egsLab

Welcome to the website for the Evidence Generation & Synthesis Lab (egsLab)! Based at National Tsing Hua Univeristy in Taiwan, we are interested in developing and employing methods for the following goals, on both small-scaled and high-dimensional data:

  • Evidence Generation: How biomedical data should be analyzed to produce evidence that provides us insight in future clinical decisions. In particular, we are looking into causal inference methods that address and alleviate bias arising in evidence generation.
  • Evidence Synthesis: How evidence from multiple sources can be robustly combined to aquire the best-available evidence for our topic of interest. This involves meta-analysis spetrum methods and other data fusion approaches.

Talk to us or join our group if you are interested in (or just want to known more about) these topics or our work!

News

Jun 20, 2025 Congratulate Chia-Hsuan Wei on receiving the 2025 FHS-NHRI medical student summer research program (健康科學文教基金會暨國家衛生研究院醫學系學生暑期研究計畫)!
Sep 22, 2024 Our lab website has finally launched! 🎉🎉🎉

Selected publications

# indicates co-first authors or co-corresponding authors

  1. JAMA Network Open
    Use of Machine Learning to Assess the Management of Uncomplicated Urinary Tract Infection
    Noah Jones, Ming-Chieh Shih, Elizabeth Healey, and 5 more authors
    JAMA Network Open, 2025
  2. BJA
    Comparative efficacy of balanced crystalloids versus 0.9% saline on delayed graft function and perioperative outcomes in kidney transplantation: a meta-analysis of randomised controlled trials
    Tzu Chang#, Ming-Chieh Shih#, Yi-Luen Wu, and 3 more authors
    British Journal of Anaesthesia, 2024
  3. AISTATS 2023
    Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions
    Zeshan Hussain#, Ming-Chieh Shih#, Michael Oberst, and 2 more authors
    In International Conference on Artificial Intelligence and Statistics, 2023
  4. NeurIPS 2022
    Falsification before Extrapolation in Causal Effect Estimation
    Zeshan M Hussain#, Michael Oberst#, Ming-Chieh Shih#, and 1 more author
    Advances in Neural Information Processing Systems, 2022
  5. RSM
    An evidence-splitting approach to evaluation of direct-indirect evidence inconsistency in network meta-analysis
    Ming-Chieh Shih, and Yu-Kang Tu
    Research Synthesis Methods, 2021
  6. RSM
    Evaluating network meta-analysis and inconsistency using arm-parameterized model in structural equation modeling
    Ming-Chieh Shih, and Yu-Kang Tu
    Research synthesis methods, 2019