Pool every immunotherapy trial's biomarker data into one commons
Dozens of trials have collected immune, genomic and imaging data on the same drugs. Nobody can analyse them together, so the answer stays hidden in fragments.
Predicting checkpoint response is a small-data problem imposed by fragmentation, not by biology: individual trials have hundreds of patients, while the aggregate is tens of thousands with multimodal data. A federated commons with harmonised data models, standardised endpoints and privacy-preserving analysis, backed by a condition of funding or of approval, would allow multimodal models to be trained and, importantly, externally validated.
- No one can predict who responds to immunotherapy · Checkpoint drugs cure some patients and do nothing for most. We still cannot tell the two apart before treating.
- Data silos · Records, scans, genomes and outcomes sit in separate systems that cannot talk. Every patient's experience is lost to the next.
- AI that is built but not validated or deployed · Thousands of cancer AI models are published; a handful are in clinical use, and fewer have shown they help patients.
Pages like this
not linked directly; found by shared links- IdeaAn organotropism atlas that predicts where a cancer will spread
Shares cBioPortal for Cancer Genomics, AACR Project GENIE, RNA sequencing & expression profiling, Pathology & radiology foundation models.
- IdeaA global rapid tissue donation network for metastatic disease
Shares cBioPortal for Cancer Genomics, AACR Project GENIE, Single-cell & spatial profiling, Data silos.
- IdeaTurn the map of immune cells inside a tumour into a standardised test
Shares Tumour proportion score (TPS), Pathology & radiology foundation models, Single-cell & spatial profiling, AI that is built but not validated or deployed.
- IdeaA federated learning consortium of cancer centres that jointly own the models
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed, Data silos.
- IdeaEvery tumour genomic report machine-readable and deposited nationally
Shares OncoKB, cBioPortal for Cancer Genomics, AACR Project GENIE, Data silos.
- IdeaWhole-patient digital twins validated in prospective randomised trials
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed.
- IdeaA registry of external validation datasets for cancer AI models, with mandatory reporting
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed.
- IdeaA pre-competitive consortium to train a shared multimodal cancer foundation model
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed, Data silos.