{"id":"W4412108432","doi":"10.2196/68817","title":"Improving the Readability of Institutional Heart Failure–Related Patient Education Materials Using GPT-4: Observational Study","year":2025,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Readability; Heart failure; Medicine; Index (typography); Internal medicine; Observational study; Cardiology; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0005416032,0.00009113512,0.000221282,0.00008938925,0.0002085704,0.00001957256,0.00006012282,0.00007806315,0.00005651718],"category_scores_gemma":[0.000328529,0.0000690037,0.00007778178,0.0003437368,0.00009506424,0.000100783,0.00003518416,0.000125569,0.00000675715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002841161,"about_ca_system_score_gemma":0.001952368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002642555,"about_ca_topic_score_gemma":0.0000358396,"domain_scores_codex":[0.9986789,0.0001534285,0.0005733957,0.0002056021,0.0002627854,0.0001259008],"domain_scores_gemma":[0.9988711,0.0001045087,0.0001264589,0.0003333595,0.0005257875,0.00003882666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003003758,0.001924592,0.8188034,0.0004979799,0.0002235546,0.000001353641,0.0067282,0.0005838876,0.0816817,0.002398252,0.00323892,0.0836178],"study_design_scores_gemma":[0.0001007801,0.0004219588,0.8272495,0.0004319262,0.0002678529,0.0000360776,0.01729002,0.000519945,0.1461239,0.001697708,0.00564687,0.0002134924],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946105,0.0000973089,0.0001192291,0.002103749,0.001211102,0.00160683,0.000008497559,0.00002186675,0.000220946],"genre_scores_gemma":[0.9986766,0.000001320887,0.0005175117,0.0003355496,0.0001754747,0.0001728327,0.00004541738,0.000005667247,0.0000696562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0834043,"threshold_uncertainty_score":0.399477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1593785595597535,"score_gpt":0.4338020316219883,"score_spread":0.2744234720622348,"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."}}