also hypothesize that this eventual expansion of human contacts will result in an increased risk of acquiring COVID-19, relating directly to the number of contacts and the size of the activity space of individuals. We will use smart multi-modal personal lifelogging and remote monitoring technology, Personicle, together with wearable sensors for this purpose.

Food Computing

Food Computing Contact Person:

Ramesh Jain

Other PIs/Investigators/PhD students:

Nikil Dutt
Amir Rahmani
Ali Rostami
Vaibhav Pandey

Partners:
Kaloric, Lancaster University, NUS - National University of Singapore, Simula Research Laboratory, TU Wien, and University of Tokyo

Project Summary:

Food determines the quality of life. Food is not only a major source of energy and nutrients essential for health but is also the most important source of personal enjoyment and social glue. Interestingly, what a person enjoys eating is not necessarily related to what her body is happy to see him/her eat. This is evident from the large increase in diet-related diseases such as obesity, diabetes, and hypertension. People working on improving enjoyment have largely ignored the sustenance and vice versa.

Food computing applies computational approaches for addressing issues in health, biology, gastronomy, food processing, food distribution, and agronomy. This exhaustive and inclusive approach to food computing will help understand different aspects of the food ecosystem and relationship among them from the overall food perspective.

Publications:

– Weiqing Min, Shuqiang Jiang, Linhu Liu, Yong Rui, Ramesh Jain, “Food Computing”, ACM Computing Surveys, 52(5):1-36, September, 2019.
– Weiqing Min, Shuqiang Jiang, and Ramesh Jain, ‘Food Recommendation: Framework, Existing Solutions, and Challenges, IEEE Trans on Multimedia, November 2019.

PE-IoT

Policy driven Privacy Enhanced Technologies (PET) enforcement on Internet of Things (IoT) data flows

Policy driven Privacy Enhanced Technologies (PET) enforcement on Internet of Things (IoT) data flows Contact Person:

Sharad Mehrotra

Other PIs/Investigators/PhD students:

Nalini Venkatasubramanian
Shantanu Sharma
Roberto Yus
Sameera Ghayyur
Primal Pappachan
Guoxi Wang

Project Summary:

IoT service provision commonly relies on environmental or user data from other data  providers(e.g. network provider, water agency, building management). However, different privacy laws and regulations such as European General Data Protection Requirement (GDPR) and California Consumer Privacy Act (CCPA) have made it mandatory for service providers to provide the users with capabilities to express privacy requirements on their data consumed by the services. Policies have emerged as an important mechanism for specification of privacy requirements and Privacy Enhancing Technologies (PETs), such as differential privacy, data scrubbing and encryption technologies, are different ways to realize the privacy needs expressed in policies. PE-IoT (Privacy Enhanced-Internet of Things) controls data captured by IoT sensors to services after applying appropriate PETs to their data flows. PE-IoT constructs different workflows for the incoming data from various IoT sensors depending on the policies set by users and data managers. In these data workflows, the data may undergo different transformations depending on the choice of PETs expressed in the privacy policies. PE-IoT, in addition to exploring a variety of PETs and policy mechanism that apply to sensor data streams, explores issues of performance, reliability and fault tolerance when processing sensor data streams

High-Dimensional Inference beyond Linear Models

High-Dimensional Inference beyond Linear Models Contact Person:

Bin Nan

Other PIs/Investigators/PhD students:

Yi Li
Lu Xia
Bingqing Hu

Funding Agency:

NSF

Project Summary:

This project concerns making proper statistical inference for high-dimensional parameters in three sets of widely used regression models: (i) generalized linear models; (ii) Cox models for censored univariate, multivariate, or clustered survival data; and (iii) functional regression with three-dimensional functional inputs. The current literature has primarily focused on linear regression models with high-dimensional covariates. One type of method is the so-called post-selection inference conditional on the selected model. Another type of method parallel to post-selection inference is to correct the biases of lasso estimates in the full model, the so-called de-biased lasso or de-biased lasso, which has been shown to possess nice theoretical and numerical properties in linear regression models. The assumptions for de-biased lasso in linear models have been directly applied to nonlinear models, e.g., generalized linear models and the Cox model for survival data, in the current literature. We find, however, that the key sparsity assumption for the inverse expected Hessian matrix hardly holds even when the precision matrix of the covariates is indeed sparse, an important sufficient condition for the de-biased approach to work in linear regression models. In this project, we will investigate new methods that we call refined de-biased methods for all three different sets of models mentioned above by further de-biasing without imposing the sparsity matrix assumption. Each set of models possesses its unique challenges.

