Phat Kim Huynh

Phat Kim Huynh

Auto-generated profile, based on publicly available information

Phat Kim Huynh

PASSIO Laboratory, North Carolina A&T State University, Greensboro, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
16 May 2024 in IEEE Transactions on Learning Technologies
Verified
Journal Article
Closed access
PSPallavi Singh
Pallavi Singh
PHPhat K. Huynh
Phat K. Huynh
DNDang Nguyen
Dang Nguyen
TLTrung (Tim) Le
Trung (Tim) Le
WMWilfrido Moreno
Wilfrido Moreno
In organizational and academic settings, the strategic formation of teams is paramount, necessitating an approach that transcends conventional methodologies. This study introduces a novel application of multi-criteria integer programming (MCIP), which simultaneously accommodates multiple criteria, thereby innovatively addressing the complex task of team formation. Unlike traditional single-objective optimization methods, our research designs a comprehensive framework capable of modeling a wide array of factors, including skill levels, backgrounds, and personality traits. The objective function of this framework is optimized to maximize within-team diversity, while minimizing both conflict levels and variance in diversity between teams. Central to our approach is a two-stage optimization process. Initially, it segments the population into sub-groups using a weighted heterogeneous multivariate K-means algorithm, allowing for a targeted and nuanced team assembly. This is followed by the application of a surrogate optimization technique within these sub-groups, efficiently navigating the complexities of MCIP for large-scale applications. Our approach is further enhanced by the inclusion of explicit constraints such as potential interpersonal conflicts, a factor often overlooked in previous studies. The results from our study demonstrate the optimality robustness of our model across simulation scenarios with different data heterogeneity levels. The contributions of this study are manifold, addressing critical gaps in existing literature with a theory-backed, empirically validated framework for advanced team formation. Beyond theoretical implications, our work provides a practical guide for implementing conflict-aware, sophisticated team formation strategies in real-world scenarios. This advancement paves the way for future research to explore and enhance this model, providing more sophisticated and efficient team formation strategies.

13 November 2025 in Computerized Medical Imaging and Graphics
Verified
Journal Article
Open access
TNThanh-Huy Nguyen
Thanh-Huy Nguyen
HNHoang-Thien Nguyen
Hoang-Thien Nguyen
VVVi Vu
Vi Vu
BLBa-Thinh Lam
Ba-Thinh Lam
PHPhat Huynh
Phat Huynh
MXMin Xu
Min Xu
The limited availability of annotated data in medical imaging makes semi-supervised learning increasingly appealing for its ability to learn from imperfect supervision. Recently, teacher-student frameworks have gained popularity for their training benefits and robust performance. However, jointly optimizing the entire network can hinder convergence and stability, especially in challenging scenarios. To address this for medical image segmentation, we propose DuetMatch, a novel dual-branch semi-supervised framework with asynchronous optimization, where each branch optimizes either the encoder or decoder while keeping the other frozen. To improve consistency under noisy conditions, we introduce Decoupled Dropout Perturbation, enforcing regularization across branches. We also design Pairwise CutMix Cross-Guidance to enhance model diversity by exchanging pseudo-labels through augmented input pairs. To mitigate confirmation bias from noisy pseudo-labels, we propose Consistency Matching, refining labels using stable predictions from frozen teacher models. Extensive experiments on benchmark brain MRI segmentation datasets, including ISLES2022 and BraTS, show that DuetMatch consistently outperforms state-of-the-art methods, demonstrating its effectiveness and robustness across diverse semi-supervised segmentation scenarios.

15 July 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
DNDuy Nguyen
Duy Nguyen
CHCa Hoang
Ca Hoang
TTTien Truong
Tien Truong
DNDang Nguyen
Dang Nguyen
HLHillary Gia Lam
Hillary Gia Lam
PHPhat Kim Huynh
Phat Kim Huynh
Cardiovascular diseases (CVDs) are prevalent among obstructive sleep apnea (OSA) patients, presenting significant challenges in predictive modeling due to the complex interplay of these comorbidities. Current methodologies predominantly lack the dynamic and longitudinal perspective necessary to accurately predict CVD progression in the presence of OSA. This study addresses these limitations by proposing a novel multi-level phenotypic model that analyzes the progression and interaction of these comorbidities over time. Our study utilizes a longitudinal cohort from the Wisconsin sleep cohort, consisting of 1,123 participants, tracked over several decades. The methodology consists of three advanced steps to capture the relationships between these comorbid conditions: (1) performing feature importance analysis using tree-based models to highlight the predominant role of variables in predicting CVD outcomes. (2) developing a logistic mixed-effects model (LGMM) to identify longitudinal transitions and their significant factors, enabling detailed tracking of individual trajectories; (3) and utilizing t-distributed stochastic neighbor embedding (t-SNE) combined with Gaussian mixture models (GMM) to classify patient data into distinct phenotypic clusters. In the analysis of feature importance, clinical indicators such as total cholesterol, low-density lipoprotein, and diabetes emerged as the top predictors, highlighting their significant roles in CVD onset and progression. The LGMM predictive models exhibited a high diagnostic accuracy with an aggregate accuracy of 0.9556. The phenotypic analysis yielded two distinct clusters, each corresponding to unique risk profiles and disease progression pathways. One cluster notably carried a higher risk for major adverse cardiovascular events (MACEs), attributed to key factors like nocturnal hypoxia and sympathetic activation. Analysis using t-SNE and GMM confirmed these phenotypes, which marked differences in progression rates between the clusters. In conclusion, our study provides a profound understanding of the dynamic OSA-CVD interactions, offering robust tools for predicting CVD onset and informing personalized treatment strategies.

