Risk prediction

Proteomic signatures improve risk prediction for common and rare diseases

section { background: white; color: black; border-radius: 1em; padding: 1em; left: 50% } #inner { display: inline-block; display: flex; align-items: center; justify-content: center } Press releases QMUL Press release UCL Press release Nature Medicine Research Briefing Blood proteins predict the risk of many diseases years before onset.

Foresight: a generative AI model of patient trajectories across the COVID-19 pandemic

GPT model trained from scratch on EHR codes of 57 million individuals for universal risk prediction and trial emulation.

Proteomic prediction of common and rare diseases

section { background: white; color: black; border-radius: 1em; padding: 1em; left: 50% } #inner { display: inline-block; display: flex; align-items: center; justify-content: center } Twitter thread summarising key results

NHS DART Internship: Graph Representation Learning

Representation learning for EHR data, exploring graph structures and semantic embeddings applied to national-scale datasets

UCL-GSK Phenomics Hub

Phenotyping at scale across diverse biobank cohorts to power genomic & proteomic analyses for target identification, drug discovery, and precision medicine.

A nationwide deep learning pipeline to predict stroke and COVID-19 death in atrial fibrillation

section { background: white; color: black; border-radius: 1em; padding: 1em; left: 50% } #inner { display: inline-block; display: flex; align-items: center; justify-content: center }