Cutting Edge Survival Methods for Epidemiological Data

Cutting Edge Survival Methods for Epidemiological Data Contact Person:

Bin Nan

Other PIs/Investigators/PhD students:

Yi Li
Jimmy Kwon
Yue Wang

Funding Agency:

NIH

Project Summary:

The main theme of the research is to develop new methodologies for resolving statistical issues emerging from our team’s long-term collaborations in cohort studies of aging populations and patients with kidney disease. We focus on developing robust and efficient estimating procedures for regression parameters from data with delayed entry in prevalent cohort studies, making appropriate and efficient statistical inference when covariates are subject to censoring and measurement error, and developing new strategies that best model the effects of terminal events on longitudinal measurements. We also plan to develop publicly available statistical software with the goal of dissemination and generalization.

Lightweight social support

Using self-tracked data to design lightweight social support

Using self-tracked data to design lightweight social support Contact Person:

Daniel Epstein

Other PIs/Investigators/PhD students:

Stephen Schueller

Project Summary:

People often struggle to receive the support they desire from friends and families around their health behavior goals. We are examining how lightweight social media platforms where people share mundane, daily updates like Snapchat and story features on Instagram and Facebook can provide opportunities for such support as people struggle to incorporate healthy eating choices or physical activity into their routines. Following on preliminary surveys on understanding how to present tracked health and wellness data on these platforms, we are building and deploying an app to allow people to share this data on their own social media.

Optimizing Digital Interventions through Micro-Randomized Trials and Causal Modeling

Optimizing Digital Interventions through Micro-Randomized Trials and Causal Modeling Contact Person:

Tianchen Qian

Project Summary:

The development in smartphone and wearable technology now makes it possible to deliver digital health interventions to individuals in real time. These interventions include notifications and reminders for physical activity, stress management exercises, etc. To optimize such digital health interventions and to reduce user burden, it is crucial to understand when, under what circumstances, and what intervention is more effective. Micro-randomized trials (MRT) is an experimental design to answer these questions. In a MRT, each user is repeatedly randomized to various versions of the digital intervention for often hundreds or thousands of times. In this project we develop causal inference methods for analyzing MRT data, in order to understand the time-varying causal effect of the interventions and how such effect interacts with user’s contextual information. The results can be used to optimize the delivery and content of the interventions.

Publications:

– Tianchen Qian, Hyesun Yoo, Predrag Klasnja, Daniel Almirall, and Susan A. Murphy. Estimating time-varying causal excursion effect in mobile health with binary outcomes. Biometrika (2020)

– Tianchen Qian, Michael Russell, Linda Collins, Predrag Klasnja, Stephanie Lanza, Hyesun Yoo, and Susan A. Murphy. The Micro-Randomized Trial for Developing Digital Interventions: Data Analysis Methods. https://arxiv.org/abs/2004.10241

CRADLE Study

CRADLE Study Contact Person:

Jessica Borelli

Other PIs/Investigators/PhD students:

Amir M. Rahmani
Sina Labbaf

Partners:
Children's Hospital Orange County (CHOC)

Project Summary:

The goal of this study is to test the impact of a brief, strengths-based intervention program designed to help parents of infants receiving care in the neonatal intensive care unit (NICU) at Children’s Hospital Orange County (CHOC) bond with their infants during and following their hospital stay. The intervention is assisted via an app-based delivery of the intervention, allowing parents to practice the skills they have learned for reflecting on moments of positive connection with their infants.

Life Skills Study

Life Skills Study Contact Person:

Uma Rao

Funding Agency:

NIH

Project Summary:

Adolescents face many challenges as they begin to gain autonomy from parents and prepare for adult roles in society and, in particular, African-American (AA) youth experience unique challenges. For example, even though youth from all racial/ethnic backgrounds experiment with alcohol/drugs, AA youth are more likely to face legal consequences due to social inequalities. Our team has developed a family intervention that specifically helps AA youth to develop life skills focusing on future orientation and in overcoming “road blocks” in the service of these long-term positive goals. This is a 6-week, parent-child program shown to deter/delay risky behaviors and achieve long-term positive outcomes in randomized controlled studies.

