{"id":"W4410811839","doi":"10.1097/cce.0000000000001268","title":"Predictions With a Purpose: Elevating Standards for Clinical Modeling Research","year":2025,"lang":"en","type":"editorial","venue":"Critical Care Explorations","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Computer science; Data science; Management science; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004103887,0.0003561089,0.0006025837,0.0005049907,0.002094127,0.0009849822,0.001507149,0.0009883551,0.000009871646],"category_scores_gemma":[0.07108302,0.0003404124,0.0002158545,0.001178656,0.0003091067,0.0006730966,0.000589311,0.004280945,0.000008527763],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007106762,"about_ca_system_score_gemma":0.01146409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007756562,"about_ca_topic_score_gemma":0.0002507867,"domain_scores_codex":[0.9927169,0.00116262,0.001049461,0.001434779,0.002730145,0.0009061163],"domain_scores_gemma":[0.9609067,0.01772278,0.00009943797,0.00157556,0.01929926,0.000396276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000426178,0.00007058797,0.00002690601,0.001446878,0.00002989927,0.00001157385,0.001375861,0.003108327,1.859355e-7,0.08141976,0.9076609,0.004806533],"study_design_scores_gemma":[0.0004343099,0.0009820299,0.000001261611,0.00093276,0.00005925272,0.000001273111,0.00133943,0.3356171,7.564269e-7,0.00582748,0.6544675,0.0003369045],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"editorial","genre_scores_codex":[0.000003013129,0.0008376685,0.6990521,0.004276714,0.2923906,0.000926864,0.001176601,0.0003913524,0.0009451389],"genre_scores_gemma":[0.00997791,0.0002412239,0.2105586,0.0001594024,0.7718678,0.004640751,0.001846288,0.0001264933,0.0005815595],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.4884935,"threshold_uncertainty_score":0.9999048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2122488646038128,"score_gpt":0.5577366774328856,"score_spread":0.3454878128290728,"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."}}