{"id":"W2911525976","doi":"10.1109/bibm.2018.8621195","title":"Boundary Detection by Determining the Difference of Classification Probabilities of Sequences: Topic Segmentation of Clinical Notes","year":2018,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Support vector machine; Artificial intelligence; Segmentation; Naive Bayes classifier; Computer science; Boundary (topology); Machine learning; Bayes' theorem; Sequence (biology); Natural language processing; Pattern recognition (psychology); Mathematics; Bayesian probability","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":[0.004412015,0.0009717853,0.001411088,0.004051543,0.0007890483,0.001624496,0.001004004,0.00176654,0.001133836],"category_scores_gemma":[0.01391167,0.0003625915,0.001141661,0.002010641,0.0007478292,0.002469123,0.00121478,0.00154736,0.001120653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006759089,"about_ca_system_score_gemma":0.001199682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003271654,"about_ca_topic_score_gemma":0.002239178,"domain_scores_codex":[0.9966928,0.0009734111,0.0003075319,0.001014315,0.0006896882,0.0003222325],"domain_scores_gemma":[0.9912173,0.00551978,0.0008291436,0.0005742151,0.001469473,0.0003901162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002385297,0.0006479134,0.06000417,0.000390072,0.0002699437,0.0003647682,0.001378253,0.03740149,0.06108684,0.00332717,0.008132651,0.8246115],"study_design_scores_gemma":[0.0001417858,0.0007639105,0.04312887,0.00007965955,0.0001486321,0.0006719131,0.000707589,0.9010442,0.03774184,0.009837327,0.005622663,0.0001115054],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3376032,0.001612419,0.6530069,0.0006342218,0.0002362246,0.0004510751,0.0007677138,0.00317872,0.002509541],"genre_scores_gemma":[0.734486,0.0003103073,0.259782,0.0002017937,0.0002286168,0.0002740143,0.002776875,0.0002236057,0.001716799],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004412015,"threshold_uncertainty_score":0.02333319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07109220662878026,"score_gpt":0.3652287898102724,"score_spread":0.2941365831814922,"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."}}