{"id":"W4417505513","doi":"10.1016/j.jclinepi.2025.112117","title":"Sequential sample size calculations and learning curves safeguard the robust development of a clinical prediction model for individuals","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute for Health and Care Research; Engineering and Physical Sciences Research Council; Department of Health and Social Care; Medical Research Council; Birmingham Biomedical Research Centre; University Hospitals Birmingham NHS Foundation Trust","keywords":"Sample size determination; Safeguard; Sample (material); Large sample; Predictive modelling; Early stopping","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0643865,0.0001340875,0.001528901,0.00009495077,0.0002891082,0.00001411102,0.000653965,0.0003213304,0.000006807214],"category_scores_gemma":[0.3108932,0.00008951235,0.0004508948,0.000187655,0.0002579117,0.0001477526,0.0003015992,0.001675746,4.834527e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002584402,"about_ca_system_score_gemma":0.001241807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002762699,"about_ca_topic_score_gemma":0.00002635438,"domain_scores_codex":[0.985451,0.007108833,0.006579414,0.0003461745,0.0002271574,0.0002873965],"domain_scores_gemma":[0.7659158,0.2270165,0.005540867,0.0004675915,0.0007943091,0.0002649793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000847225,0.00008505832,0.787322,0.0001624299,0.0001951289,5.290727e-7,0.0002938953,0.1232825,0.000001307028,0.01199438,0.001925654,0.0746524],"study_design_scores_gemma":[0.0006409338,0.0002488895,0.3722198,0.0002146679,0.00004542635,0.000008667495,0.00001635482,0.6081734,7.145749e-7,0.01320569,0.005175178,0.0000502136],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07624114,0.0005353691,0.896749,0.02517006,0.0009885023,0.0002496868,0.000007890455,0.00001912093,0.00003922499],"genre_scores_gemma":[0.2951599,0.0005467499,0.7005891,0.003264478,0.0003278781,0.00001237539,0.000003621888,0.000006847481,0.00008901241],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.484891,"threshold_uncertainty_score":0.963411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3581055674125369,"score_gpt":0.5342643376275771,"score_spread":0.1761587702150402,"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."}}