{"id":"W6939963031","doi":"10.6084/m9.figshare.25223503","title":"Additional file 1 of Characterizing the limitations of using diagnosis codes in the context of machine learning for healthcare","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Context (archaeology); Health care; Key (lock); Training set","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003418059,0.0006850156,0.0007357012,0.002749933,0.000636905,0.001845112,0.001501389,0.001687435,0.8074126],"category_scores_gemma":[0.1146495,0.0004068232,0.0007306071,0.002930667,0.000271457,0.00154318,0.00114395,0.0008123748,0.1027749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001294988,"about_ca_system_score_gemma":0.002366186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008183427,"about_ca_topic_score_gemma":0.01347527,"domain_scores_codex":[0.9981229,0.000552983,0.000382832,0.0003841991,0.0004266101,0.0001305779],"domain_scores_gemma":[0.8150138,0.1672961,0.003538734,0.004238741,0.009175876,0.0007367074],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004893062,0.0002399557,0.006156796,0.004695801,0.0000806163,0.00009835158,0.0001450577,0.001189776,0.0001457147,0.00247148,0.9569883,0.02729886],"study_design_scores_gemma":[0.004229805,0.0006481181,0.06636911,0.01087131,0.0004206965,0.001489741,0.001778643,0.01795028,0.002526377,0.05054183,0.8429062,0.0002679151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0006016762,0.00003585186,0.0009486762,0.0001969499,0.00003087872,0.0001152476,0.996289,0.0003154803,0.001466138],"genre_scores_gemma":[0.03248413,0.0002313954,0.01899551,0.001130536,0.0001497973,0.002515161,0.9343265,0.0009202178,0.009246859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9965819,"threshold_uncertainty_score":0.2747026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1212153521135158,"score_gpt":0.3017940950271205,"score_spread":0.1805787429136048,"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."}}