{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009347138,0.0001400732,0.0003276971,0.0001183887,0.0001495145,0.0001686828,0.0003555397,0.00008545207,0.00001050234],"category_scores_gemma":[0.0005615141,0.0001168394,0.00002043293,0.0003998381,0.00005476369,0.0004378509,0.0002529505,0.0003273005,0.000004671571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009640458,"about_ca_system_score_gemma":0.0007782581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002619276,"about_ca_topic_score_gemma":0.00001320539,"domain_scores_codex":[0.9973727,0.0001915946,0.001071784,0.0001443537,0.0009784125,0.0002410807],"domain_scores_gemma":[0.9986876,0.0002360248,0.0004002969,0.0002921349,0.0002229387,0.0001610141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000110359,0.0003951931,0.0126455,0.009358538,0.00008839199,0.00008904126,0.5615979,0.00007787254,0.0007674554,0.001919638,0.0001521964,0.4128973],"study_design_scores_gemma":[0.0006442794,0.00005498876,0.006819675,0.0007167366,0.000007119697,0.00009026424,0.03126905,0.960089,0.0001100447,0.000007825925,0.00006251473,0.0001285461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9437376,0.0005248936,0.05481885,0.0001348165,0.0001155933,0.0004619516,6.904341e-7,0.0001158988,0.00008976206],"genre_scores_gemma":[0.9519547,0.000002593725,0.0477773,0.0001739518,0.00001445253,0.00003172896,0.000008304564,0.00000759113,0.00002939233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9600111,"threshold_uncertainty_score":0.4764574,"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."}}