{"id":"W4221077687","doi":"10.1038/s41598-022-06484-1","title":"Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Computer science; Receiver operating characteristic; Artificial intelligence; Robustness (evolution); False positive paradox; Machine learning; Predictive modelling; Data mining","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":[],"category_scores_codex":[0.0294327,0.00008740889,0.0001723373,0.0003908831,0.0002558832,0.00006240014,0.000264205,0.0000320582,0.00001991999],"category_scores_gemma":[0.0009247719,0.00008386522,0.00001792981,0.0008552133,0.00006924372,0.000232711,0.0003256163,0.0001795893,4.239817e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001410124,"about_ca_system_score_gemma":0.0004661899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000448048,"about_ca_topic_score_gemma":0.0003605549,"domain_scores_codex":[0.9953681,0.0009513866,0.000946888,0.0008246658,0.001742164,0.0001667832],"domain_scores_gemma":[0.9982269,0.00007272449,0.0005330445,0.0008560736,0.0002186956,0.00009260438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007072988,0.00004191893,0.009211084,0.00001878138,0.000001651417,0.00001759552,0.001641444,0.9488527,0.0001043743,0.0009721763,0.001304061,0.03782719],"study_design_scores_gemma":[0.0002150597,0.00011858,0.006219195,0.00002234767,0.000006447583,0.00002128896,0.00009167912,0.9828582,0.00001346744,0.01007917,0.0002756102,0.0000789988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6924171,0.00004779867,0.3034116,0.0013079,0.002188873,0.000550121,0.00001238488,0.00002643094,0.00003772137],"genre_scores_gemma":[0.9776121,3.85775e-7,0.02169401,0.00009964735,0.0000314892,0.00005610953,0.0004807109,0.000006308158,0.00001919571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.285195,"threshold_uncertainty_score":0.9994033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1090369519650329,"score_gpt":0.3930394425137202,"score_spread":0.2840024905486873,"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."}}