{"id":"W2750756186","doi":"10.1093/brain/awx185","title":"Towards personalized therapy for multiple sclerosis: prediction of individual treatment response","year":2017,"lang":"en","type":"article","venue":"Brain","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":149,"is_retracted":false,"has_abstract":true,"ca_institutions":"Jewish General Hospital; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Université de Montréal; Hôpital Notre-Dame","funders":"National Health and Medical Research Council; Sanofi Genzyme; Novartis Pharma; EMD Serono; H. Lundbeck A/S; Multiple Sclerosis Society; Multiple Sclerosis Society of Canada; Canadian Institutes of Health Research; Teva Pharmaceutical Industries; Fondazione Italiana Sclerosi Multipla; Medical Research Council; Biogen; Sanofi","keywords":"Natalizumab; Fingolimod; Medicine; Cohort; Discontinuation; Disease; Multiple sclerosis; External validity; Proportional hazards model; Cohort study; Physical therapy; Clinical trial; Internal medicine; Oncology; Psychology; Psychiatry","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009252574,0.0008213178,0.001500625,0.001750742,0.0002847798,0.001777901,0.0007752979,0.0009997588,0.0007966905],"category_scores_gemma":[0.01884259,0.0003413525,0.001075293,0.001207775,0.0005227814,0.001088149,0.00108517,0.001995705,0.0004659927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007660452,"about_ca_system_score_gemma":0.00113497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002668485,"about_ca_topic_score_gemma":0.002369344,"domain_scores_codex":[0.9956896,0.003032031,0.0002189772,0.0004361114,0.000502389,0.0001209094],"domain_scores_gemma":[0.9903724,0.006614141,0.001406912,0.0007310285,0.0006682116,0.0002072288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001013443,0.0004852102,0.3618865,0.000572489,0.001220571,0.0001511773,0.0004310405,0.1144574,0.003050664,0.003597441,0.007346223,0.5057878],"study_design_scores_gemma":[0.000214951,0.0014176,0.1926662,0.0005783167,0.001131229,0.0005824569,0.0004222329,0.7412967,0.004446261,0.04567559,0.01136971,0.0001986802],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4476547,0.01653189,0.5132958,0.01123881,0.000290313,0.0006970573,0.003342648,0.002667742,0.004280937],"genre_scores_gemma":[0.8578091,0.00297767,0.1351131,0.001129467,0.0002780009,0.0002833226,0.001737837,0.0001045257,0.0005669536],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009252574,"threshold_uncertainty_score":0.04893291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2307511624584449,"score_gpt":0.3812508765157432,"score_spread":0.1504997140572983,"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."}}