{"id":"W4392662318","doi":"10.1080/00031305.2024.2327535","title":"Thick Data Analytics (TDA): An Iterative and Inductive Framework for Algorithmic Improvement","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; School of Medicine, Stanford University; National Institutes of Health; Canada Excellence Research Chairs, Government of Canada","keywords":"Computer science; SAFER; Subject-matter expert; USable; Data science; Analytics; Domain (mathematical analysis); Machine learning; Data mining; Domain knowledge; Frame (networking); Artificial intelligence; Risk analysis (engineering); Expert system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005984974,0.0001721952,0.0002309088,0.00008660072,0.0002690413,0.0004459015,0.001183456,0.00002762986,0.000005647475],"category_scores_gemma":[0.0003644418,0.0001238364,0.00001889058,0.0004924327,0.0003122531,0.0003387626,0.0004941343,0.0004620234,0.000007735952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006297875,"about_ca_system_score_gemma":0.0001627837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001185674,"about_ca_topic_score_gemma":0.00009805004,"domain_scores_codex":[0.9983098,0.0002194017,0.0002287963,0.0006689309,0.0002464792,0.0003265781],"domain_scores_gemma":[0.9969935,0.00147899,0.0001513677,0.001164103,0.00009125167,0.0001207171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000100759,0.00001832824,0.0001172358,0.00004669596,0.00005920242,0.00001321568,0.004751384,0.00003488834,0.00002267709,0.3549637,0.0005003568,0.6394622],"study_design_scores_gemma":[0.00006337857,0.0009578747,0.003836826,0.00005897081,0.00003618714,0.000007548812,0.001067523,0.8903852,0.00001320063,0.1001067,0.003262794,0.0002038599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00526478,0.0001726043,0.9870006,0.006109431,0.0003100148,0.0004471759,0.0005067501,0.0001465114,0.00004207963],"genre_scores_gemma":[0.3998801,0.00003029064,0.5977347,0.001899948,0.0003042706,0.00004632037,0.0000443928,0.00002386387,0.00003604536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8903502,"threshold_uncertainty_score":0.5049903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0671994435639882,"score_gpt":0.4028620339116792,"score_spread":0.335662590347691,"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."}}