{"id":"W4408563104","doi":"10.63313/hmt.9001","title":"A Meta-Analysis of Machine Learning Techniques for Predicting Disease Progression in Electronic Health Records","year":2025,"lang":"en","type":"article","venue":"Health Medicine and Therapeutics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Health records; Meta-analysis; Electronic health record; Computer science; Data science; Disease; Artificial intelligence; Machine learning; Natural language processing; Medicine; Health care; Political science; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03776831,0.002024967,0.005072548,0.006119355,0.0005112414,0.003517543,0.001611874,0.001626671,0.002421281],"category_scores_gemma":[0.1037005,0.0008514391,0.03354564,0.006565602,0.0006597709,0.002226466,0.00160401,0.00266398,0.0003459766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001638691,"about_ca_system_score_gemma":0.002059109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004244708,"about_ca_topic_score_gemma":0.006896705,"domain_scores_codex":[0.9665772,0.02084111,0.005275973,0.003536656,0.003349481,0.000419717],"domain_scores_gemma":[0.8926879,0.09183212,0.006246662,0.005151467,0.003686972,0.0003948178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.002869623,0.00003673174,0.02243308,0.03957666,0.8983558,0.00008457511,0.00008844153,0.001527107,0.0002417016,0.0005592636,0.001608779,0.03261823],"study_design_scores_gemma":[0.0004849927,0.0003119582,0.01199542,0.00842147,0.9724109,0.0001315313,0.00004602604,0.001184556,0.0003244245,0.001164881,0.003494964,0.00002868074],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.0261265,0.9586188,0.009017868,0.001377457,0.0005638387,0.0002582346,0.002621257,0.000141552,0.001274435],"genre_scores_gemma":[0.6834723,0.2952419,0.01211616,0.002495874,0.000804057,0.0009834339,0.00382939,0.0002153507,0.0008414733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03776831,"threshold_uncertainty_score":0.1997403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09371057968559568,"score_gpt":0.4359558982872003,"score_spread":0.3422453186016047,"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."}}