{"id":"W2188411887","doi":"10.18433/j33031","title":"Application of Counter-propagation Artificial Neural Networks in Prediction of Topiramate Concentration in Patients with Epilepsy","year":2015,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Analytical Methods in Pharmaceuticals","field":"Chemistry","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja","keywords":"Topiramate; Confidence interval; Artificial neural network; Carbamazepine; Epilepsy; Approximation error; Regimen; Dosing; Medicine; Statistics; Pharmacology; Mathematics; Machine learning; Computer science; Internal medicine; Psychiatry","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":[0.002266122,0.0001615728,0.0003972133,0.0001506755,0.00003318265,0.00002675079,0.0003554322,0.00006962649,0.0001134774],"category_scores_gemma":[0.0003409761,0.0001250721,0.00007086965,0.0007554298,0.0005853909,0.0006099335,0.00004613181,0.0004833833,8.326101e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001806791,"about_ca_system_score_gemma":0.0001455645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002252497,"about_ca_topic_score_gemma":0.000002888198,"domain_scores_codex":[0.9968666,0.0002276973,0.001346829,0.0002361226,0.0009996336,0.0003230866],"domain_scores_gemma":[0.998126,0.0003156621,0.0007472383,0.0001014266,0.000474365,0.0002353452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001547296,0.00067242,0.8824571,0.00008729594,0.00002295654,0.000004752283,0.0001698997,0.02751384,0.02522996,0.0005112002,0.00001299887,0.0617703],"study_design_scores_gemma":[0.0040892,0.0002483311,0.0182369,0.0001085378,0.00009806228,0.000006813348,0.0001358613,0.8728011,0.1032558,0.0005466603,0.0003380454,0.0001346034],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837496,0.0002035393,0.01485148,0.0002798982,0.0002308326,0.0002117944,0.00001230334,0.000009093906,0.0004515199],"genre_scores_gemma":[0.9984481,0.00004511872,0.001235515,0.00008380952,0.0001660479,0.000006267105,0.000004358408,0.000009028111,0.00000179742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8642202,"threshold_uncertainty_score":0.510029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08676086480422043,"score_gpt":0.3989268546987016,"score_spread":0.3121659898944812,"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."}}