Yu En Chan

Yu En Chan

Auto-generated profile, based on publicly available information

Yu En Chan

Institute for Infocomm Research (I2R), A*STAR, Singapore, Singapore

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
4 August 2023
Verified
Conference Paper
Open access
MNMila Nambiar
Mila Nambiar
SGSupriyo Ghosh
Supriyo Ghosh
POPriscilla Ong
Priscilla Ong
YCYu En Chan
Yu En Chan
YBYong Mong Bee
Yong Mong Bee
PKPavitra Krishnaswamy
Pavitra Krishnaswamy
There is increasing interest in data-driven approaches for recommending optimal treatment strategies in many chronic disease management and critical care applications. Reinforcement learning methods are well-suited to this sequential decision-making problem, but must be trained and evaluated exclusively on retrospective medical record datasets as direct online exploration is unsafe and infeasible. Despite this requirement, the vast majority of treatment optimization studies use off-policy RL methods (e.g., Double Deep Q Networks (DDQN) or its variants) that are known to perform poorly in purely offline settings. Recent advances in offline RL, such as Conservative Q-Learning (CQL), offer a suitable alternative. But there remain challenges in adapting these approaches to real-world applications where suboptimal examples dominate the retrospective dataset and strict safety constraints need to be satisfied. In this work, we introduce a practical and theoretically grounded transition sampling approach to address action imbalance during offline RL training. We perform extensive experiments on two real-world tasks for diabetes and sepsis treatment optimization to compare performance of the proposed approach against prominent off-policy and offline RL baselines (DDQN and CQL). Across a range of principled and clinically relevant metrics, we show that our proposed approach enables substantial improvements in expected health outcomes and in consistency with relevant practice and safety guidelines.

29 July 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
WZWeizhuang Zhou
Weizhuang Zhou
YCYu En Chan
Yu En Chan
CFChuan Sheng Foo
Chuan Sheng Foo
JZJingxian Zhang
Jingxian Zhang
JTJing Xian Teo
Jing Xian Teo
PKPavitra Krishnaswamy
Pavitra Krishnaswamy
Background: Consumer-grade wearable devices enable detailed recordings of heart rate and step counts in free-living conditions. Recent studies have shown that summary statistics from these wearable recordings have potential uses for longitudinal monitoring of health and disease states. However, the relationship between higher resolution physiological dynamics from wearables and known markers of health and disease remains largely uncharacterized. Objective: We aimed to derive high-resolution digital phenotypes from observational wearable recordings and to examine their associations with modifiable and inherent markers of cardiometabolic disease risk. Methods: We introduced a principled framework to extract interpretable high-resolution phenotypes from wearable data recorded in free-living conditions. The proposed framework standardizes the handling of data irregularities; encodes contextual information regarding the underlying physiological state at any given time; and generates a set of 66 minimally redundant features across active, sedentary, and sleep states. We applied our approach to a multimodal data set, from the SingHEART study (NCT02791152), which comprises heart rate and step count time series from wearables, clinical screening profiles, and whole genome sequences from 692 healthy volunteers. We used machine learning to model nonlinear relationships between the high-resolution phenotypes on the one hand and clinical or genomic risk markers for blood pressure, lipid, weight and sugar abnormalities on the other. For each risk type, we performed model comparisons based on Brier scores to assess the predictive value of high-resolution features over and beyond typical baselines. We also qualitatively characterized the wearable phenotypes for participants who had actualized clinical events. Results: We found that the high-resolution features have higher predictive value than typical baselines for clinical markers of cardiometabolic disease risk: the best models based on high-resolution features had 17.9% and 7.36% improvement in Brier score over baselines based on age and gender and resting heart rate, respectively (P<.001 in each case). Furthermore, heart rate dynamics from different activity states contain distinct information (maximum absolute correlation coefficient of 0.15). Heart rate dynamics in sedentary states are most predictive of lipid abnormalities and obesity, whereas patterns in active states are most predictive of blood pressure abnormalities (P<.001). Moreover, in comparison with standard measures, higher resolution patterns in wearable heart rate recordings are better able to represent subtle physiological dynamics related to genomic risk for cardiometabolic disease (improvement of 11.9%-22.0% in Brier scores; P<.001). Finally, illustrative case studies reveal connections between these high-resolution phenotypes and actualized clinical events, even for borderline profiles lacking apparent cardiometabolic risk markers. Conclusions: High-resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance the prediction of cardiometabolic disease risk and could enable more proactive and personalized health management. Trial Registration:

