{"entity":{"id":"artera-ai-prostate","kind":"drug","name":"ArteraAI Prostate","aka":[],"tldr":"The first AI tool cleared by the FDA to predict both prognosis and treatment benefit from a routine biopsy slide, in prostate cancer.","summary":"ArteraAI Prostate is a multimodal artificial intelligence test that combines a deep-learning image encoder applied to routine H&E biopsy slides with clinical variables to predict the risk of distant metastasis and the benefit of short-term androgen deprivation therapy added to radiotherapy in localised prostate cancer. It was validated retrospectively on NRG/RTOG randomised trial cohorts, received FDA de novo authorisation in August 2025 as the first AI tool cleared to predict both prognosis and treatment benefit from a slide, and is listed in NCCN guidelines. Its practical use is helping men with intermediate-risk disease decide whether hormone therapy is worth its side effects. Prospective validation is the open question. For a newcomer: software that reads a biopsy slide to say how aggressive the cancer is and whether hormone therapy will help.","status":"approved","asOf":"2026-09-04","links":[{"label":"Artera: ArteraAI tests","url":"https://artera.ai/"}],"tags":[],"related":[],"cancers":["prostate"],"sections":[],"technologies":["digital-pathology-ai","pathology-foundation-model"],"targets":[],"drugs":[],"companies":["artera"],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"modality":"AI digital pathology prognostic/predictive test","mechanism":"Deep-learning image encoder plus clinical data fusion.","approvals":[{"region":"US","year":2025,"indication":"Localised prostate cancer risk stratification and ADT benefit prediction"}],"mechanismSteps":["Biopsy slides are scanned to digital images","A deep-learning model extracts morphology features","Features are fused with clinical variables (PSA, Gleason, T stage)","The model outputs distant-metastasis risk and predicted benefit from short-term ADT","The report supports the radiation-plus-hormone decision"],"toxicity":[],"access":[{"country":"US","listPrice":"~$1,500 (Medicare CLFS rate established 2025, approximate)","reimbursement":"Medicare coverage via MolDX; NCCN-listed","source":"https://artera.ai","asOf":"2026-09-06"}],"regulatoryEvents":[{"date":"2025-08-14","type":"approval","region":"US","note":"De novo authorisation: first AI pathology test cleared for prognostic and predictive use in localised prostate cancer","source":"https://www.fda.gov/drugs/resources-information-approved-drugs/oncology-cancer-hematologic-malignancies-approval-notifications"}]},"route":"/drugs/artera-ai-prostate/","neighbours":{"cancer":[{"id":"prostate-high-risk","kind":"cancer","name":"Localised prostate cancer, high and very high risk","route":"/cancers/prostate-high-risk/"},{"id":"prostate-intermediate-risk","kind":"cancer","name":"Localised prostate cancer, intermediate risk","route":"/cancers/prostate-intermediate-risk/"},{"id":"prostate-low-risk","kind":"cancer","name":"Localised prostate cancer, very low and low risk","route":"/cancers/prostate-low-risk/"},{"id":"prostate","kind":"cancer","name":"Prostate cancer","route":"/cancers/prostate/"}],"technology":[{"id":"active-surveillance","kind":"technology","name":"Active surveillance","route":"/technologies/active-surveillance/"},{"id":"digital-pathology-ai","kind":"technology","name":"Digital pathology & AI","route":"/technologies/digital-pathology-ai/"},{"id":"pathology-foundation-model","kind":"technology","name":"Pathology & radiology foundation models","route":"/technologies/pathology-foundation-model/"}],"company":[{"id":"artera","kind":"company","name":"Artera","route":"/companies/artera/"},{"id":"nrg-oncology","kind":"company","name":"NRG Oncology","route":"/companies/nrg-oncology/"}],"drug":[{"id":"decipher-prostate","kind":"drug","name":"Decipher Prostate","route":"/drugs/decipher-prostate/"}],"pairing":[{"id":"ai-pathology-to-adt","kind":"pairing","name":"AI pathology → androgen deprivation duration","route":"/pairings/ai-pathology-to-adt/"}],"person":[{"id":"amar-kishan","kind":"person","name":"Amar U. Kishan","route":"/people/amar-kishan/"},{"id":"daniel-spratt","kind":"person","name":"Daniel E. Spratt","route":"/people/daniel-spratt/"}],"bottleneck":[{"id":"b-ai-validation","kind":"bottleneck","name":"AI that is built but not validated or deployed","route":"/bottlenecks/b-ai-validation/"}],"roadmap":[{"id":"ai-oncology-roadmap","kind":"roadmap","name":"AI in oncology roadmap: pattern readers → foundation models → agents in the workflow","route":"/roadmaps/ai-oncology-roadmap/"},{"id":"ai-oncology-clinic","kind":"roadmap","name":"AI in the oncology clinic: from narrow cleared tools to multimodal decision support","route":"/roadmaps/ai-oncology-clinic/"},{"id":"diagnostics-roadmap","kind":"roadmap","name":"Diagnostics roadmap: stains → gene panels → blood tests that decide treatment","route":"/roadmaps/diagnostics-roadmap/"}]}}