{"id":"W3208976791","doi":"10.3390/biomedicines9111558","title":"Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach","year":2021,"lang":"en","type":"article","venue":"Biomedicines","topic":"Bipolar Disorder and Treatment","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Ministry of Science and Technology, Taiwan","keywords":"Lithium (medication); Machine learning; Artificial intelligence; Predictive modelling; Clinical Practice; Cross-validation; Binary classification; Computer science; Support vector machine; Internal medicine; Medicine; Physical therapy","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000127768,0.0002065826,0.0004608824,0.0001599002,0.00008173638,0.000007777009,0.00006082094,0.0001105583,0.0002769942],"category_scores_gemma":[0.0001901037,0.0001511052,0.0001142024,0.0005995443,0.00009908684,0.00005399619,0.000060323,0.0001782872,0.000008321796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003910219,"about_ca_system_score_gemma":0.00008556098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001844449,"about_ca_topic_score_gemma":0.00002100739,"domain_scores_codex":[0.9985875,0.00007613246,0.0003791981,0.0003268713,0.000370135,0.0002601148],"domain_scores_gemma":[0.999095,0.00005178119,0.0001003616,0.0002752583,0.000327132,0.0001505086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006832788,0.0008838835,0.9701381,0.0003680455,0.0002815663,0.00001632529,0.0007475402,0.000001507469,0.006161075,0.00001471314,0.00004122565,0.02127768],"study_design_scores_gemma":[0.006572851,0.0007697673,0.9762359,0.0002860677,0.0004423898,0.0000637105,0.0006368376,0.001607136,0.009844604,0.00001146335,0.003379193,0.0001500614],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9817298,0.009440728,0.0001676043,0.0005929245,0.0001575061,0.000396766,0.0001666712,0.000144714,0.007203272],"genre_scores_gemma":[0.9964738,0.0001635141,0.001113235,0.0000944672,0.0001174056,0.00001565636,0.0005154678,0.00003291994,0.001473554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02112762,"threshold_uncertainty_score":0.6161892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02343934013814618,"score_gpt":0.2531398819017066,"score_spread":0.2297005417635604,"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."}}