{"id":"W2892221324","doi":"10.1038/nbt.4233","title":"Deep learning in biomedicine","year":2018,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":604,"is_retracted":false,"has_abstract":false,"ca_institutions":"MaRS","funders":"","keywords":"Biomedicine; Flexibility (engineering); Deep learning; Computer science; Artificial intelligence; Data science; Risk analysis (engineering); Machine learning; Bioinformatics; Biology; Medicine","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00019792,0.0001269656,0.0001546417,0.0003325961,0.00004212908,0.000006341354,0.0002907949,0.001409273,0.0000433424],"category_scores_gemma":[0.0003507631,0.0001171709,0.00004806459,0.000493955,0.0003380337,0.000002033148,0.0001860843,0.0006392152,0.00002878173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000195966,"about_ca_system_score_gemma":0.00001832986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001716227,"about_ca_topic_score_gemma":0.0002589436,"domain_scores_codex":[0.9990675,0.00003354703,0.0001631827,0.0004060071,0.0000791473,0.0002505987],"domain_scores_gemma":[0.9994154,0.000006523554,0.00006010423,0.0004208857,0.0000688501,0.00002824455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002395504,0.00002838706,0.002166972,0.000003105177,0.00001919408,0.00001214922,0.000009772062,5.237609e-7,0.9594046,0.0002249192,0.002619067,0.03548733],"study_design_scores_gemma":[0.0001979608,0.0003403103,0.0008174024,0.000006185999,0.000006967278,0.00002105767,0.00002952238,0.0001244253,0.7163528,0.0001420186,0.2818547,0.0001066107],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9644156,0.007037288,0.01377618,0.004230866,0.0001549699,0.0002631441,7.297525e-7,0.0004128563,0.009708337],"genre_scores_gemma":[0.9952934,0.0004664456,0.002745883,0.0006537574,0.0002596825,0.000008735237,0.00004414394,0.00001806248,0.0005098739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2792357,"threshold_uncertainty_score":0.9998871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002510414399498334,"score_gpt":0.2589834060732092,"score_spread":0.2564729916737108,"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."}}