Yinan Sun

Dr. Yinan Sun

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 July 2025 in JAMIA Open
Verified
Journal Article
Open access
CSChristopher Slade
Christopher Slade
YSYinan Sun
Yinan Sun
WCWei Cheng Chao
Wei Cheng Chao
CCChih-Chun Chen
Chih-Chun Chen
RBRoberto Benzo
Roberto Benzo
Peter WashingtonPeter Washington
Peter Washington
Objective: Mobile and ubiquitous devices enable health data collection “in a free-living environment” to support applications such as remote patient monitoring and adaptive digital interventions using machine learning (ML). Despite their potential, significant data collection challenges persist, including issues related to user compliance with reporting data, passive data consistency, and authorization. This scoping review identifies and analyzes these challenges, focusing on barriers to effective data collection. Materials and Methods: We searched IEEE, ACM, and Web of Science for papers involving training ML models using both active and passive mobile sensing. We used the following search terms: “mobile OR ubiquitous”, “EMA”, “health”, “passive”, and “deep learning OR machine learning”. We only included papers that collected both passive and active data and excluded papers that used a pre-existing dataset. Results: A total of 77 studies met the inclusion criteria. These studies utilized smartphones, smartwatches, wearable devices, and environmental sensors for data collection. Several studies reported challenges with participant compliance in active data collection, while passive data collection faced data consistency and authorization issues. Efforts to address these challenges were documented in some but not all studies. Using this information, we outline current challenges and corresponding opportunities for data collection in mobile sensing studies. Discussion: ML techniques can reduce participant burden in active data collection by optimizing prompt timing, auto-filling responses, and minimizing prompt frequency. Simplified interfaces such as user-friendly smartwatch prompts can further improve compliance. For passive data collection, techniques such as optimization of recording times to preserve battery life and motivational techniques to encourage proper device use can increase data consistency. Conclusion: Mobile sensing offers opportunities for developing intelligent mobile health applications but faces data collection challenges with respect to factors such as compliance, consistency, and authorization. Innovations in ML and user interface design show promise for addressing these barriers.

7 February 2024 in JMIR Research Protocols
Verified
Journal Article
Open access
YSYinan Sun
Yinan Sun
AKAli Kargarandehkordi
Ali Kargarandehkordi
CSChristopher Slade
Christopher Slade
AJAditi Jaiswal
Aditi Jaiswal
GBGerald Busch
Gerald Busch
Peter WashingtonPeter Washington
Peter Washington
Background: Artificial intelligence (AI)–powered digital therapies that detect methamphetamine cravings via consumer devices have the potential to reduce health care disparities by providing remote and accessible care solutions to communities with limited care solutions, such as Native Hawaiian, Filipino, and Pacific Islander communities. However, Native Hawaiian, Filipino, and Pacific Islander communities are understudied with respect to digital therapeutics and AI health sensing despite using technology at the same rates as other racial groups. Objective: In this study, we aimed to understand the feasibility of continuous remote digital monitoring and ecological momentary assessments in Native Hawaiian, Filipino, and Pacific Islander communities in Hawaii by curating a novel data set of longitudinal Fitbit (Fitbit Inc) biosignals with the corresponding craving and substance use labels. We also aimed to develop personalized AI models that predict methamphetamine craving events in real time using wearable sensor data. Methods: We will develop personalized AI and machine learning models for methamphetamine use and craving prediction in 40 individuals from Native Hawaiian, Filipino, and Pacific Islander communities by curating a novel data set of real-time Fitbit biosensor readings and the corresponding participant annotations (ie, raw self-reported substance use data) of their methamphetamine use and cravings. In the process of collecting this data set, we will gain insights into cultural and other human factors that can challenge the proper acquisition of precise annotations. With the resulting data set, we will use self-supervised learning AI approaches, which are a new family of machine learning methods that allows a neural network to be trained without labels by being optimized to make predictions about the data. The inputs to the proposed AI models are Fitbit biosensor readings, and the outputs are predictions of methamphetamine use or craving. This paradigm is gaining increased attention in AI for health care. Results: To date, more than 40 individuals have expressed interest in participating in the study, and we have successfully recruited our first 5 participants with minimal logistical challenges and proper compliance. Several logistical challenges that the research team has encountered so far and the related implications are discussed. Conclusions: We expect to develop models that significantly outperform traditional supervised methods by finetuning according to the data of a participant. Such methods will enable AI solutions that work with the limited data available from Native Hawaiian, Filipino, and Pacific Islander populations and that are inherently unbiased owing to their personalized nature. Such models can support future AI-powered digital therapeutics for substance abuse. International Registered Report Identifier (IRRID): DERR1-10.2196/46493

