{"id":"W3142047004","doi":"10.1109/trpms.2021.3071148","title":"Risk Assessment of Computer-Aided Diagnostic Software for Hepatic Resection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Qatar National Research Fund; Qatar Foundation","keywords":"Computer science; Software; Resection; Medicine; Software engineering; Surgery; Programming language","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":[0.007244254,0.0006930412,0.0004088487,0.002211704,0.0002500272,0.001499065,0.0007376918,0.0007715991,0.002521374],"category_scores_gemma":[0.07626435,0.0003076853,0.0009207574,0.001081659,0.0003917601,0.0007741909,0.0008547047,0.0005405253,0.0003969307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004599,"about_ca_system_score_gemma":0.0007088637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001931537,"about_ca_topic_score_gemma":0.00153028,"domain_scores_codex":[0.9929532,0.003420246,0.0003634802,0.0006592888,0.002381558,0.0002221209],"domain_scores_gemma":[0.8776138,0.09537759,0.0156361,0.004630087,0.00616721,0.0005750761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00298079,0.0003308286,0.5969811,0.0004273632,0.0008590183,0.0007103608,0.0003137457,0.1928493,0.006224058,0.00536639,0.001884925,0.1910722],"study_design_scores_gemma":[0.0001395466,0.002090907,0.1971952,0.0001414966,0.0008021159,0.002728791,0.0002617344,0.7650688,0.01831309,0.007535745,0.005565855,0.0001566079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9290846,0.002525529,0.0623364,0.0005625343,0.00006020346,0.0001759298,0.0007615484,0.0005722848,0.003920951],"genre_scores_gemma":[0.9865806,0.0002620904,0.01193915,0.00003858276,0.00001580066,0.00004885446,0.0003977891,0.00005398328,0.0006631507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007244254,"threshold_uncertainty_score":0.03831178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1030062713700515,"score_gpt":0.4566089389144098,"score_spread":0.3536026675443584,"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."}}