Please join us online for a talk by Dr. a Professor of Biostatistics at the University of Birmingham. He will present 鈥淪ystematic reviews and Meta-Analysis of Prognosis Research and prediction models鈥� on Wednesday, November 4 2026 at 1:30 pm Central Time. For access to this seminar, contact series administrator Cierra Streeter.
As Professor of Biostatistics at the University of Birmingham (UK), Richard leads a team of statisticians undertaking applied and methodology research to improve healthcare, with a particular focus on prognosis studies, clinical prediction models, and evidence synthesis. He is a statistics editor for The BMJ (British Medical Journal) and BMJ Medicine, an NIHR (National Institute for Health and Care Research) Senior Investigator, and a Fellow of the Academy of Medical Sciences. He champions the role of methodology and methodologists in healthcare research and is lead statistician on numerous studies, with grants from funders such as the MRC (Medical Research Council) and NIHR.听听
Richard has authored over 300 research articles and is lead editor of three textbooks: Prognosis Research in Healthcare: Concepts, Methods and Impact; Individual Participant Data Meta-Analysis: A Handbook for Healthcare Research;听and the Cochrane Handbook for Systematic Reviews of Prognosis Research and Prediction Models. The Cochrane Handbook is the very first of its kind and co-edited by epidemiologist , an adjunct professor in our department.听
Abstract:听
Understanding, summarizing and predicting outcomes is essential to modern healthcare planning and individual decision-making. This has led to a rapid rise in prognosis research studies, including thousands of studies developing and evaluating prediction models (algorithms) for individual outcome prediction. However, such studies have highly variable quality and often contain conflicting findings. This motivates the need for systematic reviews of prognosis research and prediction model studies, to identify, appraise and synthesise the existing evidence. In this talk, I will outline current methods for such reviews, including meta-analysis methods, and highlight recommendations of the Cochrane Prognosis Methods Group, based on . Three types of review will be addressed: overall prognosis, prognostic factors, and prediction models.听 Real examples will be used to showcase the issues and statistical complexities, including reviews of machine learning and AI-based prediction research, and address the potential benefits in sharing individual participant data.听