{"id":"W4395680939","doi":"10.2196/55798","title":"Using the Natural Language Processing System Medical Named Entity Recognition-Japanese to Analyze Pharmaceutical Care Records: Natural Language Processing Analysis","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Natural language processing; Computer science; Natural (archaeology); Named-entity recognition; Natural language; Artificial intelligence; Information retrieval; Engineering; History","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004312871,0.0006945149,0.0005461629,0.003724443,0.0005360006,0.00140815,0.000486133,0.0005315823,0.0008901826],"category_scores_gemma":[0.008669185,0.0002009087,0.0008722736,0.002717326,0.0003844679,0.00201617,0.0007376918,0.0004341758,0.0005084492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006698536,"about_ca_system_score_gemma":0.001213566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004496224,"about_ca_topic_score_gemma":0.004179181,"domain_scores_codex":[0.9970649,0.0009042566,0.0007001868,0.0006659712,0.0005773994,0.00008720771],"domain_scores_gemma":[0.9946486,0.002891135,0.0007355992,0.0003713865,0.001264354,0.00008895231],"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":[0.0006000077,0.0004736124,0.1340447,0.0022102,0.0005352502,0.002318637,0.003102803,0.01249561,0.09125559,0.002762368,0.00693629,0.743265],"study_design_scores_gemma":[0.0001954156,0.001045477,0.3129288,0.000376301,0.001612764,0.004944474,0.003360311,0.4491112,0.1760049,0.008813586,0.04114443,0.0004623102],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4990186,0.003401023,0.4799186,0.001649369,0.0001601729,0.001359714,0.006475429,0.003323806,0.004693152],"genre_scores_gemma":[0.5374439,0.001422977,0.4514928,0.000318137,0.0001211542,0.0005010839,0.006939397,0.00007471487,0.001685931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004496224,"threshold_uncertainty_score":0.02280891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0672794325507549,"score_gpt":0.4564147664782774,"score_spread":0.3891353339275225,"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."}}