{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05489096,0.004000512,0.002400624,0.00903808,0.003168335,0.008269947,0.007138475,0.003245464,0.006051172],"category_scores_gemma":[0.1391677,0.002462226,0.005367057,0.004712669,0.01082556,0.01142422,0.01589333,0.009329507,0.002273488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00416263,"about_ca_system_score_gemma":0.01071809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005708484,"about_ca_topic_score_gemma":0.006825183,"domain_scores_codex":[0.9534953,0.03030827,0.003510758,0.003959563,0.007689338,0.001036745],"domain_scores_gemma":[0.8521801,0.1100804,0.005189413,0.0168505,0.01399736,0.001702158],"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":[0.000298746,0.0006404623,0.00609792,0.001982405,0.0005043137,0.0006099005,0.005304631,0.149127,0.004061306,0.4985653,0.01021126,0.3225968],"study_design_scores_gemma":[0.00006753288,0.0001643942,0.0003365999,0.0005622489,0.00007616497,0.0001177371,0.0006957592,0.4003917,0.002214887,0.581472,0.01381245,0.00008847889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008611621,0.0001143001,0.9964785,0.0007608888,0.00002739963,0.0003227401,0.00007102924,0.0004207041,0.0009433284],"genre_scores_gemma":[0.02396859,0.0001262716,0.9740809,0.0002774188,0.00004964131,0.0007770212,0.000217591,0.0001164956,0.0003860944],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05489096,"threshold_uncertainty_score":0.2902946,"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."}}