{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002783848,0.00005111187,0.000119749,0.00001249389,0.00003290256,0.000003595381,0.0001120001,0.0001072365,0.000008382573],"category_scores_gemma":[0.0005357058,0.00003191048,0.0000467801,0.00004664416,0.0009425838,0.000002056652,0.00003115677,0.0000367945,2.668339e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003138927,"about_ca_system_score_gemma":0.00004278908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005658419,"about_ca_topic_score_gemma":0.00008858189,"domain_scores_codex":[0.9992653,0.00008445743,0.0003669076,0.0001275576,0.00009336128,0.00006249064],"domain_scores_gemma":[0.9993876,0.0001061295,0.000193012,0.0001601985,0.0001389402,0.00001408315],"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":[0.00003509207,0.00004164733,0.06083968,0.00003340469,0.00001552611,7.348597e-9,0.0001268006,1.545871e-7,0.7150862,0.00002091375,0.00002387038,0.2237767],"study_design_scores_gemma":[0.0001727659,0.000906482,0.1525261,0.00001385109,0.00001097865,3.941248e-7,0.0004151401,0.0001696189,0.8453406,0.000179077,0.0002269647,0.00003807827],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810161,0.00007607724,0.01844261,0.00006121023,0.00009824226,0.0000791224,0.000007203507,0.000004615963,0.0002148288],"genre_scores_gemma":[0.9974449,0.00004064122,0.002334484,0.00002814802,0.00005252673,0.00000678053,0.00001381392,0.000002413923,0.00007629152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2237386,"threshold_uncertainty_score":0.3472989,"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."}}