{"id":"W3029499780","doi":"10.2196/20826","title":"Natural Language Processing for Surveillance of Cervical and Anal Cancer and Precancer: Algorithm Development and Split-Validation Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Cervical Cancer and HPV Research","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Algorithm; Medical diagnosis; Computer science; Cervical cancer; Medicine; Artificial intelligence; Natural language processing; Machine learning; Cancer; 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":[0.04763125,0.001594236,0.001178341,0.002167973,0.0009509795,0.001751398,0.002229747,0.00213238,0.001209342],"category_scores_gemma":[0.07598035,0.0006183927,0.001670502,0.001082671,0.001177999,0.001884225,0.002040242,0.002059711,0.0004432525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001932446,"about_ca_system_score_gemma":0.003540471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007291235,"about_ca_topic_score_gemma":0.005192754,"domain_scores_codex":[0.982978,0.01092406,0.001878348,0.002326569,0.00144583,0.0004470438],"domain_scores_gemma":[0.8859705,0.09001372,0.002936363,0.004686448,0.01566077,0.0007322491],"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":[0.008059763,0.006842352,0.2089922,0.001541407,0.002157368,0.0006138519,0.002890766,0.1736716,0.0151803,0.001781452,0.004670832,0.5735981],"study_design_scores_gemma":[0.0006582326,0.002066268,0.02213994,0.0001186194,0.0003924185,0.0003623886,0.0004854019,0.959223,0.01212832,0.001146289,0.00122626,0.00005281835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7893993,0.001439519,0.2017705,0.0003837069,0.0001000189,0.003353579,0.000908251,0.00143933,0.001205767],"genre_scores_gemma":[0.7136045,0.0002483621,0.280771,0.0001820342,0.00002807371,0.001639732,0.002804313,0.0001052981,0.0006166394],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04763125,"threshold_uncertainty_score":0.2519011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02967499646182286,"score_gpt":0.3779441789061225,"score_spread":0.3482691824442997,"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."}}