{"id":"W4401854925","doi":"10.1101/2024.08.23.24312060","title":"Health Data Nexus: An Open Data Platform for AI Research and Education in Medicine","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Centre for Addiction and Mental Health; Toronto Public Health; University of Toronto","funders":"","keywords":"Nexus (standard); Data science; Open data; Health data; Computer science; Political science; World Wide Web; Health care","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.01168144,0.0005266452,0.0006031828,0.002207106,0.001317257,0.005343974,0.002611034,0.001908379,0.03650971],"category_scores_gemma":[0.02929103,0.000620847,0.0007454903,0.001971389,0.001892184,0.006962292,0.01327747,0.003018767,0.01671346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00152679,"about_ca_system_score_gemma":0.005722745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001757917,"about_ca_topic_score_gemma":0.00188802,"domain_scores_codex":[0.9945552,0.002195401,0.0005792404,0.0007374792,0.001582009,0.0003505735],"domain_scores_gemma":[0.9810837,0.007365737,0.0009342892,0.005233692,0.001600356,0.003782259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001627001,0.0004173036,0.006009654,0.001170022,0.0001089239,0.0008520766,0.00344698,0.005057984,0.007022194,0.3251669,0.3596304,0.2894906],"study_design_scores_gemma":[0.0002160518,0.0001059401,0.001983986,0.0003673051,0.00001540595,0.0003117588,0.0003500523,0.008583746,0.003466525,0.1003632,0.8841604,0.00007563878],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01724484,0.002970463,0.5959361,0.05182701,0.003341405,0.00320643,0.04879412,0.1307633,0.1459163],"genre_scores_gemma":[0.1671495,0.003164562,0.6681185,0.01111894,0.002189426,0.004025467,0.06555115,0.01726034,0.06142206],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.997389,"threshold_uncertainty_score":0.1221372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8339818708179229,"score_gpt":0.7162761550054962,"score_spread":0.1177057158124266,"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."}}