{"id":"W2592665192","doi":"10.2196/medinform.6730","title":"Patient Similarity in Prediction Models Based on Health Data: A Scoping Review","year":2017,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Context (archaeology); Computer science; Similarity (geometry); Scopus; Data mining; Field (mathematics); Predictive modelling; Data science; Health care; MEDLINE; Information retrieval; Medicine; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004457916,0.0004784173,0.002358283,0.0003477042,0.0002502259,0.0001862491,0.00412427,0.0005273008,0.00002457225],"category_scores_gemma":[0.001719975,0.00037104,0.0001958582,0.0004557556,0.0000746716,0.001112444,0.001554536,0.002649686,0.00005459618],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004306804,"about_ca_system_score_gemma":0.00645061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007160559,"about_ca_topic_score_gemma":0.00005536975,"domain_scores_codex":[0.9927329,0.0008134127,0.003177227,0.0004994926,0.002150242,0.0006266758],"domain_scores_gemma":[0.9921212,0.00059969,0.00229563,0.004284261,0.00008608146,0.0006131561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[4.504936e-7,0.00004282938,7.797163e-7,0.2816795,0.000004146247,0.000007876389,0.0001810768,0.00006651321,2.10614e-12,0.0001565637,0.003135242,0.714725],"study_design_scores_gemma":[0.00007915193,0.00008696493,3.985727e-7,0.3865509,0.00000755594,0.00001203265,0.000001815227,0.3714903,2.980466e-10,0.00002335279,0.2416238,0.000123769],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.706429e-8,0.9468445,0.04468941,0.00218649,0.0005961495,0.004313473,0.0001074114,0.0001926514,0.001069855],"genre_scores_gemma":[6.965565e-7,0.9820161,0.008009848,0.008676205,0.0001062857,0.0004182442,0.0007450293,0.00002349127,0.00000411825],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7146013,"threshold_uncertainty_score":0.9998742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2501120553890433,"score_gpt":0.4906599825597756,"score_spread":0.2405479271707323,"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."}}