14 December 2023 in SLEEP
Verified
Journal Article
Open access
PDF file
TLTrung (Tim) Le
Trung (Tim) Le
PHPhat Huynh
Phat Huynh
LTLennon Tomaselli
Lennon Tomaselli
The global wearable sleep trackers market is experiencing a significant upsurge, reflecting a burgeoning interest in personalized sleep health monitoring and management. The market is projected to expand at a compound annual growth rate of 7.92% from USD 2.06 billion in 2023 and reach an estimated USD 3.02 billion by the end of 2028 [ 1]. Among this growth, smart and AI-based wearable sleep trackers, offering functions akin to polysomnographic (PSG) studies, have gained popularity in the digital health revolution [ 2–5]. Such devices, designed in various form-factors ranging from smartwatches, wristbands, and rings to chest bands, headbands, and armbands [ 6], are continuously innovated to create more accurate and personalized sleep-tracking experiences [ 7, 8]. Furthermore, integrating cutting-edge biometric sensors and AI-driven analytics into these devices enhances their capability to measure total sleep duration and cycles and parameters such as heart rate variability, sleep positions, and brainwave patterns. The interoperability of diverse sensors is key to customizing wearable sleep trackers. By enabling data sharing between sensors, these devices can adapt to each user’s unique sleep patterns and health conditions, providing a personalized monitoring experience. The increasing awareness of the critical role of sleep in overall health, exacerbated by the COVID-19 pandemic’s impact on mental health and sleep-related difficulties, has further fueled the demand for these devices [ 9, 10]. With the nonstop innovations of wearable sleep trackers and the rising demands for personalized sleep health trackers, the standardization and rigorous validation of these devices have become paramount [ 11].

9 January 2026 in Neurocomputing
Verified
Journal Article
Closed access
TNThanh-Huy Nguyen
Thanh-Huy Nguyen
QBQuang-Khai Bui-Tran
Quang-Khai Bui-Tran
MHManh D. Ho
Manh D. Ho
TLThinh B. Lam
Thinh B. Lam
VVVi Vu
Vi Vu
UBUlas Bagci
Ulas Bagci

21 November 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
PHPhat K Huynh
Phat K Huynh
ASArveity R Setty
Arveity R Setty
QTQuan M Tran
Quan M Tran
OYOm P Yadav
Om P Yadav
NYNita Yodo
Nita Yodo
TLTrung (Tim) Le
Trung (Tim) Le
Introduction: Hospital-acquired infections of communicable viral diseases (CVDs) have been posing a tremendous challenge to healthcare workers globally. Healthcare personnel (HCP) is facing a consistent risk of viral infections, and subsequently higher rates of morbidity and mortality. Materials and methods: We proposed a domain-knowledge-driven infection risk model to quantify the individual HCP and the population-level risks. For individual-level risk estimation, a time-variant infection risk model is proposed to capture the transmission dynamics of CVDs. At the population-level, the infection risk is estimated using a Bayesian network model constructed from three feature sets, including individual-level factors, engineering control factors, and administrative control factors. For model validation, we investigated the case study of the Coronavirus disease, in which the individual-level and population-level infection risk models were applied. The data were collected from various sources such as COVID-19 transmission databases, health surveys/questionaries from medical centers, U.S. Department of Labor databases, and cross-sectional studies. Results: Regarding the individual-level risk model, the variance-based sensitivity analysis indicated that the uncertainty in the estimated risk was attributed to two variables: the number of close contacts and the viral transmission probability. Next, the disease transmission probability was computed using a multivariate logistic regression applied for a cross-sectional HCP data in the UK, with the 10-fold cross-validation accuracy of 78.23%. Combined with the previous result, we further validated the individual infection risk model by considering six occupations in the U.S. Department of Labor O*Net database. The occupation-specific risk evaluation suggested that the registered nurses, medical assistants, and respiratory therapists were the highest-risk occupations. For the population-level risk model validation, the infection risk in Texas and California was estimated, in which the infection risk in Texas was lower than that in California. This can be explained by California’s higher patient load for each HCP per day and lower personal protective equipment (PPE) sufficiency level. Conclusion: The accurate estimation of infection risk at both individual level and population levels using our domain-knowledge-driven infection risk model will significantly enhance the PPE allocation, safety plans for HCP, and hospital staffing strategies.