{"id":"W4381734045","doi":"10.1093/humrep/dead093.101","title":"O-087 Patient-centric, machine learning (ML)-based personalised prognostics supports fertility specialists to improve access to assisted reproductive technology (ART) and increase overall live birth (LB) outcomes","year":2023,"lang":"en","type":"article","venue":"Human Reproduction","topic":"Assisted Reproductive Technology and Twin Pregnancy","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"CReATe Fertility Centre; Translational Research in Oncology","funders":"","keywords":"Prognostics; Assisted reproductive technology; Fertility; Infertility; Reproductive medicine; Cohort; Medicine; Computer science; Population; Pregnancy; Environmental health; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.004840794,0.0001365683,0.0002729831,0.0006062796,0.0004328565,0.00100361,0.0005119509,0.0003321777,0.01052111],"category_scores_gemma":[0.01889348,0.0001521795,0.0004634327,0.0007600923,0.0002588096,0.0003179811,0.0006832604,0.0003441325,0.001623592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002043855,"about_ca_system_score_gemma":0.004758564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04256486,"about_ca_topic_score_gemma":0.07656835,"domain_scores_codex":[0.998378,0.0008104985,0.0001565542,0.0001312112,0.0003655671,0.0001581186],"domain_scores_gemma":[0.9875383,0.005641204,0.002801389,0.0006842212,0.002127641,0.001207235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001129689,0.0002966431,0.7198017,0.0003787047,0.00009538641,0.0001207602,0.0007269011,0.001552149,0.0004475968,0.0002639089,0.03240243,0.2427842],"study_design_scores_gemma":[0.0003811237,0.001442809,0.9334738,0.0007481746,0.0001748778,0.0003266827,0.001511156,0.00884767,0.001869916,0.0004101951,0.05075006,0.00006365275],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9122132,0.001796796,0.008877838,0.007445259,0.0002582836,0.001708622,0.02491288,0.001186838,0.04160025],"genre_scores_gemma":[0.9782087,0.0006888515,0.01066269,0.0008596655,0.000168077,0.0004998383,0.004740344,0.00005167485,0.004120252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04256486,"threshold_uncertainty_score":0.08463424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02573090087572455,"score_gpt":0.3028789259772804,"score_spread":0.2771480251015558,"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."}}