Global Observational Health Data Research
Research Field
Jason C. Hsu is a Professor in the College of Management at Taipei Medical University. He currently serves as the President of the Observational Health Data Sciences and Informatics (OHDSI) Taiwan Society, leading national and international efforts in observational health data science and real-world evidence research. Through his academic and leadership roles, he is committed to advancing global collaboration, data standardization, and high-quality observational research.
The Global Observational Health Data Research Lab focuses on leveraging real-world data (RWD) and real-world evidence (RWE) to generate high-impact health insights. Anchored in standardized data models such as the OMOP Common Data Model and embedded within the OHDSI global research network, the lab integrates clinical, administrative, and population health data to support cross-institutional and cross-national research. We emphasize rigorous methodology, multidisciplinary collaboration, and translational outcomes that inform clinical practice, health policy, and digital health innovation.
1. MedVISTA: Conducts large-scale, multi-country observational studies to generate real-world evidence on the effectiveness and safety of new therapies, with special focus on populations underrepresented in clinical trials.
2. MedBenefit-AI: Develops machine-learning models to predict individualized treatment effects and heterogeneity of response, advancing precision medicine beyond average treatment effects.
3. MedSafety-AI: Applies artificial intelligence to predict and prevent drug safety risks in real-world practice, emphasizing explainable and cross-country–validated models.
Key disease focus areas: The three programs are primarily applied to cardio–kidney–metabolic (CKM) conditions, cancer, and COVID-19, serving as core domains for developing, validating, and translating real-world evidence and AI methodologies into clinical and policy impact.
- Fulbright Scholar Award, U.S. Department of State
- Drug Policy Research Award, Harvard Medical School, USA
- Future Technology Award, Ministry of Science and Technology (Taiwan)
- Project title: Multi-modal Lung Cancer Clinical Intelligent Decision-Support and Sharing System
- Outstanding Teaching Award for New Faculty, Taipei Medical University
- Outstanding Young Scholar Award, National Science and Technology Council (NSTC) 2030 Cross-Generation Young Scholar Program
PostDoc., Department of Population Medicine, Harvard Medical School.
Ph.D., International Business, National Taiwan University.
M.S., Technology Management, National Tsing Hua University.
B.S., Pharmacy, Taipei Medical University
Job Description
Interns will be assigned to specific research tasks under the lab’s flagship programs—
MedVISTA (a global real-world evidence program focusing on treatment effectiveness and safety beyond clinical trials),
MedBenefit-AI (an AI-driven program for individualized treatment benefit prediction using real-world data), and
MedSafety-AI (an AI-based program for predicting and evaluating drug safety risks in real-world practice)—
with applications in cardio–kidney–metabolic (CKM) conditions, cancer, and COVID-19.
Each intern is expected to independently complete defined research deliverables, which may include cohort construction, data analysis, result summarization, and preparation of research materials such as analytical reports or presentation slides. The internship emphasizes accountability, research execution, and measurable outputs, rather than observational learning.
Preferred Intern Educational Level
Applicants should have completed their master’s or doctoral training in medicine, public health, data science, computer science, biomedical sciences, health management, or related fields, and be capable of contributing independently to research tasks within a limited time frame.
Skill sets or Qualities
- Demonstrated ability to conduct independent research or analytical work
- Strong interest in observational research, real-world data, or real-world evidence generation
- Preferred: Prior participation in OHDSI-related meetings, workshops, or symposiums, with hands-on experience using OMOP Common Data Model data and OHDSI tools (e.g., ATLAS or related toolchains)
- Alternatively: Strong enthusiasm, self-motivation, and the ability to rapidly learn OMOP CDM concepts and OHDSI research workflows within a short time frame
- Prior experience with data analysis, statistics, epidemiology, or machine learning is highly preferred
- Ability to work with minimal supervision and deliver defined research outputs within a limited timeline
- Strong sense of responsibility, research discipline, and outcome-oriented mindset
- Proficiency in reading and communicating in English in a research or academic setting