{"id":"W2794910998","doi":"10.1016/j.ssmph.2018.03.007","title":"Machine learning in social epidemiology: Learning from experience","year":2018,"lang":"en","type":"article","venue":"SSM - Population Health","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Social learning; Epidemiology; Psychology; Computer science; Artificial intelligence; Knowledge management; Medicine","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00213748,0.0001732668,0.0003218485,0.00007307268,0.000863481,0.00001069808,0.0001430228,0.0001210818,0.0023129],"category_scores_gemma":[0.0007196817,0.0001866447,0.00004008264,0.0002969523,0.0002171713,0.0002817984,0.0001363841,0.0006260781,0.0007440199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008128591,"about_ca_system_score_gemma":0.00002547263,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02522408,"about_ca_topic_score_gemma":0.002406794,"domain_scores_codex":[0.996298,0.001430054,0.0006333273,0.0006876075,0.0002586073,0.000692455],"domain_scores_gemma":[0.9989859,0.0002807248,0.0003732896,0.0001651097,0.00000480992,0.0001900909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001347703,0.00002385846,0.9468713,0.000004408125,0.000001502929,0.000001179297,0.007715333,0.001266565,0.00009265308,0.00011248,0.00006528475,0.04383191],"study_design_scores_gemma":[0.0002911049,0.0001025652,0.9681429,0.00002159458,0.000001540447,0.000001115362,0.0007155691,0.02045442,0.00001321202,0.001616789,0.008473744,0.0001654842],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.991734,0.00009654166,0.003455965,0.002255865,0.0001338799,0.0003182262,0.000003618783,0.0001058728,0.001895979],"genre_scores_gemma":[0.9938413,0.00008087842,0.001875742,0.003488695,0.0002712303,0.00002703611,0.0001229046,0.00002605933,0.0002661548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04366643,"threshold_uncertainty_score":0.9985991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07282738971133168,"score_gpt":0.3731319701535039,"score_spread":0.3003045804421722,"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."}}