Responsible AI Seminar: A journey through the disorderly world of diagnostic and prognostic models for covid-19
Title
A journey through the disorderly world of diagnostic and prognostic models for covid-19: A living systematic review
Abstract
Diagnostic and prognostic models could provide an evidence-based approach for efficient triage of suspected or infected patients. However, since the covid-19 outbreak, over 200 models have been proposed, and the number keeps growing. We performed a rigorous systematic review and standardized risk of bias assessment of published and pre-print papers proposing prediction models for covid-19. It has been dubbed "the fastest systematic review ever", and has transformed into a "living" review, with multiple updates published since the original publication. In this talk, we will describe the study setup and results. We review the spectrum of available models, ranging from simple scoring systems to AI based on medical imaging, and pinpoint important issues with the study design and analysis that hamper their reliability.
About the speaker
Laure is assistant professor of Epidemiology at Maastricht University in the Netherlands and KU Leuven, Belgium. She earned a M.A. in Biostatistics, summa cum laude, and a PhD from the KU Leuven in Belgium. She’s interested in methods to handle heterogeneity between populations when developing and validating prediction models, and in the utility of prediction models in clinical practice. Her work has received multiple awards, including the Edmond Hustinx science prize for the review she will present here. She is associate editor for BMC Diagnostic and Prognostic Research, member of the International Society for Clinical Biostatistics and member of STRATOS’ (STRengthening Analytical Thinking for Observational Studies) topic group on the evaluation of diagnostic tests and prediction models. She was also closely involved in the development of diagnostic models for ovarian cancer which are now implemented in mobile apps and ultrasound machines of GE and Samsung, and are incorporated in international clinical guidelines.
You can find the review here.
Attend this talk on Zoom.
About the Responsible AI Seminar Series
Responsible AI draws on widely different scientific disciplines, from the technical aspects of AI, via ethics, philosophy and law, to the individual realities of different application domains. We wish to take advantage of the limitations imposed by Covid-19 to start an informal conversation across Denmark about different aspects of Responsible AI via a hybrid format seminar series. We hope to catch your interest with three seminar talks before the summer vacation, following which we hope to merge efforts across universities to start a truly inter-university seminar series. Initiators: Aasa Feragen, Melanie Ganz and Sune Hannibal Holm from the DFF-funded project Bias and Fairness in Medicine.