On Friday 6 June the IAHS held a one day workshop on clinical prediction modelling with eminent guest speakers from Erasmus Medical Center, Rotterdam.
Clinical prediction models are mathematical formulae that try to predict the chances of a clinical outcome (such as death or diagnosis) based on characteristics related to the patient, treatment or disease. The models are often converted into a user-friendly computer-based tool. Clinicians often use such tools to help them communicate the chances of clinical outcomes to their patients and to improve their management. It is therefore of crucial importance that such models are developed and tested appropriately.
Chaired by Professor Siladitya Bhattacharya and Professor Amanda Lee, the workshop began with a series of presentations from two guest speakers, Professor Ewout Steyerberg and Professor Egbert te Velde from Erasmus Medical Center, Rotterdam, which were followed by short presentations from IAHS researchers who have developed, or are planning to develop, clinical prediction models.
Professor Steyerberg is a Professor of Medical Decision Making at the Department of Public Health who is world-renowned for his research in prognostic modelling and is author of the textbook ‘Clinical Prediction Models’. Professor te Velde is an Emeritus Professor from the Department of Public Health who has written multiple papers on prognostic modelling in fertility medicine.
In his first talk, Prof Steyerberg gave an overview of clinical prediction models and their use in medical practice. This was followed by Prof te Velde’s lecture on methods of testing the accuracy and usability of such models. In his second presentation, Prof Steyerberg spoke about ways of evaluating improvements in model predictions when a new biomarker or test is available and added to the model.
The guest speakers were followed by David McLernon, Medical Statistics Team; Harry Marks, Chronic Disease Research Group; Gordon Prescott, Medical Statistics Team; Angus Macleod, Chronic Disease Research Group; and Neil Basu, Epidemiology, who presented their proposed research. Talks covered a broad spectrum of clinical diseases including infertility, chronic kidney disease, preeclampsia, Parkinson’s disease, and vasculitis.
All of the presentations were extremely informative and stimulated much debate during the afternoon discussion hour which was ably chaired by Graeme MacLennan, Health Services Research Unit.
Organised jointly by the Medical Statistics Team and the Obstetrics and Gynaecology group, the workshop was attended by 30 members of staff from various clinical and research disciplines across the Institute, and received very positive feedback from those who attended.
Dr Harry Marks, who presented her work during the day said ‘Clinical prediction models have the potential to improve the stratification of care delivery for many individuals who have been identified with chronic disease, so that they get appropriate care in the right setting for them, based on their risk of future health events. This clinical prediction modelling workshop was very useful to facilitate best practice in those currently working in this research field in Aberdeen.’
Dr Angus Macleod, who also presented during the day and said that “It was a useful, practical and stimulating workshop and it was good to bring clinicians and statisticians together so that we could learn from each other.”