{"id":"W4412619321","doi":"10.2196/68830","title":"Autoencoder-Based Representation Learning for Similar Patients Retrieval From Electronic Health Records: Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases","keywords":"Autoencoder; Mahalanobis distance; Artificial intelligence; Hyperparameter; Deep learning; Computer science; Euclidean distance; Pattern recognition (psychology); Feature learning; Feature (linguistics); Machine learning","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":[0.001228492,0.0002124758,0.0004684568,0.0002217625,0.0004107438,0.0001381288,0.0009137409,0.0001475844,0.00003244659],"category_scores_gemma":[0.001138225,0.0001955959,0.00008607897,0.0008006555,0.000051785,0.0004185535,0.0002269706,0.001025349,0.00001983023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003848538,"about_ca_system_score_gemma":0.001568736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001699951,"about_ca_topic_score_gemma":0.0001020307,"domain_scores_codex":[0.9963841,0.000516456,0.001144436,0.0003012994,0.001079307,0.0005743743],"domain_scores_gemma":[0.9971416,0.001207553,0.0005474125,0.0005397114,0.0003092246,0.0002545071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008390972,0.003391263,0.4998353,0.001656065,0.0004304193,0.000007315072,0.1734023,0.02713166,0.000001538275,0.009216855,0.04158304,0.2425051],"study_design_scores_gemma":[0.002263746,0.001481999,0.01846557,0.0001579659,0.000007687597,2.401478e-7,0.002419394,0.968216,0.00001162845,0.0008453576,0.005966658,0.0001637729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2847362,0.00004848998,0.7074455,0.004061228,0.0005408718,0.002354153,0.000007490384,0.000379305,0.0004267322],"genre_scores_gemma":[0.9681368,0.00001055862,0.02706041,0.004179609,0.00007366846,0.0001877848,0.0002200987,0.00001164488,0.0001194467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9410843,"threshold_uncertainty_score":0.797617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03300473588645807,"score_gpt":0.395272443593794,"score_spread":0.362267707707336,"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."}}