{"id":"W2912814480","doi":"10.1002/cjp2.127","title":"The use of digital pathology and image analysis in clinical trials","year":2019,"lang":"en","type":"article","venue":"The Journal of Pathology Clinical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Barts and The London School of Medicine and Dentistry; Medical Research Council; Newcastle upon Tyne Hospitals NHS Foundation Trust; Queen's University; Cancer Research UK; Queen's University Belfast; University of Oxford; University of Southampton; Newcastle University; National Cancer Research Institute; Bristol-Myers Squibb; UK Research and Innovation; University of Leeds; National Institute for Health and Care Research","keywords":"Digital pathology; Digital image analysis; Computer science; Medical physics; Clinical trial; Data science; Key (lock); Digital image; Pathology; Medicine; Artificial intelligence; Image processing; Image (mathematics); Computer vision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07281943,0.0009705066,0.00167752,0.007774413,0.0009113724,0.0103475,0.002547392,0.003272609,0.01012607],"category_scores_gemma":[0.1314104,0.0009756293,0.001575151,0.005624608,0.007088312,0.006200037,0.005094496,0.004561415,0.003533684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002579135,"about_ca_system_score_gemma":0.004528589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001260812,"about_ca_topic_score_gemma":0.001486932,"domain_scores_codex":[0.9390848,0.04134301,0.004037204,0.003196484,0.01172284,0.0006156627],"domain_scores_gemma":[0.7976072,0.1449016,0.01790515,0.02107032,0.01618847,0.0023273],"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":[0.0009247882,0.000165649,0.006575685,0.006351722,0.0003759965,0.0006892773,0.0009490914,0.004701272,0.008616267,0.04963721,0.02439027,0.8966228],"study_design_scores_gemma":[0.0006310686,0.003022456,0.02314515,0.01344189,0.0007650316,0.0123729,0.001602991,0.02027257,0.03495364,0.2087741,0.6802471,0.000771252],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01637045,0.1138564,0.7625506,0.03525331,0.004785683,0.002674309,0.001499359,0.004398383,0.05861147],"genre_scores_gemma":[0.1445214,0.06504199,0.7646984,0.01018058,0.004817252,0.002634033,0.0008150887,0.0008451533,0.006446093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07281943,"threshold_uncertainty_score":0.3851106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.517263181926019,"score_gpt":0.5866856574035789,"score_spread":0.06942247547755998,"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."}}