{"id":"W4292386145","doi":"10.1371/journal.pdig.0000078","title":"A multiple instance learning approach for detecting COVID-19 in peripheral blood smears","year":2022,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Coronavirus disease 2019 (COVID-19); Peripheral blood; Blood smear; Computer science; Disease; Cell type; Medicine; Cell; Pathology; Immunology; Infectious disease (medical specialty); Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0003455017,0.0001983114,0.0002983156,0.0002025923,0.0005793548,0.0006092411,0.0008127659,0.00002050367,0.000003058195],"category_scores_gemma":[0.0009275441,0.000232239,0.000108584,0.0007459067,0.00004995993,0.001496141,0.0005784913,0.0003183476,0.000002324019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005701099,"about_ca_system_score_gemma":0.0008982322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000105277,"about_ca_topic_score_gemma":0.00002417092,"domain_scores_codex":[0.9976223,0.00009491327,0.0003987514,0.0006895062,0.0004661195,0.0007284711],"domain_scores_gemma":[0.9986983,0.000276055,0.0001917137,0.0003623744,0.0000359996,0.0004355637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005334435,0.01404377,0.4202232,0.003582441,0.0002227401,0.0002538041,0.02168489,0.2329907,0.0001612922,0.01485046,0.001312178,0.2901411],"study_design_scores_gemma":[0.00643209,0.001976607,0.002045547,0.00007754269,0.00001290216,0.0001868536,0.003090645,0.9672008,0.0001159757,0.004263086,0.013492,0.001105952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7797304,0.001486017,0.2079405,0.001474407,0.0002229549,0.002183848,0.000293691,0.001491034,0.005177146],"genre_scores_gemma":[0.9798102,0.000002360261,0.01744244,0.002047567,0.00002917811,0.0003998254,0.00005807194,0.00003467458,0.0001756834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7342101,"threshold_uncertainty_score":0.947043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03972602264648287,"score_gpt":0.2824320786263937,"score_spread":0.2427060559799109,"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."}}