{"id":"W3152927204","doi":"10.2196/27172","title":"Anomaly Detection Algorithm for Real-World Data and Evidence in Clinical Research: Implementation, Evaluation, and Validation Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Data mining; Anomaly detection; Data quality; Cluster analysis; Data set; Algorithm; Audit; Process (computing); Machine learning; Artificial intelligence; Metric (unit)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02035493,0.0008138321,0.001102686,0.002482196,0.0005329674,0.00166768,0.001905786,0.002032793,0.001350193],"category_scores_gemma":[0.05926556,0.0003950084,0.0008712748,0.001831419,0.0007045446,0.001682895,0.001225975,0.00128268,0.0003943831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001529757,"about_ca_system_score_gemma":0.002769651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003576209,"about_ca_topic_score_gemma":0.001986809,"domain_scores_codex":[0.9869265,0.006401724,0.001508805,0.001403574,0.003383785,0.0003756724],"domain_scores_gemma":[0.9537312,0.03184516,0.001709735,0.002585007,0.00951464,0.0006142064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002397023,0.002711972,0.09080148,0.0009209272,0.0008882654,0.0004722471,0.0005799384,0.2115763,0.01222573,0.004065337,0.003359675,0.670001],"study_design_scores_gemma":[0.0001984376,0.000836116,0.006199326,0.00006596888,0.0001260402,0.0002585189,0.0001098182,0.9811056,0.008867502,0.001040746,0.001163782,0.00002805622],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2949262,0.0008011711,0.6965279,0.0004749182,0.0001189219,0.001662058,0.0003613358,0.004089353,0.001038193],"genre_scores_gemma":[0.4608264,0.0001757135,0.5373749,0.00007499796,0.00001613566,0.0007755585,0.0003828658,0.00005725423,0.0003162191],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02035493,"threshold_uncertainty_score":0.1076485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3370115842758494,"score_gpt":0.5574363388989187,"score_spread":0.2204247546230693,"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."}}