{"id":"W4412163759","doi":"10.1158/1557-3265.aimachine-b001","title":"Abstract B001: Jarvais: A modular framework to standardize machine learning workflows and accelerate reproducible AI in oncology – benchmarking against a human-developed model for predicting emergency department visits during cancer treatment","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Benchmarking; Workflow; Modular design; Medicine; Cancer; Emergency department; Cancer treatment; Oncology; Medical physics; Computer science; Internal medicine; Business; Nursing; Operating system; Database","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01038336,0.00276246,0.0009958147,0.001619704,0.0009250463,0.003163345,0.004912049,0.001415296,0.02033401],"category_scores_gemma":[0.03161592,0.001620149,0.002492998,0.0008587349,0.002069332,0.003712503,0.005711101,0.004195674,0.01819151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001374365,"about_ca_system_score_gemma":0.005391574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005037968,"about_ca_topic_score_gemma":0.003685133,"domain_scores_codex":[0.9953725,0.001371011,0.0004567256,0.001139345,0.001301789,0.0003586918],"domain_scores_gemma":[0.9880432,0.005232663,0.0009638994,0.002983917,0.001974647,0.0008016585],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003572628,0.001164912,0.03136756,0.002908126,0.0008660795,0.0007626907,0.001406541,0.09527196,0.02819918,0.03061986,0.5538183,0.2500421],"study_design_scores_gemma":[0.0007231551,0.0005509396,0.01067046,0.0004218476,0.0001221673,0.0003841608,0.0000934674,0.7502337,0.04223232,0.03845729,0.155715,0.0003955453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01116718,0.0002116011,0.2713722,0.0009613353,0.0003886253,0.0006910464,0.01364467,0.6972424,0.004320884],"genre_scores_gemma":[0.1993837,0.0004844297,0.5177254,0.002539099,0.0003376985,0.003517671,0.08584026,0.1816764,0.008495252],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9896166,"threshold_uncertainty_score":0.06802404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1611582012071351,"score_gpt":0.549015948345654,"score_spread":0.3878577471385189,"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."}}