Key Steps and Common Pitfalls in Clinical Prediction Model Research
Clinical prediction models estimate an individual’s risk of a particular health outcome. Thousands of prediction models are published each year, yet few are reliable or fit for purpose. In this talk, I outline key steps and common pitfalls in prediction model research, and outline ways to produce more reliable and clinically useful models - including protocols, better handling of continuous predictors, examining calibration and clinical utility, checking model (in)stability, and ensuring sample size is appropriate for model development. Thanks for watching!

▶︎
Pitfalls for Clinical Decision Support Based on Artificial Intelligence (AI)

▶︎
What do tech pioneers think about the AI revolution? - The Engineers, BBC World Service

▶︎
Introduction to latent class / profile analysis

▶︎
Clinical Prediction Models & The Multiverse of Madness

▶︎
How Proctor’s texts in Karen Read lawsuit could free dangerous criminals

▶︎
Systematic Reviews of Prognosis Research & Prediction Models

▶︎
But what is quantum computing? (Grover's Algorithm)

▶︎
Hamza Ibn Abdulmuttalib (ra): The Lion of Allah | The Firsts | Dr. Omar Suleiman

▶︎
India Economy OK…But Danger Ahead? 5-State Polls में NDA 2-0 Lead? • Sriram Seshadri

▶︎
AI 최후의 승자 이래서 구글입니다 (KAIST 전자및전기공학부 김정호 교수)

▶︎
ESMARConf2023: {netmeta} tutorial

▶︎
Will Australia's social media ban for under-16s work? - The Global Story podcast, BBC World Service

▶︎
How to make 3D Games in Godot

▶︎
How to Build Endurance | Huberman Lab Essentials

▶︎
30 Years of Business Knowledge in 2hrs 26mins

▶︎
Tufayl ibn Amr (ra): The Hidden Legend | The Firsts | Dr. Omar Suleiman

▶︎
Intro to Hypothesis Testing in Statistics - Hypothesis Testing Statistics Problems & Examples

▶︎
But what is a neural network? | Deep learning chapter 1

▶︎
VALIDATING PREDICTION MODELS - what is discrimination and calibration?

▶︎
