{"id":"W7116406781","doi":"10.2196/82462","title":"Explainable Logistic Regression for Heart Disease Risk Prediction in Community and Clinical Populations: Development and External Validation Study (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; Heart disease; Disease; Risk assessment; Regression analysis; MEDLINE","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.003856093,0.0001175001,0.0002804037,0.0001333854,0.001507384,0.00001832603,0.00008054959,0.0001420121,0.000009159841],"category_scores_gemma":[0.001962134,0.0001075879,0.00003884109,0.0001386885,0.00005986859,0.0001268894,0.0002096959,0.0007398608,0.000009629428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000261216,"about_ca_system_score_gemma":0.0002778995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001874222,"about_ca_topic_score_gemma":0.00161765,"domain_scores_codex":[0.9957946,0.002599817,0.0009063985,0.0003091871,0.0001481092,0.0002418866],"domain_scores_gemma":[0.9977567,0.001383206,0.0001720461,0.0003773058,0.0001786377,0.0001321224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003005111,0.000189026,0.9839076,0.0002748425,0.00001053634,0.00000150633,0.004205116,0.0001035629,0.000001990811,0.0001789838,0.0003452415,0.01048107],"study_design_scores_gemma":[0.0004722488,0.0001088963,0.9775202,0.0006774658,0.00003163558,2.53576e-7,0.01272844,0.002203575,0.000007700695,0.005202264,0.0009693929,0.00007791739],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899969,0.0002164915,0.004057478,0.0002582999,0.0005805357,0.004715371,0.00002697057,0.00006073284,0.00008719374],"genre_scores_gemma":[0.9965,0.00003572028,0.001110281,0.0001147265,0.00009792381,0.001843872,0.00002948117,0.00001027286,0.0002577203],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01040315,"threshold_uncertainty_score":0.9997925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3183562680799437,"score_gpt":0.5600324116557923,"score_spread":0.2416761435758486,"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."}}