Loading
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.
Shares cBioPortal for Cancer Genomics, AACR Project GENIE, Pathology & radiology foundation models, RNA sequencing & expression profiling.
Shares Tumour proportion score (TPS), Estimation of the Percentage of US Patients With Cancer Who Are Eligible for and Respond to Checkpoint Inhibitor Immunotherapy Drugs, Pathology & radiology foundation models, Single-cell & spatial profiling.
Shares cBioPortal for Cancer Genomics, AACR Project GENIE, Single-cell & spatial profiling, Data silos.
Shares OncoKB, cBioPortal for Cancer Genomics, AACR Project GENIE, Data silos.
Shares OncoKB, AACR Project GENIE, Estimation of the Percentage of US Patients With Cancer Who Are Eligible for and Respond to Checkpoint Inhibitor Immunotherapy Drugs, No one can predict who responds to immunotherapy.
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed, Data silos.
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed.
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed, Data silos.