{"id":"W2984884209","doi":"10.1093/geroni/igz038.060","title":"WHAT’S OLD IS NEW: USING ARTIFICIAL INTELLIGENCE TO ACCELERATE DISCOVERY OF NEW TREATMENTS","year":2019,"lang":"en","type":"article","venue":"Innovation in Aging","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Toronto Western Hospital; Institute for Clinical Evaluative Sciences; University Health Network","funders":"","keywords":"Medicine; Disease; Comorbidity; Logistic regression; Parkinson's disease; Drug repositioning; Watson; MEDLINE; Repurposing; Drug; Psychiatry; Internal medicine; Artificial intelligence; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01480207,0.0005210362,0.0009758492,0.006258923,0.0003450923,0.004193724,0.0007376552,0.0007768146,0.002990563],"category_scores_gemma":[0.0486774,0.000319512,0.00086806,0.003430822,0.001452586,0.003740682,0.001534168,0.001436383,0.0004406309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001293569,"about_ca_system_score_gemma":0.002256347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002784426,"about_ca_topic_score_gemma":0.003614921,"domain_scores_codex":[0.9941109,0.004294306,0.0003308811,0.0002838582,0.000861683,0.0001183895],"domain_scores_gemma":[0.9517038,0.04112563,0.002940909,0.00187751,0.001608256,0.0007437674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007606825,0.0005277658,0.08222265,0.003698671,0.001522576,0.0006665331,0.0007080624,0.03166752,0.002085162,0.06702499,0.020766,0.7883494],"study_design_scores_gemma":[0.0005614724,0.00106426,0.0719429,0.003687868,0.001024709,0.0009092705,0.001389746,0.2236221,0.003240124,0.6080039,0.08427151,0.0002821377],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"commentary","genre_scores_codex":[0.3066542,0.2397093,0.2240329,0.1605313,0.001906572,0.0009634682,0.002746231,0.002056465,0.0613995],"genre_scores_gemma":[0.7253196,0.06697261,0.1995091,0.003779182,0.001344673,0.0002726783,0.0008049653,0.00008739649,0.001909757],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.01480207,"threshold_uncertainty_score":0.07828176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5263246246292027,"score_gpt":0.472706293356254,"score_spread":0.05361833127294868,"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."}}