{"id":"W4404936882","doi":"10.1101/2024.11.29.24318211","title":"Methods for analytical validation of novel digital clinical measures: A simulation study","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Arnold Ventures","keywords":"Computer science; Model validation; Reliability engineering; Data science; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06148122,0.001045048,0.0009181529,0.001366956,0.0007241264,0.001445528,0.002225471,0.001607011,0.003804832],"category_scores_gemma":[0.1811595,0.0006350877,0.001485985,0.00141218,0.001529365,0.001686202,0.00206449,0.002421493,0.0003810315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001943493,"about_ca_system_score_gemma":0.002868087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007974098,"about_ca_topic_score_gemma":0.004801135,"domain_scores_codex":[0.9754636,0.02059375,0.0009194071,0.001108512,0.001545092,0.0003696623],"domain_scores_gemma":[0.693328,0.2735268,0.008725468,0.01290763,0.01062656,0.0008856368],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001597884,0.001072148,0.03652821,0.000714878,0.0005139886,0.0003090661,0.0007846107,0.8210544,0.001501367,0.06880035,0.002585498,0.06453756],"study_design_scores_gemma":[0.0003261958,0.0005489488,0.00212768,0.0001833228,0.00008445997,0.00008219208,0.0001395398,0.9792776,0.0009684201,0.01443629,0.001780027,0.00004542178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1429372,0.0004711811,0.8486007,0.000704698,0.0001095131,0.00258197,0.0006377324,0.0003566539,0.003600342],"genre_scores_gemma":[0.5524332,0.0002762784,0.4419303,0.0002235835,0.000033731,0.004024325,0.0004225106,0.00005676843,0.0005993337],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9385188,"threshold_uncertainty_score":0.3251477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8446405011541336,"score_gpt":0.7065212277254581,"score_spread":0.1381192734286755,"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."}}