{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001517272,0.00009512558,0.0002044055,0.0001224955,0.001436908,0.0000154479,0.0001081162,0.0001926517,0.000615433],"category_scores_gemma":[0.001781649,0.00008092413,0.0000530248,0.0005136894,0.0002334003,0.0001350388,0.000002341627,0.0004322433,0.00001348813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008953141,"about_ca_system_score_gemma":0.001101855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007065754,"about_ca_topic_score_gemma":0.004146971,"domain_scores_codex":[0.9976404,0.0006369052,0.0005596993,0.0003069172,0.0005798017,0.0002762635],"domain_scores_gemma":[0.9872022,0.01200193,0.0002059572,0.0001167405,0.0002415928,0.0002315991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007957289,0.0004366115,0.1438224,0.0007062703,0.00005992975,0.000008718204,0.003086337,0.01930097,0.0000681328,0.002387079,0.001017949,0.829026],"study_design_scores_gemma":[0.0007396403,0.001184226,0.02822241,0.0006360997,0.00006247919,0.00000765007,0.001952567,0.9593204,0.003535451,0.002484997,0.001639779,0.0002142882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4685375,0.00004278377,0.5263563,0.002496606,0.001953824,0.0004367143,0.00007049263,0.00003944375,0.00006630365],"genre_scores_gemma":[0.9916798,0.0009559176,0.006483204,0.0004629487,0.0001631769,0.0001661492,0.000008147244,0.000006782713,0.00007381429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9400194,"threshold_uncertainty_score":0.9998631,"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."}}