{"id":"W4296962373","doi":"10.1007/978-3-031-16760-7_8","title":"Multi-Feature Vision Transformer via Self-Supervised Representation Learning for Improvement of COVID-19 Diagnosis","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Semi-supervised learning; Feature (linguistics); Machine learning; Coronavirus disease 2019 (COVID-19); Feature learning; Supervised learning; Labeled data; Deep learning; Context (archaeology); Pattern recognition (psychology); Artificial neural network; Infectious disease (medical specialty); Medicine; Pathology; Disease","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"],"consensus_categories":[],"category_scores_codex":[0.0009980912,0.0004696216,0.0007698948,0.0009290618,0.0003698954,0.00006664559,0.0005699898,0.0003341922,0.0002269634],"category_scores_gemma":[0.0006576648,0.0004412647,0.0003393335,0.0005654138,0.0003150718,0.0002136678,0.0002327876,0.0009466587,0.000002699838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001287811,"about_ca_system_score_gemma":0.001088865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002199454,"about_ca_topic_score_gemma":0.00009840144,"domain_scores_codex":[0.9963246,0.00004570774,0.0006145398,0.001389365,0.001145331,0.0004804787],"domain_scores_gemma":[0.9965461,0.001806475,0.0003665659,0.0007140943,0.0002965772,0.0002702138],"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":[0.0003615587,0.0006292781,0.002495098,0.002412795,0.0001469881,0.00009207806,0.007276229,0.1338079,0.02246058,0.00009248716,0.0006642404,0.8295608],"study_design_scores_gemma":[0.00795391,0.005260558,0.0009477454,0.001407235,0.0005213238,0.00006701224,0.000008230395,0.7882748,0.03509947,0.002829827,0.156271,0.001358955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001005577,0.0004704944,0.9734915,0.02130841,0.0007926585,0.0026916,0.00002879351,0.0001646943,0.0000462354],"genre_scores_gemma":[0.2452531,0.001518458,0.6792324,0.06994905,0.001160045,0.001148978,0.0005539819,0.000355456,0.0008286253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8282018,"threshold_uncertainty_score":0.9998039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03159226809544642,"score_gpt":0.3367101878616175,"score_spread":0.3051179197661711,"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."}}