{"id":"W4392619616","doi":"10.1145/3651159","title":"DeepMedFeature: An Accurate Feature Extraction and Drug-Drug Interaction Model for Clinical Text in Medical Informatics","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Informatics; Drug; Convolution (computer science); Feature extraction; F1 score; Feature vector; Mechanism (biology); Machine learning; Natural language processing; Artificial neural network; Medicine; Pharmacology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005973593,0.000849875,0.0006874566,0.001076627,0.0002152934,0.0005590567,0.0009733175,0.001044154,0.002991035],"category_scores_gemma":[0.001635854,0.0002682781,0.0009739176,0.0009982787,0.000197853,0.001379414,0.0007677681,0.001370454,0.001826743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007183132,"about_ca_system_score_gemma":0.001115649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005755677,"about_ca_topic_score_gemma":0.008267957,"domain_scores_codex":[0.9997441,0.00004826457,0.00003442006,0.0000758722,0.00006101208,0.00003629728],"domain_scores_gemma":[0.9996976,0.00015195,0.00003285388,0.00003402032,0.00006603477,0.00001761265],"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":[0.0006162754,0.000411297,0.005164915,0.0004547529,0.0001815867,0.0005149601,0.0001424386,0.07662385,0.01883201,0.003505772,0.03228579,0.8612664],"study_design_scores_gemma":[0.00003532296,0.0001586986,0.001693585,0.00003294793,0.00004861138,0.0002433689,0.00002456308,0.9772406,0.006140076,0.005538915,0.008823728,0.00001962235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07792418,0.004488471,0.879293,0.002240917,0.0004914761,0.0003781079,0.01363435,0.01879807,0.002751409],"genre_scores_gemma":[0.5586414,0.002755704,0.4016631,0.001118268,0.0002999721,0.0006881921,0.02363595,0.0003862537,0.01081115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005755677,"threshold_uncertainty_score":0.01144433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01635232293385361,"score_gpt":0.3468787532546184,"score_spread":0.3305264303207648,"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."}}