1 November 2021 in medRxiv
Verified
Preprint
Open access
PDF file
WZWeizhuang Zhou
Weizhuang Zhou
YCYu En Chan
Yu En Chan
CFChuan Sheng Foo
Chuan Sheng Foo
JZJingxian Zhang
Jingxian Zhang
JTJing Xian Teo
Jing Xian Teo
PKPavitra Krishnaswamy
Pavitra Krishnaswamy
Background: Consumer-grade wearable devices enable detailed recordings of heart rate and step counts in free-living conditions. Recent studies have shown that summary statistics from these wearable recordings have potential uses for longitudinal monitoring of health and disease states. However, the relationship between higher resolution physiological dynamics from wearables and known markers of health and disease remains largely uncharacterized. Objective: We aimed to (i) derive high resolution digital phenotypes from observational wearable recordings, (ii) characterize their ability to predict modifiable markers of cardiometabolic disease, and (iii) study their connections with genetic predispositions for cardiometabolic disease and with lifestyle factors. Methods: We introduce a principled framework to extract interpretable high resolution phenotypes from wearable data recorded in free-living conditions. The proposed framework standardizes handling of data irregularities, encodes contextual information about underlying physiological state at any given time, and generates a set of 66 minimally redundant features across active, sedentary and sleep states. We applied our approach on a multimodal dataset, from the SingHEART study ( NCT02791152 ), that comprises of heart rate and step count time series from wearables, clinical screening profiles, whole genome sequences and lifestyle survey responses from 692 healthy volunteers. We employed machine learning to model non-linear relationships between the high resolution phenotypes and clinical risk markers for blood pressure, lipid and weight abnormalities. For each risk type, we performed model comparisons based on Brier Skill Scores (BSS) to assess predictive value of the high resolution features over and beyond typical baselines. We then examined associations between the wearable-derived features, polygenic risk for cardiometabolic disease, and lifestyle habits and health perceptions. Results: Compared to typical summary statistic measures like resting heart rate, we find that the high-resolution features collectively have greater predictive value for modifiable clinical markers associated with cardiometabolic disease risk (average improvement in Brier Skill Score=52.3%, P <.001). Further, we show that heart rate dynamics from different activity states contain distinct information about type of cardiometabolic risk, with dynamics in sedentary states being most predictive of lipid abnormalities and patterns in active states being most predictive of blood pressure abnormalities ( P <.001). Finally, our results reveal that subtle heart rate dynamics in wearable recordings serve as physiological correlates of genetic predisposition for cardiometabolic disease, lifestyle habits and health perceptions. Conclusions: High resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance prediction of cardiometabolic disease risk, and could enable more proactive and personalized health management. Trial Registration: ClinicalTrials.gov NCT02791152 ; https://clinicaltrials.gov/ct2/show/NCT02791152

4 September 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
SKSezin ATA KIRCALI
Sezin ATA KIRCALI
WZWeizhuang Zhou
Weizhuang Zhou
JTJesisca Tandi
Jesisca Tandi
WLWei Qing Lee
Wei Qing Lee
YCYu En Chan
Yu En Chan
MEMojisola Erdt
Mojisola Erdt
Background: Digital health applications generate rich behavioral data; yet, how users transition between behavioral states remains poorly understood. Existing approaches show limited capacity to capture and represent the evolving and nuanced nature of real-world behavioral dynamics, which are essential for informing personalized behavior change interventions. Objective: This study aimed to understand how users’ behaviors evolve within digital health applications by developing a data-driven approach that captures transition dynamics across behavioral features. We aimed to validate modeled transitions against observed user data, analyze transition pathways, and derive interpretable insights. Methods: We analyzed 32 weeks of data from 36,574 users from a population health program run by the Health Promotion Board (HPB) in Singapore. We developed a graph-based behavioral trajectory model (GraphBeTraM ) that models behavioral transitions as shortest paths through user similarity graphs. By aggregating paths over time, the model captures users’ progression toward target behavioral states and quantifies the direction, magnitude, and timing of change. We validated modeled transitions against real-world data by comparing (1) transition matrices and (2) feature-level pathways, using Spearman correlation, Fisher z-transformed means, and cosine distance. We focused on high-variance features and used heatmaps to visualize patterns of change. Finally, characterized transition pathways between behavioral states and distinguished generalizable and context-specific features. Results: We observed strong alignment between observed and modeled transition matrices with strong correlation (Spearman ρ=0.82; P <.001) and low cosine distance (0.05), suggesting that real-world behavioral transitions can be effectively represented through shortest paths with GraphBeTraM. Feature-level pathway validation showed consistent patterns of change across both personalized and real-world pathways. Physical activity features like weekly moderate to vigorous physical activity (MVPA) emerged as stable, generalizable signals of change at the population level, with strong mean correlation (ρ_ personalized =0.97; ρ_ real-world =0.79) and low mean cosine distance (cosine_ personalized =0.24; cosine_ real-world =0.41) across both personalized and real-world transitions. In contrast, features related to personal preferences, including time-related activity patterns (eg, proportion of weekday to weekend MVPA), purchase preferences for healthy foods and drinks, and engagement indicators (eg, last contact with the program or app), exhibited context-specific relevance and reflected change at an individual level. An in-depth transition analysis from an active state with prolonged sedentary periods to an active state with healthy eating habits revealed interpretable patterns in onset, magnitude, and rate of change. Specifically, features such as preferences for healthy food and drink purchases emerged later in the trajectory but then showed sharper and faster transitions once these behaviors began to shift. These insights highlight how GraphBeTraM can guide nudging strategies in alignment with natural behavior dynamics, including both stable and later-onset patterns. Conclusions: GraphBeTraM provides an interpretable framework for modeling behavioral transitions in digital health applications and captures key dynamics that support personalized intervention design.