{"id":"W4412851193","doi":"10.1016/j.ajt.2025.07.531","title":"Machine Learning Models for Predicting Post-Transplant Lymphoproliferative Disease Risk: Insights from a Large-Scale Retrospective Cohort Study","year":2025,"lang":"en","type":"article","venue":"American Journal of Transplantation","topic":"Transplantation: Methods and Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Medicine; Retrospective cohort study; Lymphoproliferative disease; Cohort; Scale (ratio); Disease; Oncology; Intensive care medicine; Machine learning; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008654813,0.0006894864,0.0005909019,0.0009809728,0.0004675183,0.00145881,0.0009534663,0.0006026016,0.001554031],"category_scores_gemma":[0.01817064,0.0003515731,0.001467993,0.001121493,0.0002573607,0.0008665575,0.0006940796,0.00161742,0.0004002108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004027297,"about_ca_system_score_gemma":0.0007049439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005260698,"about_ca_topic_score_gemma":0.005810523,"domain_scores_codex":[0.9982367,0.001017166,0.0001348647,0.0002966969,0.0001758033,0.0001389299],"domain_scores_gemma":[0.9882436,0.007683613,0.001323871,0.001676976,0.0007754581,0.0002965062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007734264,0.000245724,0.9759528,0.00003340872,0.001243577,0.0001435444,0.0001206398,0.004114259,0.0002480247,0.0004108265,0.002032767,0.01468104],"study_design_scores_gemma":[0.0002459767,0.0007799647,0.8470448,0.0001106247,0.002234591,0.001235205,0.0008325051,0.1383186,0.0006510419,0.004090833,0.004377827,0.00007799605],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874166,0.001014327,0.007339375,0.0006370621,0.00005275691,0.00003575189,0.002978674,0.00004402476,0.0004813777],"genre_scores_gemma":[0.9921726,0.0005127287,0.003155034,0.00009000895,0.00005835974,0.00004224094,0.003529191,0.00002335117,0.000416415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008654813,"threshold_uncertainty_score":0.0457716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009319291644863795,"score_gpt":0.2869781076814554,"score_spread":0.2776588160365916,"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."}}