{"id":"W4409368810","doi":"10.1002/sim.70049","title":"A Generalized Phase I/II Dose Optimization Trial Design With Multi‐Categorical and Multi‐Graded Outcomes","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Simon Fraser University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Categorical variable; Monotonic function; Benchmarking; Robustness (evolution); Computer science; Maximum tolerated dose; Optimal design; Clinical trial; Continuous variable; Reliability (semiconductor); Reliability engineering; Mathematical optimization; Medicine; Mathematics; Machine learning","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00358311,0.0003591383,0.001403788,0.0002817375,0.0001428684,0.00002616308,0.0002230499,0.0002126433,0.000213874],"category_scores_gemma":[0.1252545,0.0002427504,0.0000369579,0.0005311327,0.0005995711,0.00004435603,0.0001051002,0.0004492071,0.000001538921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009320905,"about_ca_system_score_gemma":0.0001388864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005582536,"about_ca_topic_score_gemma":0.000027868,"domain_scores_codex":[0.9957371,0.001329599,0.001497348,0.0005644524,0.0004823084,0.0003892395],"domain_scores_gemma":[0.9596681,0.03919164,0.0003310334,0.0004237799,0.0001980415,0.0001873837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.05786354,0.005658694,0.0005736415,0.0005605763,0.00055923,0.0004277707,0.001343023,0.001324779,0.0001816364,0.8788407,0.01006817,0.04259825],"study_design_scores_gemma":[0.2666955,0.003121477,0.0001755811,0.0002081785,0.0004924464,0.000004538228,0.0001217161,0.1941886,0.00004749436,0.5345702,0.00005832231,0.0003159941],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002056128,0.00007712883,0.99397,0.0008660128,0.0007491781,0.002038979,0.00009249491,0.00008173856,0.00006835194],"genre_scores_gemma":[0.006637603,0.0001335853,0.9917489,0.0004489562,0.0001324783,0.0001929787,0.00002162586,0.00004184213,0.0006419817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3442705,"threshold_uncertainty_score":0.9899074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5347114705751628,"score_gpt":0.5995985752183284,"score_spread":0.0648871046431656,"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."}}