{"id":"W3199944795","doi":"10.2196/30223","title":"Automatic Classification of Thyroid Findings Using Static and Contextualized Ensemble Natural Language Processing Systems: Development Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Yonsei University; National Research Foundation","keywords":"Computer science; Artificial intelligence; Machine learning; Natural language processing; Convolutional neural network","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":[0.001147594,0.0004811832,0.0003222444,0.0005768833,0.0001743314,0.000391814,0.0005994713,0.0004078666,0.001009358],"category_scores_gemma":[0.002393117,0.0001813764,0.0004632249,0.0003995704,0.0001591526,0.0008977593,0.0004112865,0.0004027888,0.0003636714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006039343,"about_ca_system_score_gemma":0.0008294387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006524845,"about_ca_topic_score_gemma":0.007528021,"domain_scores_codex":[0.9995566,0.00009434629,0.00003067404,0.0001853578,0.00008980308,0.00004316297],"domain_scores_gemma":[0.9988105,0.000427609,0.00007799504,0.0001282701,0.000506658,0.00004895774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004536547,0.0008130428,0.03771484,0.0001991269,0.0002183962,0.0006377232,0.0003308012,0.1312353,0.05576856,0.0008169683,0.003696358,0.7681152],"study_design_scores_gemma":[0.00001288196,0.0003553763,0.01039857,0.00001259585,0.00007316252,0.0001682354,0.00008771066,0.9678661,0.01964943,0.0002964866,0.001059999,0.00001945628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8378832,0.000528761,0.1555308,0.0001952412,0.00006556392,0.0002323215,0.000860855,0.002921764,0.001781547],"genre_scores_gemma":[0.8744584,0.0002209178,0.1215494,0.00007255372,0.0000228925,0.0001430442,0.00192881,0.00005372871,0.001550232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006524845,"threshold_uncertainty_score":0.01297373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02984785814862104,"score_gpt":0.351851651865812,"score_spread":0.322003793717191,"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."}}