{"id":"W4390586053","doi":"10.1016/j.jpi.2023.100358","title":"Use of n-grams and K-means clustering to classify data from free text bone marrow reports","year":2024,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence; Security token; Centroid; Bone marrow; Text mining; Natural language processing; Data mining; Pattern recognition (psychology); Pathology; 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":[],"consensus_categories":[],"category_scores_codex":[0.007822753,0.0001274757,0.0004587161,0.0003401658,0.00005529346,0.0003288798,0.0007941165,0.0001150529,0.0001060333],"category_scores_gemma":[0.006537768,0.00008268482,0.00009004189,0.0003126478,0.0001286176,0.001405493,0.0008087105,0.0003347892,0.00002842928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003620294,"about_ca_system_score_gemma":0.0001017886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001107507,"about_ca_topic_score_gemma":0.00005226804,"domain_scores_codex":[0.9955433,0.0001337295,0.002660982,0.000163009,0.001320661,0.0001783116],"domain_scores_gemma":[0.9962146,0.00103356,0.0009892207,0.001246605,0.000370311,0.0001457001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003229299,0.0003816183,0.07952043,0.000460078,0.0004211375,0.005276441,0.03075852,0.01321821,0.01422939,0.000341044,0.5623993,0.2926709],"study_design_scores_gemma":[0.001436397,0.002099441,0.06447209,0.002154908,0.0005208335,0.0107122,0.01655781,0.2347838,0.001225465,0.05797716,0.607197,0.0008628501],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8852209,0.0004902447,0.1089097,0.002893006,0.001784228,0.0001690168,0.0001416199,0.00001147064,0.0003798033],"genre_scores_gemma":[0.7890837,0.0002683422,0.2088666,0.001239964,0.0002501313,0.000001962778,0.00001444396,0.00001393842,0.0002608413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2918081,"threshold_uncertainty_score":0.7826791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2526589685442207,"score_gpt":0.3780998978172646,"score_spread":0.1254409292730438,"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."}}