{"id":"W4225262102","doi":"10.1007/s10985-022-09554-8","title":"Privacy-preserving estimation of an optimal individualized treatment rule: a case study in maximizing time to severe depression-related outcomes","year":2022,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"National Institute of Mental Health; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Robustness (evolution); Flexibility (engineering); Confounding; Computer science; Context (archaeology); Regression; Econometrics; Data mining; Regression analysis; Machine learning; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001236349,0.0003005349,0.000952945,0.0009937175,0.0002036427,0.00005465483,0.001270965,0.00006605362,0.002572029],"category_scores_gemma":[0.001049267,0.0002741335,0.0001216644,0.002061271,0.0000217439,0.0006536206,0.002827697,0.0002082453,0.00001446465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002397096,"about_ca_system_score_gemma":0.00006063604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00162377,"about_ca_topic_score_gemma":0.0002197085,"domain_scores_codex":[0.996747,0.0006668302,0.0009629937,0.0007330064,0.0005918823,0.0002982892],"domain_scores_gemma":[0.9958536,0.0006471839,0.0004503462,0.002862322,0.00005483119,0.0001316853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005942069,0.01030821,0.2139305,0.0001084084,0.01051242,0.004978479,0.03778273,0.6690176,0.0006045345,0.00008135368,0.0009727777,0.0511088],"study_design_scores_gemma":[0.003247566,0.0009468746,0.007960473,0.00005700436,0.006408195,0.0002680155,0.0105793,0.9650667,0.0004697793,0.00398137,0.00007461963,0.000940098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867649,0.00001980124,0.01060843,0.00006872561,0.000009225036,0.001064313,0.001154465,0.0002200445,0.00009008079],"genre_scores_gemma":[0.7632845,0.000001138158,0.234649,0.00001840133,0.000004205433,0.0002325066,0.001590602,0.00003428186,0.000185378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2960491,"threshold_uncertainty_score":0.9999711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1101066198287473,"score_gpt":0.4265556289728123,"score_spread":0.316449009144065,"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."}}