{"id":"W2618245351","doi":"10.1101/142760","title":"Opportunities and obstacles for deep learning in biology and medicine","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":309,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation; Howard Hughes Medical Institute; National Institutes of Health; National Science Foundation","keywords":"Deep learning; Interpretability; Artificial intelligence; Variety (cybernetics); Computer science; Data science; Machine learning","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":[0.02723607,0.001069674,0.001336694,0.001886525,0.001538376,0.006400224,0.003410465,0.006810124,0.008655103],"category_scores_gemma":[0.03339484,0.0007978426,0.000850853,0.001607257,0.01327439,0.01705576,0.008885466,0.01294528,0.002963822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004031714,"about_ca_system_score_gemma":0.00485771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004158099,"about_ca_topic_score_gemma":0.002500325,"domain_scores_codex":[0.9937249,0.003719503,0.000235913,0.0006325583,0.001093939,0.0005931886],"domain_scores_gemma":[0.9587339,0.03039072,0.0008835356,0.00256597,0.004177957,0.003247844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003846469,0.0002382661,0.002655359,0.001139223,0.0001175441,0.0001877776,0.0005950771,0.02545723,0.001030953,0.6994018,0.076297,0.1924952],"study_design_scores_gemma":[0.00004005744,0.00004864233,0.0004553869,0.0004928271,0.00001094103,0.00006417629,0.0003682875,0.02642391,0.0004926915,0.9243115,0.04725505,0.000036659],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"review","genre_scores_codex":[0.01224712,0.06241424,0.1224816,0.7822084,0.002749139,0.00006695069,0.0005388096,0.0006632697,0.01663052],"genre_scores_gemma":[0.6248047,0.07730903,0.1818498,0.08955359,0.01133338,0.0006385921,0.001160119,0.000387543,0.01296305],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.02723607,"threshold_uncertainty_score":0.1440399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0496381747885837,"score_gpt":0.311126466346927,"score_spread":0.2614882915583433,"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."}}