{"id":"W4221110957","doi":"10.1016/j.artmed.2022.102284","title":"Word-level text highlighting of medical texts for telehealth services","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Mitacs","keywords":"Computer science; Word2vec; Workload; Context (archaeology); Telehealth; Word (group theory); tf–idf; Domain (mathematical analysis); Digitization; Quality (philosophy); Artificial intelligence; Data science; Information retrieval; Health care; Telemedicine; Term (time)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001859689,0.0001393639,0.0003074834,0.0001312758,0.0001378378,0.000004698484,0.0005923299,0.0001554618,0.0004044508],"category_scores_gemma":[0.0007845248,0.0001164985,0.00005823882,0.0003308415,0.0003470381,0.000002374363,0.000235265,0.0002357598,0.000003344713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002354633,"about_ca_system_score_gemma":0.0001473246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004410285,"about_ca_topic_score_gemma":0.0005411207,"domain_scores_codex":[0.9979097,0.0001109715,0.0006808717,0.0003695622,0.0005865933,0.0003422627],"domain_scores_gemma":[0.9991686,0.0002124645,0.0001732725,0.0002529163,0.00007196105,0.0001208153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004439959,0.0003229001,0.001774195,0.0002259714,0.00004040555,0.00001933329,0.001792336,0.0001755665,0.03575636,0.005775039,0.002640691,0.9510332],"study_design_scores_gemma":[0.001814653,0.01074225,0.005293879,0.001179353,0.0001015332,0.0001786734,0.0652176,0.02967057,0.2874036,0.04581065,0.5510467,0.001540484],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9314905,0.003980207,0.03815173,0.02370209,0.001405317,0.0005816591,0.00005491111,0.00004189666,0.0005916895],"genre_scores_gemma":[0.9959913,0.0002336239,0.001964367,0.001050851,0.000464662,0.00008911401,0.00007533405,0.0000159608,0.0001147867],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9494927,"threshold_uncertainty_score":0.475067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0774513499730896,"score_gpt":0.3770074536796968,"score_spread":0.2995561037066072,"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."}}