{"id":"W4206948011","doi":"10.3389/fmed.2021.749146","title":"Establishment and Verification of Neural Network for Rapid and Accurate Cytological Examination of Four Types of Cerebrospinal Fluid Cells","year":2022,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Cerebrospinal fluid; Cytology; Pathology; Artificial neural network; Peripheral blood; Computer science; Giemsa stain; Clinical Practice; Medicine; Artificial intelligence; Immunology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001333666,0.0007981836,0.0004267042,0.0008022445,0.0004666648,0.0008104398,0.0009462896,0.0008615666,0.001317639],"category_scores_gemma":[0.002724327,0.0002798015,0.000386306,0.0003256068,0.0003202702,0.0007848185,0.0006546533,0.0006652923,0.0005362777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001196352,"about_ca_system_score_gemma":0.001429331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01166077,"about_ca_topic_score_gemma":0.00760984,"domain_scores_codex":[0.9994456,0.00007335756,0.00004220814,0.0001944311,0.0001492121,0.0000952931],"domain_scores_gemma":[0.9989377,0.0001989172,0.00008142942,0.00009128746,0.0006409319,0.00004978667],"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":[0.000572426,0.0004825222,0.03457114,0.0002664672,0.0001661656,0.0005305568,0.0002088699,0.2659917,0.114262,0.002711998,0.005131401,0.5751048],"study_design_scores_gemma":[0.00001025749,0.00007511652,0.003601188,0.00001496969,0.00002495446,0.00005306309,0.00002733257,0.965119,0.03013938,0.0003899098,0.0005320677,0.00001281176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3986634,0.0007505023,0.5887293,0.0004262211,0.00034043,0.000341036,0.0006325651,0.004944728,0.005171794],"genre_scores_gemma":[0.8752356,0.0002064341,0.1208702,0.000117921,0.0000244522,0.0002053386,0.0006575205,0.00005002384,0.002632605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01166077,"threshold_uncertainty_score":0.02318585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02404164877762521,"score_gpt":0.2499858662484947,"score_spread":0.2259442174708695,"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."}}