Loading
How AI is moving from single-task readers of scans and slides towards systems that weigh everything about a patient, and what regulators and evidence still require.
Hundreds of narrow AI devices are cleared, mostly in radiology triage and screening. The first predictive pathology tools (ArteraAI) prove that AI can change treatment decisions under regulation. Foundation models promise breadth, but the evidence base for deployment, the regulatory framework for updating models, and reimbursement are all unsettled.
FDA clears the first AI detection aids: mammography CAD successors, Paige Prostate (2021), radiology triage for haemorrhage and embolism. Evidence is mostly reader studies.
MASAI (Sweden) shows AI-supported mammography reading finds more cancers with less workload; Sybil and Mirai predict future cancer from today's scan; whole-slide imaging becomes routine, enabling slide-level AI.
ArteraAI Prostate (de novo 2025) predicts treatment benefit; ArteraAI Breast cleared 2026. Pathology foundation models (Virchow2, Prov-GigaPath, TITAN, Atlas) move into commercial biomarker products; multimodal models (MUSK) predict immunotherapy response retrospectively.
Randomised or pragmatic trials of AI-guided decisions (screening intervals, treatment selection); FDA predetermined change control plans for model updates; EU AI Act high-risk obligations; payment codes for AI-derived biomarkers. LLM assistants (Med-Gemini class) enter tumour boards for documentation and trial matching under human review.
A single model reads slides, scans, genomics and records to recommend and monitor therapy, audited against outcomes and updated continuously. Depends on data-sharing, liability and validation questions that are open today.
Every era's records, trial outcomes and papers, and every watch item, as JSON.
Probability ranges are named estimates that the claim is borne out on roughly a five-year horizon. They are meant to be argued with: propose a revision with your name and reasoning via a pull request to src/data/confidence.ts.
Loading this step…
Loading this step…
Loading this step…
Loading this step…
Loading this step…
Shares ArteraAI Breast, ArteraAI Prostate, Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models.
Shares Prov-GigaPath (Microsoft, Providence), Virchow / Virchow2 (Paige, MSK), Paige AI, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow.
Shares Paige AI, Pathology & radiology foundation models, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, Digital pathology & AI.
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, Digital pathology & AI.
Shares Paige AI, Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, Digital pathology & AI.
Shares TITAN (whole-slide multimodal model), Paige AI, Pathology & radiology foundation models.
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI in radiology, Digital pathology & AI.
Shares Tempus multimodal models, Patient-level multimodal foundation models for treatment selection, AI trial matching & clinical decision support, Pathology & radiology foundation models.