Ying-Ying Tsai

Ying-Ying Tsai

Auto-generated profile, based on publicly available information

Ying-Ying Tsai

Institute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, 35, Keyan Road, Zhunan Town 1 , Miaoli County 350

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
3 April 2025 in APL Bioengineering
Verified
Journal Article
Open access
YTYing-Ying Tsai
Ying-Ying Tsai
YCYu-Jie Chen
Yu-Jie Chen
YLYen-Feng Lin
Yen-Feng Lin
FHFan-Chi Hsiao
Fan-Chi Hsiao
CHChing-Han Hsu
Ching-Han Hsu
Lun-De LiaoLun-De Liao
Lun-De Liao
Prolonged exposure to high-stress environments can lead to mental illnesses such as anxiety disorders, depression, and posttraumatic stress disorder. Here, a wearable device utilizing photoplethysmography (PPG) technology is developed to noninvasively measure physiological signals and analyze heart rate variability (HRV) parameters. Traditional normative HRV databases typically do not account for responses induced by specific stressors such as cognitive tasks. Therefore, machine learning is used to build a more dynamic stress assessment model. Machine learning can capture complex nonlinear relationships among HRV parameters during stress-inducing tasks, adapts to individual stress response variations, and provides real-time stress level predictions. Furthermore, machine learning models can integrate temporal patterns in HRV data to achieve nuanced stress level assessment. This study examines the feasibility of PPG signals and validates the developed stress model. The RR intervals derived from PPG signals were highly positively correlated with those from electrocardiography signals (correlation coefficient = 0.9920, R-squared = 0.9837); this confirms the usability of PPG signals for HRV analysis. The stress model is constructed via the open-source Swell dataset. In the experiments, participants complete the Depression Anxiety Stress Scales-21-Chinese (DASS-21-C) questionnaire to quantify levels of depression, anxiety, and stress over a week. Baseline and stress-state PPG data are collected, converted into HRV values, and input into the model for stress quantification. The Stroop test is used to elicit stress responses. After the experiment, the DASS-21-C stress scores were compared with the model's baseline, stress state, and combined scores. The highest correlation was observed between the model's baseline score and the DASS-21-C stress score (correlation coefficient = 0.92, R-squared = 0.8457), supporting the model's psychological significance in quantifying everyday stress. HRV parameter changes across experimental phases are discussed as well as sex differences in stress responses. In the future, this device may be applied in clinical scenarios for further validation and could be integrated with additional physiological indicators for broader application in daily health management and stress warning systems.

1 February 2026 in Digital Health
Verified
Journal Article
Open access
YTYing-Ying Tsai
Ying-Ying Tsai
CSChien-Yu Shen
Chien-Yu Shen
CHChing-Han Hsu
Ching-Han Hsu
WCWei J. Chen
Wei J. Chen
Lun-De LiaoLun-De Liao
Lun-De Liao
Objective: Integrating heterogeneous public health surveillance and operational data into a governed, auditable environment that supports timely decision-relevant analysis remains difficult in practice. In this paper, the design, implementation, and technical evaluation of an epidemic war room decision-support platform and the calibration of its coupled compartmental transmission model are reported. Methods: The platform was implemented at the National Health Research Institutes, Taiwan, on a microservice architecture with automated extract–transform–load pipelines, network segmentation, role-based authorization, and audit logging. The integrated datasets spanned from January 2020 to November 2023. The evaluation was confined to three technical dimensions: data integration and quality control, security and governance, and in-sample model fit against observed national incidence. A controlled scenario comparison and a full factorial sensitivity analysis over 40 policy configurations were performed. Results: On the platform, 11 curated dataset groups were integrated. In the in-sample fit assessment, the coupled model reproduced the observed 2022 peak to within 3.7% in terms of magnitude, and two days in terms of timing over 300 days (r = 0.886, with a root mean squared error of 13,542 cases per day), whereas the cumulative incidence was underestimated by 17.9%. A comparison of two points of the same policy grid revealed that the high-intensity configuration (with a higher mask adherence, wider contact tracing, and longer quarantine) resulted in a simulated peak daily incidence that was 68.0% lower than that of the low-intensity configuration (52,012 cases versus 162,598 cases), with the peak deferred by 63 days and a cumulative difference of 1.47 million simulated infections over 150 days (−36.4%); much of this effect reflects deferral rather than prevention. Within the evaluated parameter grid, compared with quarantine duration, mask adherence and contact tracing produced greater changes in the simulated outcomes; quarantine beyond three days altered the cumulative number of infections by less than 1.2%, except where contact tracing and mask adherence were both high (−2.0% and −14.3%). Conclusion: Standardized governance and interactive decision interfaces can be integrated within a single public health analytical environment, thereby providing an implementation reference for public health data infrastructure. The dominant modeled benefit is the reduction and deferral of the epidemic peak rather than the prevention of cumulative infections. Whether the platform improves decision quality was not evaluated; prospective user evaluation is the next step.