In the current research study, we are trying to identify brain networks associated with youth protective factors resulting in positive response to the intervention. The adolescent brain is highly plastic and undergoes significant remodeling, and a better understanding of the brain network changes will help us to fine-tune the intervention program or develop alternative strategies for those who don’t show significant benefit. We are recruiting 11-14-year-old African-Americans (both boys and girls) and performing MRI scans (no radiation involved) before and after the above-described family intervention.

Brain Development Study

Brain Development Study Contact Person:

Uma Rao

Other PIs/Investigators/PhD students:

Marie L. Gillespie
Akul Sharma
Theo G.M. van Erp

Partners:
Children's Hospital Orange County (CHOC)

Funding Agency:

NIH

Project Summary:

Research has indicated that depressive illness is the second leading cause of disability worldwide, and it frequently begins in adolescence and persists into adult life. Childhood trauma has long-term consequences and increases the risk for depression. Both clinical experience and research have indicated that depression resulting from childhood trauma is more severe and shows poorer responses to treatments. There is some evidence from our lab and others that the brain networks may be different in this type of depression compared to other causes. A better understanding of these differences can be helpful in developing more effective prevention and treatment programs for individuals with childhood trauma (both medical and non-medical therapies).

In the current research study, we are recruiting 13-17 year-olds (with and without depression, with and without childhood trauma). We will perform MRI scans (no radiation is involved) to carefully study the brain networks in these two forms of depression and compare them with normal adolescent brain developmental changes. Also, we would like to study brain networks in youth who experienced childhood trauma but did not develop depression to better understand the protective mechanisms.

Dietary Patterns Study

Dietary Patterns Study Contact Person:

Uma Rao

Other PIs/Investigators/PhD students:

Tomas Zurita
Kelly F. M. Kazmierski
Larissa Wong
Megan Faulkner
Sabrina Kuo
Heather Huszti

Partners:
Children's Hospital Orange County (CHOC)

Funding Agency:

NIH

Project Summary:

Obesity is a major problem in our society resulting in a variety of physical and mental health problems. Adolescent development is associated with significant behavioral and biological changes that can lead to persistent obesity into adult life. In particular, African-American (AA) and Hispanic/Latina (HL) females have high rates of obesity compared to their Non-Hispanic White (NHW) counterparts. Research has indicated that this is not merely due to differences in socioeconomic status. AA and HL experience significant chronic (ongoing) stressors which can alter eating behavior activity levels, fat distribution and metabolic hormones, resulting in obesity and associated health problems.

In the current research study, we are examining social and biological stress in 13-17 year-old AA, HL, and NHW females (normal weight, overweight and obese). Additionally, we are studying eating patterns and activity levels in the home environment and in a controlled laboratory setting as well as body composition (muscle mass and fat distribution) and metabolic hormones. To our knowledge, this is the first study to carefully examine the role of stress in determining racial differences in obesity rates. If our results confirm the influential role of stress, we aim to develop interventions and advocate for public policy changes to address social and biological stress in addition to nutrition and exercise (currently the primary focus in clinical and public policy programs).

Fertility apps

Understanding life events and transitions supported by fertility apps

Understanding life events and transitions supported by fertility apps Contact Person:

Daniel Epstein

Other PIs/Investigators/PhD students:

Yunan Chen

Project Summary:

Women’s health needs change over the course of life, transitioning between health stages and goals such as menarche, pregnancy or avoidance, and menopause. We sought to understand the extent to which fertility and health tracking apps support these life stages and the transitions between them. We find that oftentimes these apps support the “typical” cases reasonably well (healthy people in their 20’s and 30’s), but miss the transition needs of younger and older people or people with other challenges (e.g., infertility). We find a need to design tools which are more integrative, bringing together data from varied sources to help support more holistic tracking.

Mood tracking

Examining and designing more useful mood tracking tools

Examining and designing more useful mood tracking tools Contact Person:

Daniel Epstein

Project Summary:

People are widely adopting apps for tracking their moods and emotions. We aim to understand how and why these apps are being used and whether they are providing the benefit people desire. Early findings suggest a mismatch between how often people tend to open mood tracking apps (about once a day) and what mood tracking apps support journaling (mood in the moment). We are beginning to examine how these findings may support the design of an effective once-a-day mood tracking app.

