{"id":"W4391244114","doi":"10.1002/sta4.641","title":"Differentially private outcome‐weighted learning for optimal dynamic treatment regime estimation","year":2024,"lang":"en","type":"article","venue":"Stat","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of New Brunswick","funders":"Canadian Statistical Sciences Institute; Fonds de Recherche du Québec - Santé; National Institutes of Health; National Institute of Mental Health; Canada Excellence Research Chairs, Government of Canada","keywords":"Differential privacy; Computer science; Support vector machine; Leverage (statistics); Machine learning; Context (archaeology); Artificial intelligence; Estimator; Data mining; Precision medicine; Outcome (game theory); Information privacy; Set (abstract data type); Mathematics; Computer security; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01971112,0.001340915,0.002893263,0.001127612,0.0009093158,0.002908557,0.00304235,0.002777484,0.00446907],"category_scores_gemma":[0.09459101,0.001016794,0.001500436,0.001740062,0.003803426,0.005276482,0.004463625,0.00560935,0.0009043481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00332625,"about_ca_system_score_gemma":0.004444245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002044546,"about_ca_topic_score_gemma":0.001694022,"domain_scores_codex":[0.987868,0.007131898,0.0005547361,0.001783943,0.001929248,0.0007322237],"domain_scores_gemma":[0.936291,0.05224599,0.002786271,0.006365997,0.001590346,0.0007204675],"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":[0.0009441506,0.0003436608,0.005978497,0.0004761685,0.0003345514,0.0003668686,0.0004132545,0.4755602,0.001698264,0.3978224,0.006187205,0.1098747],"study_design_scores_gemma":[0.0001081095,0.0001081958,0.0004926604,0.00009672406,0.00004456881,0.0001070835,0.00003867415,0.6921517,0.001234646,0.3037073,0.00187869,0.00003175738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01055984,0.0005662099,0.9840776,0.001955779,0.0000696536,0.0001592922,0.0004769726,0.0002493985,0.001885224],"genre_scores_gemma":[0.6927282,0.001621696,0.2938251,0.002324944,0.0004720413,0.001015051,0.001774168,0.0002202497,0.006018532],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01971112,"threshold_uncertainty_score":0.1042436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02996735987845892,"score_gpt":0.3163899338247644,"score_spread":0.2864225739463054,"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."}}