{"id":"W2751783141","doi":"10.5858/arpa.2017-0139-oa","title":"Integrated Pathology Informatics Enables High-Quality Personalized and Precision Medicine: Digital Pathology and Beyond","year":2017,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakeridge Health; University Health Network","funders":"","keywords":"Digital pathology; Subspecialty; Workload; Hematopathology; Pathology; Precision medicine; Computer science; Medicine; Quality assurance; Personalized medicine; Informatics; Medical physics; Medical laboratory; Health informatics; Telepathology; Data science; Health care; Bioinformatics; External quality assessment; Telemedicine; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001328563,0.0003337783,0.0008914844,0.0003619198,0.0003922284,0.00004809098,0.0008842724,0.0002237346,0.00001881997],"category_scores_gemma":[0.002380977,0.0002489729,0.00003557818,0.0001901242,0.006510353,0.0008202148,0.0007115963,0.0004318782,0.000002978265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002614419,"about_ca_system_score_gemma":0.0001507775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003315093,"about_ca_topic_score_gemma":0.00002825664,"domain_scores_codex":[0.9973541,0.0004874781,0.0008873975,0.0005685757,0.000313497,0.0003888999],"domain_scores_gemma":[0.9963112,0.001128558,0.0009390378,0.00119238,0.0002240602,0.0002047343],"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":[0.0006891,0.0001900098,0.03650141,0.0005850325,0.0001663047,0.002023518,0.07075271,0.000006007084,0.1855934,0.09595567,0.001428416,0.6061085],"study_design_scores_gemma":[0.02449926,0.01197423,0.6728655,0.001687545,0.0003723594,0.00583022,0.0141224,0.004569354,0.01118237,0.230985,0.01989095,0.002020771],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8794345,0.002307182,0.1107086,0.004141602,0.0009643206,0.0003173807,0.00008825491,0.0001136577,0.001924527],"genre_scores_gemma":[0.9797744,0.001678099,0.01733276,0.0008709672,0.0001798611,0.00002627891,0.00003035335,0.00002026554,0.0000869765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6363641,"threshold_uncertainty_score":0.9999962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01617967339655678,"score_gpt":0.2882883895018667,"score_spread":0.2721087161053099,"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."}}