Food Journaling

Examining a Multimodal Approach to Lowering the Burden of Food Journaling

Examining a Multimodal Approach to Lowering the Burden of Food Journaling Contact Person:

Daniel Epstein

Funding Agency:

NSF CRII

Project Summary:

People use personal journaling methods to develop better habits and make informed decisions about health and well-being. Activities such as food journaling become burdensome, inaccurate, or incomplete over time due to poor design of supportive devices and single-platform constraints. In this project, the investigator plans to use internet-of-things (IoT) functionality to develop a system with integrated and multimodal input capabilities to support food journaling. An integrated device platform will be developed to support data input from multiple devices such as smart phones, wearables, and laptops. An iterative, user-centered design methodology will be applied. Prospective users will be selected for usability studies, and the prototype will be validated by comparing multimodal IoT-enabled food journaling to other common food journaling applications. Benefits include more usable technologies for personal journaling to support mental and physical health, stress management, and personal wellbeing. This project will center around two participatory design investigations. The research team (1) will examine how people with healthy eating goals use lightweight technology probes developed for journaling food via voice description, photography, or text description. This probe deployment will inform recommendations for how platforms can support collecting data collaboratively across input modalities. These recommendations, and an iterative design process to improve usability, will inform a full-featured multimodal food journaling tool. The research team (2) will then compare the developed tool against design strategies typical of commercial and research food journals, again with people who have healthy eating goals. The comparison will be mixed-methods, combining perceptions of the value and burden of the technology through validated survey instruments with semi-structured interviews discussing the challenges of each approach.

The long-term impact of light intervention on sleep physiology and cognition in mild cognitive impairment

The long-term impact of light intervention on sleep physiology and cognition in mild cognitive impairment Contact Person:

Sara Mednick

Other PIs/Investigators/PhD students:

Mariana Figueiro

Partners:
Rensselaer Polytechnic Institute

Funding Agency:

NIH R01

Project Summary:

This application proposes to investigate the impact of a long-term lighting treatment on sleep physiology and sleep-dependent cognitive processes in MCI and mild AD patients. We hypothesize that a long-term (6-month) lighting intervention technology (LIT) designed to promote circadian entrainment will improve sleep and, thus cognition. We also hypothesize that LIT will improve depression and quality of life (QoL).

The Pharmacological Enhancement of Sleep for Memory Improvement

The Pharmacological Enhancement of Sleep for Memory Improvement Contact Person:

Sara Mednick

Funding Agency:

NIH R01

Project Summary:

The central aim of this application is to use pharmacological intervention to address the specificity of sleep-dependent memory with respect to 1) sleep feature (i.e., sleep spindles vs. other sleep features), 2) memory domain (i.e. declarative vs. non-declarative), and 3) pharmacological agents (i.e., zolpidem (GABAa) vs. sodium oxybate (GABAb) vs. placebo).

The Impact of Sex Hormones on Sleep-Dependent Memory in Young and Midlife Men and Women

The Impact of Sex Hormones on Sleep-Dependent Memory in Young and Midlife Men and Women Contact Person:

Sara Mednick

Other PIs/Investigators/PhD students:

Fiona Baker

Partners:
Stanford Research Institute

Funding Agency:

NIH R01

Project Summary:

The major goals of this project are to determine lifespan developmental mechanisms of sex and sex hormone and their impact on memory in young and midlife and older women, and use a novel sleep-boosting intervention to further understand the potential protective role of sleep against cognitive decline.

SLIM

Supporting Lifestyle Change in Obese Pregnant Mothers through Wearable Internet-of-Things

Supporting Lifestyle Change in Obese Pregnant Mothers through Wearable Internet-of-Things Contact Person:

Amir M. Rahmani

Other PIs/Investigators/PhD students:

Pasi Liljeberg
Anna Axelin
HannaKaisa Niela-Vilen
Iman Azimi
Johanna Saariko
Fatemeh Sarhaddi
Jennifer Auxier

Partners:
TYKS Hospital

Funding Agency:

Academy of Finland

Project Summary:

Pregnant women with obesity have indisputably increased risk for gestational diabetes mellitus, depression, miscarriage, and preterm birth, just to mention few. These pregnancy complications clearly have negative effects on their unborn children. Due to the magnitude of this global challenge it calls for immediate action. During the course of this project, an Internet-of-Things-based intelligent monitoring system will be developed to detect and predict obesity-related pregnancy complications as early as possible. Cybernetic health concept will be utilized by intertwining lifestyle and environmental data together with bio-signals associated with medical knowledge to develop a closed-loop system to make maternity care more effective, dynamic and end-user driven. This is done via a platform that leverages portable devices and inexpensive wearable sensors, coupled with a multimodal event modeling, activity recognition, and life-logging engine. This research will deliver a ubiquitous pregnancy monitoring service to end-users, mothers, and healthcare providers, enabling pregnancy events detection, prediction, assessment, and prevention.

