{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009584437,0.00008567145,0.0001660452,0.0002160509,0.0002202975,0.0002247192,0.0004668335,0.00006781481,0.00001477656],"category_scores_gemma":[0.0007030754,0.00008228136,0.00001758851,0.0009910918,0.0001223188,0.001172041,0.0006837694,0.0002681803,0.00000304032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006438257,"about_ca_system_score_gemma":0.0003623069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001299403,"about_ca_topic_score_gemma":0.001660791,"domain_scores_codex":[0.9973476,0.0003592537,0.0009242704,0.0003141053,0.0008588956,0.0001959087],"domain_scores_gemma":[0.997586,0.0008012615,0.0001979533,0.0006933807,0.0005685433,0.0001528515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002897839,0.0001016522,0.01016339,0.00002489455,0.000008413553,9.705163e-7,0.001013534,3.845427e-7,0.000004791066,0.0006099204,0.0004714905,0.9875976],"study_design_scores_gemma":[0.001112628,0.0004257341,0.1279363,0.00007117315,0.00001952456,0.00001840516,0.004580598,0.8594438,0.000521271,0.002675997,0.003036977,0.0001575653],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3042464,0.00004991227,0.6929526,0.0009050552,0.00006687742,0.001635085,0.000007914817,0.00007301389,0.00006310212],"genre_scores_gemma":[0.8965359,0.0004248638,0.1018058,0.000213895,0.0001040692,0.0008304541,0.00004657129,0.000006949523,0.00003143011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9874401,"threshold_uncertainty_score":0.3355336,"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."}}