ActiveScreening · Health
Precision Screening for Colorectal Cancer
Developing a precision-screening framework that integrates risk stratification with optimised screening protocols.
Research & Product Lab
We research.
We build.
Advancing health. Expanding human potential.
Research
What we're researching.
Our research is currently concentrated in health, spanning responsible AI, screening, biosensing, genomics, and clinical translation.
- ActiveBiosensing · Health
VOC Biomarkers for Early Disease Detection
Exploring volatile organic compounds as non-invasive biomarkers for early signs of disease, with an initial focus on colorectal cancer.
Nexus X research
Products
What we're building.
We translate research into real-world products. Products starts as experiments in the playground, and if they prove their value, they get spun out into ventures of their own.
Showing out in the world.
- guidegenetics.com
Developed In-partnership
Guide Genetics
AI-powered family history pedigree builder for genetic risk assessment. Leveraging call agents and LLMs to surface hereditary risk early.
- nexushealth.ai
Developed In-house
Nexus Health
A subscription learning platform with guided tutorials that make Health AI practical, understandable, and easier to apply.
- learnblock.com
Developed In-house
Learnblock
A question bank platform for structured exam prep and learning. Built to make study material shareable, searchable, and effective.
Discover
Ideas worth sharing.
A catalogue of articles, podcasts, papers, and other posts we think are interesting.
Clinical & healthpaperarXiv.org4 minResidencyRL: Reinforcement Learning in Simulated Clinical EnvironmentsResidencyRL is a reinforcement learning method for training clinical AI agents through simulated, multi-turn patient encounters with adversarial LLM simulators and rewards aligned to diagnostic accuracy, management, communication, documentation, and safety. In held-out evaluations, the agent improved diagnostic accuracy under adversarial conditions, reduced missed red flags, and outperformed the base model across reported clinical benchmarks, though real-world validation remains necessary.Why we saved thisThis paper is relevant to researchers and builders developing clinical AI agents because it evaluates sequential decision-making, safety, and generalization beyond static medical benchmarks using simulated encounters.Read ResidencyRL: Reinforcement Learning in Simulated Clinical Environments (opens in a new tab)
Clinical & healtharticleresearch.google10 minSensorFM: Towards a general intelligence and interface for wearable health dataGoogle Research presents SensorFM, a foundation model for wearable health data pre-trained on more than one trillion minutes of multimodal sensor data from five million people. The model transfers across 35 health prediction tasks, supports label-efficient adaptation and data infilling, and can help ground a Personal Health Agent in individual physiology.Why we saved thisThis work is relevant to researchers and builders developing general-purpose health models, wearable-data applications, and AI health agents, particularly where labeled clinical data is limited.Read SensorFM: Towards a general intelligence and interface for wearable health data (opens in a new tab)Clinical & healthblogThe Guardian5 minScientists develop AI tool to spot heart failure risk five years before it strikesAn Oxford-developed AI tool predicted heart-failure risk five years before onset with 86% accuracy in a study of 72,000 patients in England.Read Scientists develop AI tool to spot heart failure risk five years before it strikes (opens in a new tab)