Publications:

– Kirsi Grym, Hannakaisa Niela-Vilen, Eeva Ekholm, Lotta Hamari, Iman Azimi, Amir M. Rahmani, Pasi Liljeberg, Eliisa Löyttyniemi, and Anna Axelin, “A Feasibility Study of Wearable Wristbands as a Measurement Tool during Pregnancy and One-month Postpartum,” BMC Pregnancy and Childbirth, 2019.
– Olugbenga Oti, Iman Azimi, Arman Anzanpour, Amir M. Rahmani, Anna Axelin, and Pasi Liljeberg, “IoT-based Healthcare System for Real-time Maternal Stress Monitoring,” in ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE’18), 2018, USA.
– Juho Laitala, Mingzhe Jiang, Elise Syrjälä, Emad Kasaeyan Naeini, Antti Airola, Amir M. Rahmani, Nikil Dutt, Pasi Liljeberg, “Robust ECG R-peak Detection Using LSTM”, The 35th ACM/SIGAPP Symposium On Applied Computing (SAC’20), 2020, Czech.

PREVENT

Preterm Birth Prevention in Everyday Settings

Preterm Birth Prevention in Everyday Settings Contact Person:

Amir M. Rahmani

Other PIs/Investigators/PhD students:

Pasi Liljeberg
Anna Axelin
HannaKaisa Niela-Vilen
Iman Azimi
Johanna Saariko
Fatemeh Sarhaddi

Partners:
TYKS Hospital

Funding Agency:

Academy of Finland

Project Summary:

Preterm birth (PTB) is the most common cause of neonatal deaths. Due to the high rate of PTBs (15M/y), it is extremely beneficial to identify the women at risk at an early stage and prevent PTB. Physiological parameters could help us to uncover and model multifactorial processes that lead to PTB. Continuous monitoring of such parameters holds significant promise to successful prevention. Internet of Things (IoT) technologies can be leveraged to create the ability to perform such monitoring throughout pregnancy. In this project, we tackle PTB issues by proposing an IoT platform tailored for PTB prevention for everyday settings. Our core contributions are 1) a customized architecture including a set of wearable electronic devices that are feasible for 7-9 months of continuous monitoring, 2) a personalized PTB prevention solution using artificial intelligence methods, and 3) a comprehensive performance assessment via the implementation of this monitoring in clinical trials.

Publications:

– Hannakaisa Niela-Vilen, Amir M. Rahmani, Pasi Liljeberg, and Anna Axelin, “Being ‘A Google Mom’ or Securely Monitored at Home – Perceptions of Remote Monitoring in Maternity Care,” Wiley’s Journal of Advanced Nursing, 2019.
– Iman Azimi, Olugbenga Oti, Sina Labbaf, Hannakaisa Niela-Vilen, Anna Axelin, Nikil Dutt, Pasi Liljeberg, and Amir M. Rahmani, “Personalized Maternal Sleep Quality Assessment: An Objective IoT-based Longitudinal Study,” IEEE ACCESS Journal (IEEE-ACCESS), 2019.
– Iman Azimi, Tapio Pahikkala, Amir M. Rahmani, Hannakaisa Niela-Vilen, Anna Axelin, and Pasi Liljeberg, “Missing Data Resilient Decision-making for Healthcare IoT through Personalization: A Case Study on Maternal Health,” Elsevier Journal of Future Generation Computer Systems (Elsevier-FGCS), 2019.

MSM

New Technologies and Chemical Culture: Examining Deployment and Effects Among MSM

Project Summary:

This project will examine how various chemical substances such as recreational drugs, prescribed drugs, steroids, and more impact the sexual health of gay men and other men who have sex with men (MSM) through online technologies. Despite unprecedented pharmaceutical advancements in HIV treatment and prevention, rates of transmission remain consistent and slightly increasing among MSM with almost half of all infections. Virtual space has come to dominate the space within which MSM meet for sexual encounters. In addition, this new venue for connecting people for sexual purposes is often fueled by various “chemical” influences. The proliferation of messaging relating to various chemicals in online technologies may be creating a “chemculture” among MSM. Through a critical qualitative design, this research explores the proliferation of chemculture through online technologies and how this relates to sexual health in the gay community.

