{"id":"W7117468468","doi":"10.3390/bioengineering13010030","title":"Accurate Clinical Entity Recognition and Code Mapping of Anatomopathological Reports Using BioClinicalBERT Enhanced by Retrieval-Augmented Generation: A Hybrid Deep Learning Approach","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Deep learning; Pipeline (software); Coding (social sciences); Code (set theory); Pattern recognition (psychology)","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":[0.0007723292,0.0001536497,0.0002917839,0.00006769075,0.0000763042,0.00002447286,0.00008267359,0.0002546055,0.000004086195],"category_scores_gemma":[0.001335879,0.0001455339,0.0000920046,0.0001758923,0.0001684981,0.000005958074,0.0001377273,0.0002065084,4.201164e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001373262,"about_ca_system_score_gemma":0.00003316409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004556389,"about_ca_topic_score_gemma":0.000001010848,"domain_scores_codex":[0.9984674,0.0001135187,0.0006353277,0.0004788914,0.0001024706,0.0002023806],"domain_scores_gemma":[0.9994082,0.00005002182,0.0001925088,0.0001933613,0.00008397168,0.00007190819],"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":[0.00006297506,0.00010137,0.004001241,0.00009361475,0.0001027878,0.000009703121,0.00001955993,0.0003052435,0.9715633,0.000002538076,0.0002204269,0.02351728],"study_design_scores_gemma":[0.001735,0.000653896,0.004722398,0.0002740055,0.0001481029,0.0001472047,0.0001895829,0.1594152,0.8218371,0.00006469157,0.01006034,0.0007524881],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.686969,0.001368011,0.3112345,0.00002491818,0.0002106806,0.00009335488,0.000009767757,0.00003081901,0.00005892293],"genre_scores_gemma":[0.9822611,0.0006430401,0.01659572,0.00005449898,0.0001195433,0.000006593693,0.0002396436,0.00001088628,0.00006903402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.295292,"threshold_uncertainty_score":0.59347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06099622682867463,"score_gpt":0.3221194033208158,"score_spread":0.2611231764921412,"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."}}