The van der Schaar Lab’s tenth Revolutionizing Healthcare engagement session for clinicians took place virtually on September 29, 2021.
In this session, Mihaela van der Schaar and a panel of 4 international clinicians discussed the importance of bridging the gap between ideas and implementation in machine learning for healthcare.
Our panel for this session consisted of:
- Ari Ercole, MD PhD (Consultant in anesthesia & intensive care; deputy chief clinical informatics officer, Cambridge University Hospitals NHS Foundation Trust)
- Eoin McKinney, MD PhD (University lecturer in renal medicine, University of Cambridge; Honorary consultant in nephrology and transplantation, Cambridge University Hospitals NHS Foundation Trust)
- Lucas Fleuren (PhD candidate, Artificial Intelligence, Laboratory for Critical Care Computational Intelligence, Amsterdam UMC; Resident, Department of Intensive Care Medicine, Amsterdam UMC)
- Carsten Niemann, MD PhD (Associate professor and consultant, head of CLL Laboratory, Rigshospitalet; Chair of Nordic CLL Study Group)
In the first part of the session, Mihaela and the clinicians showed how machine learning can help clinicians estimate individualized treatment effects, using a working demonstrator to show real-world case studies from the ICU setting. The latter part of the session featured a clinician roundtable, during which the panelists discussed different approaches to ensuring that clinicians can make full use of machine learning models.
Introduction – 0:00
Declaration of interests – 0:40
Session overview – 1:30
Meet the roundtable panelists – 3:42
Presentation by Mihaela: “Getting ML-powered tools into the hands of clinicians” – 5:30
Eoin McKinney: average treatment effects vs. individualized treatment effects – 13:17
Eoin McKinney: ICU case studies in the Clairvoyance demonstrator – 30:02
Lucas Fleuren: ICU case studies in the Clairvoyance demonstrator – 48:00
Evgeny Saveliev: overview of Clairvoyance & Clairvoyance demonstrator – 55:00
Roundtable topic 1: proving causal links without relying on RCTs – 58:36
Roundtable topic 2: applying existing tools to new clinical domains – 1:03:56
Roundtable topic 3: improvements and next steps – 1:10:11
Intro to next sessions and note on CPD credits – 1:15:34
NOTE: This information was up-to-date at the time of the presentation but does not take into account material published since then.
Sign up for our upcoming sessions here.