{"id":"W2971656115","doi":"10.1016/s2589-7500(19)30112-8","title":"Turning the crank for machine learning: ease, at what expense?","year":2019,"lang":"en","type":"letter","venue":"The Lancet Digital Health","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Health care; Transformative learning; Deep learning; Machine learning; Workflow; Data science; Psychology; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03214027,0.002263543,0.002353801,0.004433643,0.003382521,0.01660809,0.004059361,0.008569521,0.04054181],"category_scores_gemma":[0.1832578,0.001312421,0.002245856,0.003027629,0.01782561,0.04306212,0.009796806,0.01699114,0.04551668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002194398,"about_ca_system_score_gemma":0.004414956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005528599,"about_ca_topic_score_gemma":0.006048405,"domain_scores_codex":[0.9664473,0.01611027,0.002015995,0.002463891,0.0113572,0.001605281],"domain_scores_gemma":[0.8731477,0.07554809,0.004097531,0.02372696,0.01701846,0.00646132],"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":[0.0005442397,0.0002489511,0.003145429,0.002165873,0.0002410334,0.000542529,0.002733895,0.0008884849,0.001250535,0.09937878,0.4895416,0.3993186],"study_design_scores_gemma":[0.0001325233,0.0002947798,0.00203187,0.004137912,0.0001369786,0.001512333,0.003324972,0.002333601,0.001306702,0.3458712,0.6386801,0.0002371599],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.004031665,0.04291572,0.06955619,0.8307484,0.01339669,0.0001282775,0.0006631446,0.003043271,0.03551675],"genre_scores_gemma":[0.1560222,0.07340427,0.285668,0.3580416,0.05196086,0.0008747642,0.001437001,0.01027889,0.06231239],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.04054181,"threshold_uncertainty_score":0.169976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2266024426136011,"score_gpt":0.4228292533615161,"score_spread":0.1962268107479149,"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."}}