{"id":"W4403538369","doi":"10.1016/j.dajour.2024.100523","title":"A multi-criteria decision analysis framework for evaluating deep learning models in healthcare research","year":2024,"lang":"en","type":"article","venue":"Decision Analytics Journal","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Humber Polytechnic; Concordia University","funders":"","keywords":"Health care; Computer science; Management science; Decision analysis; Data science; Knowledge management; Artificial intelligence; Psychology; Political science; Engineering; Mathematics","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":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0210971,0.0003024167,0.0006919548,0.004776465,0.0009991203,0.002432261,0.001790255,0.0003480362,0.00008093012],"category_scores_gemma":[0.01135309,0.0002659693,0.0005331238,0.008023626,0.00005243613,0.0008261964,0.0005952055,0.003477842,0.00004991428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007438188,"about_ca_system_score_gemma":0.0005663297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001385179,"about_ca_topic_score_gemma":0.0003331098,"domain_scores_codex":[0.9921712,0.001596683,0.001533224,0.0010895,0.002508338,0.001101017],"domain_scores_gemma":[0.9859499,0.01063568,0.0002605098,0.000896756,0.001693411,0.0005637012],"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":[0.00008275219,0.00005627822,0.004340868,0.00007202548,0.0001172705,0.000194328,0.002245566,0.4613782,0.00001728244,0.01864963,0.0001586906,0.5126871],"study_design_scores_gemma":[0.0003450985,0.0002615505,0.002766533,0.0006993195,0.00004476249,0.00007518264,0.0001813058,0.763529,0.000002102006,0.2314475,0.0004531838,0.0001944774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02717918,0.004252543,0.9632211,0.003948708,0.0009000028,0.0003477235,0.000003693781,0.0001234821,0.00002354768],"genre_scores_gemma":[0.4889015,0.000309691,0.5104017,0.0001365944,0.0001521438,0.00001517068,0.000003811427,0.00002888152,0.00005053154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5124927,"threshold_uncertainty_score":0.9999793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2845120089915341,"score_gpt":0.5449850039244639,"score_spread":0.2604729949329298,"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."}}