TMCF Workshop Use-Cases - Counterfactual CPMS & Emerging COVID Work, Niels Peek

Explore the outcomes of a Turing Institute 'Theory and Methods Challenge Fortnights in Data Science and AI' focused on enhancing prediction algorithms with causal inference capabilities. Delve into the concept of 'counterfactual prediction' and its applications in decision-making processes, particularly in healthcare scenarios like COVID-19 patient care. Learn about the limitations of traditional prediction algorithms and how causal inference can address 'what if' questions, improving fairness and decision support. Examine case studies including QRISK, emergency hospital admissions, and COVID-19 predictions to understand the practical implications of these advanced methodologies.

Introduction
Why we need prognostic models
Existing prognostic models
Qrisk
Brian Macmillan
Emergency hospital admissions
COVID19 predictions