{"id":"W4205900565","doi":"10.1038/s41591-021-01620-2","title":"Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge","year":2022,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":494,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"EIT Health; Syöpäsäätiö; KWF Kankerbestrijding; Vetenskapsrådet; Karolinska Institutet; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Google; Academy of Finland; Verily Life Sciences; Åke Wiberg Stiftelse; Cancerfonden","keywords":"Prostate cancer; Grading (engineering); Prostate; Confidence interval; Medical imaging; Prospective cohort study","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06854763,0.001331082,0.001379389,0.00270752,0.001546749,0.005780102,0.002466828,0.001897562,0.002224252],"category_scores_gemma":[0.1367425,0.000435016,0.00118848,0.001951144,0.002657766,0.003388376,0.006011096,0.004989385,0.001095753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002187505,"about_ca_system_score_gemma":0.007017518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00612434,"about_ca_topic_score_gemma":0.006212272,"domain_scores_codex":[0.9617198,0.0257491,0.001358974,0.004236608,0.006403722,0.0005317513],"domain_scores_gemma":[0.9211894,0.04746087,0.004672315,0.0111812,0.0126397,0.002856478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0009316725,0.0006120964,0.07334652,0.0008698897,0.001548396,0.0001487391,0.0006623511,0.03728292,0.004777217,0.02225697,0.05578601,0.8017772],"study_design_scores_gemma":[0.0004874218,0.001959123,0.09252787,0.001649632,0.0006946432,0.001315901,0.0008798016,0.5311265,0.01324745,0.2019058,0.1537662,0.0004396733],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2556599,0.02861452,0.5806355,0.09188541,0.004925931,0.001999095,0.004751301,0.005872048,0.02565616],"genre_scores_gemma":[0.5168129,0.003498225,0.4594269,0.00766061,0.001585455,0.001146793,0.006091257,0.001030309,0.002747656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06854763,"threshold_uncertainty_score":0.3625188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03961981370886775,"score_gpt":0.3412773054710338,"score_spread":0.3016574917621661,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}