{"id":"W4405381253","doi":"10.20517/ais.2024.69","title":"Clinical deployment of machine learning models in craniofacial surgery: considerations for adoption and implementation","year":2024,"lang":"en","type":"article","venue":"Artificial Intelligence Surgery","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Software deployment; Craniofacial surgery; Craniofacial; Computer science; Medicine; Software engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.002562166,0.0001466911,0.0004528689,0.0004703663,0.0001231709,0.00005674123,0.00002392529,0.0001366464,0.0001679478],"category_scores_gemma":[0.001225181,0.0001473919,0.0002131162,0.0003767275,0.0001299268,0.000277946,0.00001611539,0.0002507875,0.00001365944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000793162,"about_ca_system_score_gemma":0.0005727298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00138203,"about_ca_topic_score_gemma":0.001256155,"domain_scores_codex":[0.9973456,0.0001557978,0.001620046,0.0003845587,0.0002012551,0.0002927946],"domain_scores_gemma":[0.9942223,0.005144813,0.0001464412,0.0001297483,0.0002359833,0.0001207137],"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":[0.0002363276,0.000223951,0.135485,0.000414458,0.0000479353,0.0000151743,0.002160686,0.0006649853,0.000552616,0.01751207,0.0004623614,0.8422245],"study_design_scores_gemma":[0.0000605721,0.0007389443,0.01764824,0.001536535,0.0003279727,0.00009274584,0.01524221,0.4929418,0.07219781,0.396337,0.002040729,0.0008354826],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554983,0.0009640305,0.0378894,0.003204109,0.00145343,0.0008414312,0.00002516719,0.00008691531,0.00003724628],"genre_scores_gemma":[0.9966666,0.001609536,0.0009578224,0.0001740787,0.0003347766,0.0001172523,0.00009654619,0.00002608343,0.00001727642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.841389,"threshold_uncertainty_score":0.6010469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4314351839765875,"score_gpt":0.4902099819919613,"score_spread":0.05877479801537372,"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."}}