Environmental threats to health

A prospective longitudinal study of environmental threats to public health

Project Summary:

In this project, we aim to determine the effect of environmental, community, and individual factors on differential trajectories of resilience – real-time physiologic stress, self-reported, physician-diagnosed (SRPD) mental health (anxiety, depression, post-traumatic stress disorder) and physical health (heart disease, diabetes, hypertension, etc.) ailments, and behavioral intentions – analyzed using a multi-level modeling approach with data from adults in several Gulf and Southeast Atlantic states. To determine the effect of an existing tailored risk communication intervention about the risks, impacts, and realistic behavioral adaptations associated with coastal environmental change on trajectories of resilience over time among respondents using wearable technology.

TBI

Development of a Community-based TBI Treatment Completion Intervention Among Homeless Adults

Project Summary:

Tuberculosis (TB) is a disease of poverty as it disproportionately affects impoverished communities. In the US, TB rates are unacceptably high among homeless persons who have a 10-fold increase in TB incidence as compared to the general population. In California, the rate of TB is more than twice the national case rate and recent TB outbreaks have been alarming. Given the complex health disparity factors that affect TBI treatment adherence among homeless persons, in this project, we will develop and pilot test an innovative, community-based directly observed intervention. Our innovative health promotion intervention program focuses on: 1) completion of TBI treatment, 2) reducing substance use; 3) improving mental health; and 4) improving critical social determinants of TB risk (unstable housing and poor health care access) among homeless adults in the highest TB prevalence area in Los Angeles.

Asha

Improving Health and Nutrition of Indian Women with AIDS and their Children

Project Summary:

The overall goal of this project is to enhance the physical and mental health of rural Indian women living with AIDS and their children. We achieve these goals through the use of trained village women as Accredited Social Health Activists (ASHA) to enhance the health of women and children through improved ART adherence, CD4 levels, and physical and mental health. Specific objectives include: we plan to assess the effects of nutrition training and/or food supplements on primary outcomes for rural women living with AIDS in improving body composition and immune status (CD4 levels) as assessed at 6-, 12- and 18-month follow-up. Examining the effects of the program arms and their interaction on adherence to ART, psychological health, nutritional adequacy, and lipid profile over time.

HCV

Prevention for Homeless At-Risk for HCV

Project Summary:

Compared to the general population, homeless persons have a 26-fold increase in Hepatitis C Virus (HCV) prevalence, a diagnosis strongly associated with injection drug use (IDU). Focused screening, early detection, and treatment for homeless adults are critical for effective treatment. In this project, we develop a theoretically-based innovative model of care among HCV-infected homeless persons by utilizing a community-based delivery approach.

Patient questions about their medical records and the implications for patient portal redesign

Patient questions about their medical records and the implications for patient portal redesign Contact Person:

Kai Zheng

Other PIs/Investigators/PhD students:

Christopher Longhurst
Andrew L. Rosenberg
Scott E. Rudkin

Project Summary:
Recent health IT policies (e.g., Meaningful Use), and initiatives such as OpenNotes, demand patients be provided with direct, electronic access to their medical records. In response, healthcare provider institutions have been increasingly offering online patient portals to place medical data at patients’ fingertips. Despite the increased availability, and research indicating high patient interest, portal adoption among patients remains unsatisfactory, and utilization rates surprisingly low. Several studies in the literature have pointed out that a key barrier to realizing the full potential of patient portals is the lack of useful information despite the abundance of data they make available. This proposed project will leverage patient posts in online health forums accompanied by data that appear to be directly copied/pasted (or transcribed) from their medical records, to generate insights into common questions that patients have about their data and how these questions get resolved through the collective wisdom of the online patient community. Such insights can, in turn, inform patient portal redesign to better accommodate patients’ data, information, and knowledge needs.
In this project, we will focus on a single online health forum, MedHelp.org, and a single type of medical data, laboratory test results, as an initial step toward follow-up investigations involving more online health forums and additional types of medical data (e.g. radiology reports). Through this pilot effort, we aim to first develop a set of computational algorithms that can reliably identify, interpret, and summarize the MedHelp posts of interest, as well as responses contributed by patient peers—particularly those selected as ‘best’ answer(s) by the patient who posted the question. Then, we will conduct a qualitative interview study with the decision-making teams that oversee patient portal implementation across three healthcare systems. The interviews will solicit participants’ feedback on the study findings based on MedHelp data, and how current patient portal design can be improved so that common patient questions regarding their medical data get resolved at the point of viewing. This study will establish necessary tools, and valuable experience, for future studies involving more online health information resources, more empirical sites, and creation of software prototypes incorporating the study findings. Ultimately, we hope to implement the redesigned patient portal system, and conduct experiments and controlled trials to evaluate patient acceptance of the new design and its impact on health literacy and patient outcomes.
Publications:

