{"id":"W2964417596","doi":"10.1093/bioinformatics/btz602","title":"Non-parametric individual treatment effect estimation for survival data with random forests","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Random forest; Censoring (clinical trials); Computer science; Estimation; Statistics; Parametric statistics; Population; Random effects model; Survival analysis; Average treatment effect; Machine learning; Artificial intelligence; Data mining; Mathematics; Medicine; Propensity score matching; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0007355984,0.0003041165,0.0005268789,0.0002000041,0.00007396415,0.00009599676,0.0004708983,0.0001203724,0.00001629997],"category_scores_gemma":[0.0009647264,0.0001934859,0.00006412326,0.0002985047,0.00004346644,0.0008075175,0.0001334604,0.00009099999,0.00006549839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001156668,"about_ca_system_score_gemma":0.00008935427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008807459,"about_ca_topic_score_gemma":0.00003166332,"domain_scores_codex":[0.9985863,0.00002509708,0.0004801307,0.0001997949,0.0003755409,0.0003331582],"domain_scores_gemma":[0.9963617,0.001982547,0.0003523963,0.001088895,0.0001357106,0.00007872725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007812318,0.002369835,0.118916,0.0136947,0.003495979,0.00001900764,0.007579912,0.007511971,0.0001431312,0.07037035,0.03725125,0.7308356],"study_design_scores_gemma":[0.01694353,0.007909044,0.002389262,0.0004156377,0.0007379927,0.00002333054,0.000289761,0.9290019,0.007831642,0.0306929,0.002681444,0.001083571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1851714,0.00001275102,0.8089134,0.00001689237,0.0001798707,0.003776213,0.0002701334,0.0003148987,0.001344521],"genre_scores_gemma":[0.3368844,0.00001083966,0.6616674,0.00002228913,0.00005394336,0.0002456818,0.0009055343,0.00004585581,0.0001640683],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9214899,"threshold_uncertainty_score":0.7890126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112018737931895,"score_gpt":0.3930259803352855,"score_spread":0.2810072424033905,"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."}}