{"id":"W4400191026","doi":"10.1016/j.eplepsyres.2024.107404","title":"Predicting efficacy of antiseizure medication treatment with machine learning algorithms in North Indian population","year":2024,"lang":"en","type":"article","venue":"Epilepsy Research","topic":"Epilepsy research and treatment","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Innovation Cluster (Canada)","funders":"Council of Scientific and Industrial Research, India; Indian Council of Medical Research; University of Delhi; Human Resource Development Centre, Council of Scientific And Industrial Research","keywords":"Epilepsy; Algorithm; Population; Machine learning; Artificial intelligence; Computer science; Medicine; Psychiatry","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":[0.001132135,0.0001877208,0.0003726707,0.001045199,0.0001486255,0.00004813726,0.0001087582,0.0001082435,0.0001403081],"category_scores_gemma":[0.0003017133,0.0001280291,0.00008040167,0.001701043,0.0001528071,0.0001382378,0.00005248045,0.00084933,0.00005933846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005508117,"about_ca_system_score_gemma":0.0004254874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0047479,"about_ca_topic_score_gemma":0.003441082,"domain_scores_codex":[0.9968203,0.0003624275,0.0003974405,0.0005158546,0.001291301,0.0006126319],"domain_scores_gemma":[0.9985304,0.0006052693,0.00005105146,0.0003422507,0.000170495,0.0003004726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004540943,0.0005118907,0.8439314,0.0002204335,0.0001581307,0.0008777846,0.001376859,0.00004931521,0.0001550224,0.00003866033,0.00002420806,0.1522022],"study_design_scores_gemma":[0.002945698,0.00485616,0.9769352,0.0007363227,0.00004261328,0.00009271313,0.0002954416,0.01226832,0.0008674904,0.00002476437,0.0008402006,0.00009508097],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945753,0.002019205,0.00003141043,0.0009860954,0.00004808373,0.001209844,0.0000292051,0.00009562301,0.00100523],"genre_scores_gemma":[0.9960261,0.001529482,0.0004787308,0.000004872331,0.0001893961,0.0001559955,0.000773185,0.00004631143,0.0007959016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1521071,"threshold_uncertainty_score":0.7177436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04621778385860568,"score_gpt":0.3771196750531627,"score_spread":0.330901891194557,"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."}}