{"id":"W4403619348","doi":"10.1007/978-3-031-72390-2_21","title":"MEDBind: Unifying Language and Multimodal Medical Data Embeddings","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto General Hospital; University of Toronto; Vector Institute; Ted Rogers Centre for Heart Research; University Health Network","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Programming language","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":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.002406435,0.000549651,0.0005572915,0.0008363501,0.0002609173,0.0008539669,0.007261073,0.0005259435,0.00006415554],"category_scores_gemma":[0.0004882665,0.0004802739,0.00006046049,0.0005574084,0.0007501491,0.0006946081,0.009581285,0.002529285,0.0000612345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001949309,"about_ca_system_score_gemma":0.0008933921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002884439,"about_ca_topic_score_gemma":0.000354599,"domain_scores_codex":[0.9941035,0.00005870019,0.0005716869,0.002609212,0.00189898,0.0007579362],"domain_scores_gemma":[0.9955996,0.0009930886,0.0001922759,0.002662418,0.0001116831,0.0004409191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002689144,0.0000106715,0.0001411792,0.0002860321,0.00001474343,0.0009664941,0.00353576,0.00182063,0.00001413384,0.03560695,0.00004483041,0.9575559],"study_design_scores_gemma":[0.000156942,0.00006996683,0.00006467827,0.001050084,0.000008248041,0.0003683621,8.62624e-7,0.9697693,0.00003550399,0.02514225,0.002814029,0.0005197551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000229489,0.003098432,0.9844239,0.006025455,0.002247623,0.0003116397,0.00001902058,0.0004117645,0.003232712],"genre_scores_gemma":[0.2880727,0.000278246,0.7019365,0.005569395,0.002217169,0.00001251835,0.00007657087,0.0001559275,0.001681029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9679487,"threshold_uncertainty_score":0.9997719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02359772266688148,"score_gpt":0.3255727558199283,"score_spread":0.3019750331530469,"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."}}