Xintian and Boya are awarded for their joint project “Evaluating the performance of three indirect treatment comparison methods for Health Technology Assessments”. Improving decision-making in Health Technology Assessments, which are used by regulatory bodies in the assessment of novel treatments or medical devices, has the potential to remove biases and improve the processes which govern the medical technology available to the public. This work has the potential to impact industry practices and ultimately patient care.
Upon winning the award Xintian and Boya stated:
“We are very honoured to receive the MAPS Postgraduate Innovation and Enterprise prize for our research, which focused on evaluating the performance of three indirect treatment comparison methods with simulated data across 162 scenarios.
Our projects aimed to explore how statistical methods can bridge the gap between treatments in clinical settings, where direct comparisons may be impractical or unethical. Additionally, we investigated why and how the results of two pivotal papers in the field were seemingly opposite. By simulating clinical data across 162 scenarios, we assessed the performance of three commonly used methods for indirect treatment comparisons: the Bucher method, Matching-adjusted indirect comparisons (MAIC), and Simulated treatment comparisons (STC). Through this work, we highlighted the importance of selecting the appropriate method based on the specific characteristics of the data, given the strengths and weaknesses of each approach observed across the simulated scenarios.
The main contribution of our project was the refinement of the MAIC reweighing process with consideration of bias thresholds, which provides a more stable framework for using MAIC in clinical research, particularly in scenarios with poor covariate overlap or small sample sizes. We also obtained new results related to marginal and conditional estimates and explored matching on an additional variance term.
We sincerely hope that our research can serve as both a tool for future studies in indirect treatment comparisons and as a guide for researchers in refining their methodologies, ultimately supporting more reliable clinical decision-making.
Finally, we would like to express our heartful gratitude to our supervisor, Associate Professor Chak Hei (Hugo) Lo, for his exceptional guidance and expertise throughout this project. His invaluable insights helped shape the direction of our work and ensured its practical applicability. Furthermore, we extend our thanks to our industrial partner, Open Health, and to the Department of Statistical Science for the resources and support provided. This award is the result of a team effort, and we are truly grateful to everyone who contributed to its success.”
