{"id":"W2608319802","doi":"10.1109/jtehm.2017.2691339","title":"Efficacy Evaluation of SAVE for the Diagnosis of Superficial Neoplastic Lesion","year":2017,"lang":"en","type":"article","venue":"IEEE Journal of Translational Engineering in Health and Medicine","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Western Economic Diversification Canada; Natural Sciences and Engineering Research Council of Canada; Grand Challenges Canada; Canada Foundation for Innovation","keywords":"Chromoendoscopy; Biopsy; Lesion; Medicine; Computer science; Artificial intelligence; Radiology; Cancer; Colonoscopy; Colorectal cancer; Pathology; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001508663,0.00005773383,0.0002711854,0.0001489814,0.00005832882,0.000002095034,0.00004381376,0.00003555435,0.000005885139],"category_scores_gemma":[0.001222899,0.00003816259,0.00004946209,0.00005468188,0.00004738953,0.00004692114,0.000001744792,0.0001265064,1.758607e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003432876,"about_ca_system_score_gemma":0.0002789982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001017836,"about_ca_topic_score_gemma":0.00002868813,"domain_scores_codex":[0.9989676,0.00001954576,0.000486562,0.00005407649,0.0003926053,0.00007964373],"domain_scores_gemma":[0.9985618,0.0007221648,0.0002861932,0.00007152124,0.0002767357,0.00008155788],"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":[0.02234191,0.0002941375,0.06047728,0.003431389,0.0002593124,0.000004363882,0.005962808,0.3317281,0.005503413,0.0004403136,0.0002963651,0.5692606],"study_design_scores_gemma":[0.01496975,0.007567944,0.7340742,0.003589381,0.0003006558,0.00009302823,0.0001230089,0.2366608,0.00196037,0.0001303706,0.0004626869,0.00006773842],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977042,0.004921283,0.01269809,0.004423518,0.0005409982,0.0003582966,0.000003115734,0.000002186611,0.00001047708],"genre_scores_gemma":[0.9983907,0.0005907758,0.0005040778,0.00002649273,0.0004705945,0.00000872184,0.000001566502,0.000005451862,0.000001560583],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.673597,"threshold_uncertainty_score":0.1556225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1049506204085974,"score_gpt":0.3863253560192723,"score_spread":0.2813747356106749,"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."}}