{"id":"W4224921946","doi":"10.2196/35475","title":"Using Natural Language Processing and Machine Learning to Preoperatively Predict Lymph Node Metastasis for Non–Small Cell Lung Cancer With Electronic Medical Records: Development and Validation Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China","keywords":"Receiver operating characteristic; Artificial intelligence; Machine learning; Concordance; Random forest; Computer science; Medicine; Information extraction; Lung cancer; Lymph node; Standardized uptake value; Natural language processing; Text mining; Radiology; Computed tomography; Pathology; Internal medicine","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":[0.01126463,0.001074624,0.0005085541,0.00237772,0.0003996358,0.0007828011,0.00124517,0.001110824,0.0007767954],"category_scores_gemma":[0.02147347,0.0003591014,0.001453989,0.001274253,0.0004965831,0.001670103,0.0009981028,0.0007703739,0.0005311298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009714377,"about_ca_system_score_gemma":0.001517007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007092861,"about_ca_topic_score_gemma":0.005898929,"domain_scores_codex":[0.9946472,0.002839092,0.0005662757,0.0008222908,0.0009231656,0.0002018582],"domain_scores_gemma":[0.9791113,0.0149625,0.001053765,0.001538023,0.003108798,0.0002257239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001622128,0.008671653,0.4711809,0.001200838,0.001423741,0.001212497,0.0009633127,0.06870028,0.008245373,0.0008209914,0.003885869,0.4320724],"study_design_scores_gemma":[0.0003506517,0.003783393,0.2252042,0.0002913047,0.0008934272,0.001065334,0.0007118693,0.745188,0.01718998,0.0008388502,0.004377668,0.0001053319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9690169,0.0009484396,0.025178,0.0002258986,0.00005713465,0.00116247,0.00177391,0.0005279918,0.001109146],"genre_scores_gemma":[0.9352903,0.0005442536,0.05494546,0.0001117069,0.00004347272,0.0008305255,0.007590075,0.00002682459,0.0006173071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01126463,"threshold_uncertainty_score":0.05957383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0173266373551024,"score_gpt":0.3225897557349218,"score_spread":0.3052631183798193,"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."}}