3 December 2024 in AI
Verified
Journal Article
Open access
PDF file
SLShizhe Li
Shizhe Li
CFChunzhi Fan
Chunzhi Fan
AKAli Kargarandehkordi
Ali Kargarandehkordi
YSYinan Sun
Yinan Sun
CSChristopher Slade
Christopher Slade
Peter WashingtonPeter Washington
Peter Washington
Substance use disorders affect 17.3% of Americans. Digital health solutions that use machine learning to detect substance use from wearable biosignal data can eventually pave the way for real-time digital interventions. However, difficulties in addressing severe between-subject data heterogeneity have hampered the adaptation of machine learning approaches for substance use detection, necessitating more robust technological solutions. We tested the utility of personalized machine learning using participant-specific convolutional neural networks (CNNs) enhanced with self-supervised learning (SSL) to detect drug use. In a pilot feasibility study, we collected data from 9 participants using Fitbit Charge 5 devices, supplemented by ecological momentary assessments to collect real-time labels of substance use. We implemented a baseline 1D-CNN model with traditional supervised learning and an experimental SSL-enhanced model to improve individualized feature extraction under limited label conditions. Results: Among the 9 participants, we achieved an average area under the receiver operating characteristic curve score across participants of 0.695 for the supervised CNNs and 0.729 for the SSL models. Strategic selection of an optimal threshold enabled us to optimize either sensitivity or specificity while maintaining reasonable performance for the other metric. Conclusion: These findings suggest that Fitbit data have the potential to enhance substance use monitoring systems. However, the small sample size in this study limits its generalizability to diverse populations, so we call for future research that explores SSL-powered personalization at a larger scale.

2 November 2024 in Information
Verified
Journal Article
Open access
PDF file
SGStanislava Gardasevic
Stanislava Gardasevic
AJAditi Jaiswal
Aditi Jaiswal
MLManika Lamba
Manika Lamba
JFJena L Funakoshi
Jena L Funakoshi
KCKar-Hai Chu
Kar-Hai Chu
Peter WashingtonPeter Washington
Peter Washington
Social network analysis (SNA), or the application of network analysis techniques to social media data, is an increasingly prominent approach used in computational public health research. We conducted a systematic review to investigate trends around SNA applied to social media data for public health and epidemiology while outlining existing ethical practices. Following PRISMA guidelines, we reviewed articles from Web of Science and PubMed published between January 2019 and February 2024, leading to a total of 51 papers surveyed. The majority of analyzed research (69%) involved studying Twitter/X, followed by Sina Weibo (16%). The most prominent topics in this timeframe were related to COVID-19, while other papers explored public health topics such as citizen science, public emergencies, behavior change, and various medical conditions. We surveyed the methodological approaches and network characteristics commonly employed in public health SNA studies, finding that most studies applied only basic network metrics and algorithms such as layout, community detection, and standard centrality measures. We highlight the ethical concerns related to the use of social media data, such as privacy and consent, underscoring the potential of integrating ethical SNA with more inclusive, human-centered practices to enhance the effectiveness and community buy-in of emerging computational public health efforts.