– Reynolds TL, Ali N, McGregor E, O’Brien T, Longhurst C, Rosenberg AL, Rudkin SE, Zheng K. Understanding patient questions about their medical records in order to improve patient portal design. AMIA Annu Symp Proc. 2017;1468–77. PMCID: PMC5977702

EHR-integrated decision support for judicious opioid prescribing

EHR-integrated decision support for judicious opioid prescribing Contact Person:

Kai Zheng

Other PIs/Investigators/PhD students:

Ariana Nelson
Mustafa Hussain
Tera Reynolds
Gregory Polston
Brent G Yeung
Lauren Sukumar

Partners:
UCI Medical Center and UCSD Medical Center

Project Summary:
Every day, 91 Americans die from opioid overdose. While the mortality rates for all other leading health causes have substantially decreased in the past several decades, the rates of mortality due to opioid overdose have quadrupled since 1999 in the U.S., now accounting for more than half of drug overdose deaths. In this opioid epidemic, prescription opioids are playing a central role: 1 in 10 patients with prescribed opioids became dependent on the drug; 4 in 5 of those using heroin started with legitimate opioid prescriptions; and many prescribed opioids are being diverted. In response, the CDC issued an opioid prescribing guideline calling for immediate actions to curb the epidemic and identify and treat those at risk.
However, implementing the CDC’s guideline recommendations, such as tapering-and-discontinuing, has proved to be difficult. For non-pain management specialists, it is often challenging to tell those in pain from those with dependence. Further, clinicians in primary care and the ED, the two settings where over half of all opioids are prescribed and dispensed, may have insufficient knowledge and experience in using non-opioid alternatives or managing those who have become dependent. Many clinicians therefore choose to dismiss drug-seeking patients, rather than offer them weaning regimens, citing suspicion of patient intent as a rationale. While it avoids the risk of malpractice lawsuits and even criminal charges, the CDC Guideline specifically advises against this practice, as rejected patients may then seek illicit opioids instead.
There have been efforts to develop informatics tools to address these issues. The Prescription Drug Monitoring Program (PDMP), for example, is a nationwide initiative to provide clinicians access to patients’ prescription and dispensing history of controlled substances. However, PDMP takes the form of a standalone application that is not integrated with electronic health records (EHR) and thus requires a separate authentication process, discouraging its routine use by busy clinicians. At UC Irvine Health and UC San Diego Health, we have an ongoing project to interface with PDMP to bring patients’ prescription and dispensing history of controlled substances into our EHR system. This project will support and augment this effort, by developing research-informed insights to help us identify an optimal way of integrating PDMP information and developing an effective, yet less cognitively demanding, computerized decision-support tool for managing opioid analgesics while catering to those in true needs. Once a functional prototype of the tool is developed, we will evaluate its usability and effectiveness using a cognitive psychology experiment approach by involving 100 3rd- and 4th-year UC Irvine medical students. Toward the end of the project, we will refine the design of the tool based on the experiment findings, and create a plan to implement it in the EHR and conduct further research studies to evaluate its clinical effectiveness in the field.
Publications:

– Hussain MI, Nelson AM, Yeung BG, Sukumar L, Zheng K. How the presentation of patient information and decision-support advisories influences opioid prescribing behavior: a simulation study. J Am Med Inform Assoc. 2020;27(4):613–20. PMID: 32016407

– Hussain MI, Reynolds TL, Zheng K. Medication safety alert fatigue may be reduced via interaction design and clinical role-tailoring: a systematic review. J Am Med Inform Assoc. 2019;26(10):1141–9. PMID: 31206159

– Hussain MI, Nelson A, Polston G, Zheng K. Improving the design of California’s prescription drug monitoring program. JAMIA Open. 2019;2(1):160–72. DOI: 10.1093/jamiaopen/ooy064