{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003082478,0.000107235,0.0003148879,0.00004357238,0.00006220902,0.00003105087,0.00005697044,0.00007537753,0.0000961903],"category_scores_gemma":[0.000130372,0.00007930729,0.00001620374,0.0001535467,0.0001239231,0.0001118984,0.0001079398,0.000230142,3.848176e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003450037,"about_ca_system_score_gemma":0.0002837258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002758972,"about_ca_topic_score_gemma":0.0000482361,"domain_scores_codex":[0.9986895,0.00001541357,0.0004106044,0.0001207092,0.0005800458,0.0001836986],"domain_scores_gemma":[0.9992695,0.00008173248,0.00008241318,0.00005945255,0.0001514533,0.0003554742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002281614,0.00005758246,0.02367347,0.002434045,0.0000405031,0.000002968894,0.02288192,2.208551e-7,0.000008746852,0.000005269467,0.0001093513,0.9505578],"study_design_scores_gemma":[0.009834057,0.001193687,0.719712,0.0002825983,0.00007703518,0.00003587503,0.01985168,0.2430502,0.0008829213,0.00001172773,0.004734,0.0003342712],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943359,0.002463453,0.0007928732,0.001237759,0.00002737956,0.0009239123,0.00002033398,0.00002398965,0.0001743785],"genre_scores_gemma":[0.9943262,0.0001677909,0.004589914,0.0006113888,0.0001391971,0.0001058818,0.00002900362,0.000008754864,0.0000218667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9502235,"threshold_uncertainty_score":0.3234057,"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."}}