23 September 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YSYinan Sun
Yinan Sun
AJAditi Jaiswal
Aditi Jaiswal
CSChristopher Slade
Christopher Slade
KPKristina T Phillips
Kristina T Phillips
RBRoberto Benzo
Roberto Benzo
Peter WashingtonPeter Washington
Peter Washington
Background: Ecological momentary assessment (EMA) involves repeated prompts to capture real-time self-reported health outcomes and behaviors via mobile devices. With the rise of mobile health (mHealth) technologies, EMA has been applied across diverse populations and health domains. However, the extent to which EMA engagement and data quality vary across social determinants of health (SDoH) remains underexplored. Emerging evidence suggests that EMA adherence and data completeness may be sometimes associated with participant characteristics such as socioeconomic status, race/ethnicity, and education level. These associations may sometimes influence who engages with EMA protocols and the types of contextual data captured. Despite growing interest in these patterns, no review to date has synthesized evidence on how SDoH relate to EMA compliance and engagement. Objective: We conducted a scoping review to study two research questions: (R1) how EMA compliance rates in health studies can differ across SDoH and (R2) what types of SDoH have been identified through EMA health studies. Methods: Following PRISMA-ScR guidelines, we searched PubMed, Web of Science, and EBSCOhost using two sets of queries targeting EMA and its relationship to SDoH. Eligible studies were peer reviewed, were published in English between 2013 and 2024, and used mobile-based EMA methods. Studies were included if they (1) reported on differences in EMA compliance by SDoH or (2) reported at least one SDoH observed or uncovered during an EMA study. We used the social ecological model (SEM) as a guiding framework to categorize and interpret SDoH across individual, interpersonal, community, and societal levels. A qualitative thematic synthesis was conducted to iteratively and collaboratively extract, categorize, and review determinants. Results: We analyzed 48 eligible studies, of which 35 addressed R1 by examining compliance patterns across various SDoH. Using the SEM, we identified 13 determinants categorized across 4 levels: individual (eg, daily routine, biological sex, age, socioeconomic status, language, education, and race or ethnicity), interpersonal (eg, social support), community and organizational (eg, social context, social acceptance, stigmatization, and youth culture), and policy or societal (eg, systemic and structural barriers). These studies described differences in EMA response rates, compliance, and dropout associated with these determinants, often among vulnerable populations. The remaining 13 studies addressed R2, demonstrating examples of the types of SDoH that EMA research can uncover, including family culture, social support, social contexts, stigmatization, gender norms, heroic narratives, LGBTQ+ culture, racial discrimination, and systematic and structural barriers. Conclusions: This scoping review illustrates how EMA compliance rates can differ across SDoH and highlights the potential of EMA to uncover social and cultural factors linked to health behaviors and outcomes. Our findings underscore the importance of integrating SDoH considerations into EMA study designs to capture context-specific sociocultural dynamics.

25 August 2023 in JMIR Preprints
Verified
Preprint
Open access
YSYinan Sun
Yinan Sun
AKAli Kargarandehkordi
Ali Kargarandehkordi
CSChristopher Slade
Christopher Slade
AJAditi Jaiswal
Aditi Jaiswal
GBGerald Busch
Gerald Busch
Peter WashingtonPeter Washington
Peter Washington
BACKGROUND Artificial intelligence (AI)–powered digital therapies that detect methamphetamine cravings via consumer devices have the potential to reduce health care disparities by providing remote and accessible care solutions to communities with limited care solutions, such as Native Hawaiian, Filipino, and Pacific Islander communities. However, Native Hawaiian, Filipino, and Pacific Islander communities are understudied with respect to digital therapeutics and AI health sensing despite using technology at the same rates as other racial groups. OBJECTIVE In this study, we aimed to understand the feasibility of continuous remote digital monitoring and ecological momentary assessments in Native Hawaiian, Filipino, and Pacific Islander communities in Hawaii by curating a novel data set of longitudinal Fitbit (Fitbit Inc) biosignals with the corresponding craving and substance use labels. We also aimed to develop personalized AI models that predict methamphetamine craving events in real time using wearable sensor data. METHODS We will develop personalized AI and machine learning models for methamphetamine use and craving prediction in 40 individuals from Native Hawaiian, Filipino, and Pacific Islander communities by curating a novel data set of real-time Fitbit biosensor readings and the corresponding participant annotations (ie, raw self-reported substance use data) of their methamphetamine use and cravings. In the process of collecting this data set, we will gain insights into cultural and other human factors that can challenge the proper acquisition of precise annotations. With the resulting data set, we will use self-supervised learning AI approaches, which are a new family of machine learning methods that allows a neural network to be trained without labels by being optimized to make predictions about the data. The inputs to the proposed AI models are Fitbit biosensor readings, and the outputs are predictions of methamphetamine use or craving. This paradigm is gaining increased attention in AI for health care. RESULTS To date, more than 40 individuals have expressed interest in participating in the study, and we have successfully recruited our first 5 participants with minimal logistical challenges and proper compliance. Several logistical challenges that the research team has encountered so far and the related implications are discussed. CONCLUSIONS We expect to develop models that significantly outperform traditional supervised methods by finetuning according to the data of a participant. Such methods will enable AI solutions that work with the limited data available from Native Hawaiian, Filipino, and Pacific Islander populations and that are inherently unbiased owing to their personalized nature. Such models can support future AI-powered digital therapeutics for substance abuse. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/46493