{"id":"W4388641629","doi":"10.2196/50328","title":"A Mobile App That Addresses Interpretability Challenges in Machine Learning–Based Diabetes Predictions: Survey-Based User Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Interpretability; Mobile apps; Computer science; Machine learning; Diabetes mellitus; Artificial intelligence; Human–computer interaction; Data science; World Wide Web; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01150797,0.000289433,0.0004401936,0.001413477,0.0005154658,0.0002587504,0.001641326,0.0001403533,0.00007134883],"category_scores_gemma":[0.001865922,0.0002512194,0.00009248396,0.003281594,0.000218161,0.0008148544,0.0009944321,0.002190077,0.0002282213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003160651,"about_ca_system_score_gemma":0.0003590952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009176118,"about_ca_topic_score_gemma":0.001452071,"domain_scores_codex":[0.9875277,0.00833215,0.0005425173,0.0008531197,0.001628807,0.001115739],"domain_scores_gemma":[0.9926791,0.005372668,0.0001481393,0.001005669,0.0005716219,0.0002228531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008241879,0.001039228,0.9473692,0.0006315798,0.0000281311,0.0000163471,0.02082482,0.01396093,0.00000863033,0.00007001412,0.000399055,0.01556962],"study_design_scores_gemma":[0.0005825509,0.001602092,0.5044712,0.0001171939,8.988551e-7,2.075453e-7,0.001267949,0.4905561,0.00008587542,0.00008985803,0.001077206,0.0001488556],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9887061,0.0008511075,0.003603549,0.001393075,0.0002794533,0.00350255,0.00008051318,0.00117404,0.0004096788],"genre_scores_gemma":[0.9959326,0.00009735677,0.0001808178,0.0000304426,0.00002758839,0.003538842,0.00006976786,0.00003289946,0.00008966687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4765952,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1623964573883651,"score_gpt":0.4401856112530089,"score_spread":0.2777891538646439,"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."}}