{"id":"W4410953661","doi":"10.1016/j.fertnstert.2025.05.168","title":"Recommendation to improve the rigor and impact of nonrandomized studies of interventions in fertility treatment research","year":2025,"lang":"en","type":"article","venue":"Fertility and Sterility","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Merck KGaA; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Merck Healthcare KGaA","keywords":"Fertility; Psychological intervention; Randomized controlled trial; Rigour; Medicine; Psychology; Gynecology; Environmental health; Internal medicine; Mathematics; Psychiatry; Population","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":[],"consensus_categories":[],"category_scores_codex":[0.00374373,0.0001247748,0.0005492502,0.0001223087,0.00008504064,0.00001274377,0.00009433981,0.00005833922,0.00003065715],"category_scores_gemma":[0.003280401,0.00007588095,0.0001260432,0.0002629247,0.0003666526,0.0001020965,0.000222024,0.0001318985,1.49437e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002218996,"about_ca_system_score_gemma":0.00005227538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008640333,"about_ca_topic_score_gemma":0.002187718,"domain_scores_codex":[0.9979829,0.0008041537,0.0006707113,0.0002745308,0.0001005103,0.0001672134],"domain_scores_gemma":[0.996997,0.002142697,0.0001049588,0.0004299236,0.0002889117,0.00003653351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.2545799,0.007951981,0.1589819,0.008478994,0.001606359,0.000001936869,0.03016843,0.000005133851,0.04400669,0.002771548,0.0002060088,0.4912412],"study_design_scores_gemma":[0.00145154,0.0007280334,0.7870935,0.0001967909,0.00003305425,1.012864e-7,0.0009222344,0.0001235467,0.01127142,0.198117,0.000009554845,0.00005325164],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944636,0.0001854586,0.003277299,0.0004007849,0.0000268507,0.001322783,0.00008335435,0.00001908355,0.0002207826],"genre_scores_gemma":[0.9982772,0.00006205883,0.001400592,0.000005707748,0.000001824353,0.0001890648,0.000003080203,0.000003136165,0.00005734886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6281116,"threshold_uncertainty_score":0.3927183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4673525755076959,"score_gpt":0.588457109762856,"score_spread":0.1211045342551602,"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."}}