{"doi":"10.3348/kjr.2020.1104","title":"Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data","abstract":"OBJECTIVE: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. MATERIALS AND METHODS: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. RESULTS: = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. CONCLUSION: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.","journal":"Korean Journal of Radiology","year":2021,"id":167203,"datarank":0.5244761342199721,"base_score":3.4965075614664802,"endowment":3.4965075614664802,"self_citation_contribution":0.5244761342199721,"citation_network_contribution":0.0,"self_endowment_contribution":0.5244761342199721,"citer_contribution":0.0,"corpus_percentile":63.1,"corpus_rank":4774,"citation_count":32,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.7303,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":361603,"name":"Yanhe Xiao","orcid":"0000-0003-1553-0883","position":1,"is_corresponding":false},{"id":57587,"name":"Zhicheng Jiao","orcid":"0000-0002-6968-0919","position":2,"is_corresponding":false},{"id":694005,"name":"Rujapa Thepumnoeysuk","orcid":"0000-0002-1637-1768","position":3,"is_corresponding":false},{"id":631897,"name":"Kasey Halsey","orcid":"0000-0002-6746-8615","position":4,"is_corresponding":false},{"id":245749,"name":"Jing Wu","orcid":"0000-0001-9602-7387","position":5,"is_corresponding":false},{"id":631898,"name":"Thi My Linh Tran","orcid":"0000-0002-8126-1258","position":6,"is_corresponding":false},{"id":631899,"name":"B. R. Hsieh","orcid":"0000-0001-5209-801X","position":7,"is_corresponding":false},{"id":631896,"name":"Ji Whae Choi","orcid":"0000-0003-1061-3102","position":8,"is_corresponding":false},{"id":631900,"name":"Dongcui Wang","orcid":"0000-0002-4435-2214","position":9,"is_corresponding":false},{"id":103869,"name":"Martin Vallières","orcid":"0000-0001-7639-8172","position":10,"is_corresponding":false},{"id":259891,"name":"Robin Wang","orcid":"0000-0001-7369-0602","position":11,"is_corresponding":false},{"id":631901,"name":"Scott Collins","orcid":"0000-0002-8117-164X","position":12,"is_corresponding":false},{"id":58496,"name":"Xue Feng","orcid":"0000-0002-2181-9889","position":13,"is_corresponding":false},{"id":70257,"name":"Michael D. Feldman","orcid":"0000-0002-6661-4940","position":14,"is_corresponding":false},{"id":259898,"name":"Paul J. Zhang","orcid":"0000-0001-6810-8681","position":15,"is_corresponding":false},{"id":631904,"name":"Michael K. Atalay","orcid":"0000-0003-3549-2634","position":16,"is_corresponding":false},{"id":694006,"name":"Ronnie Sebro","orcid":"0000-0001-7232-4416","position":17,"is_corresponding":false},{"id":310670,"name":"Li Yang","orcid":"0000-0001-5973-3653","position":18,"is_corresponding":false},{"id":230034,"name":"Yong Fan","orcid":"0000-0001-9869-4685","position":19,"is_corresponding":false},{"id":631905,"name":"Weihua Liao","orcid":"0000-0002-1926-3527","position":20,"is_corresponding":false},{"id":259901,"name":"Harrison X. Bai","orcid":"0000-0002-7460-8866","position":21,"is_corresponding":false},{"id":259893,"name":"Subhanik Purkayastha","orcid":"0000-0003-3067-2070","position":0,"is_corresponding":true}],"reference_count":48,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-18T23:45:54.042727Z","pmid":"33739635","pmcid":"PMC8236359","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}