Artificial intelligence for the triage of COVID-19 patients at the emergency department: a systematic review

The aim of this article is to systematically analyze the available literature on the efficacy and validity of artificial intelligence (AI) applied to medical imaging techniques in the triage of patients with suspected or confirmed coronavirus disease 2019 (COVID-19) in Emergency Departments (EDs). A systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines was conducted. Medline, Web of Science, and Scopus were searched to identify observational studies evaluating the efficacy of AI methods in the diagnosis and prognosis of COVID-19 using medical imaging. The main characteristics of the selected studies were extracted by two independent researchers and were formally assessed in terms of methodological quality using the Newcastle-Ottawa scale. A total of 11 studies, including 14,499 patients, met inclusion criteria. The quality of the studies was medium to high. Overall, the diagnostic yield of the AI techniques compared to a gold standard was high, with sensitivity and specificity values ranging from 79% to 98% and from 70%to 93%, respectively. The methodological approaches and imaging datasets were highly heterogeneous among studies. In conclusion, AI methods significantly boost the diagnostic yield of medical imaging in the triage of COVID-19 patients in the ED. However, there are significant limitations that should be overcome in future studies, particularly regarding the heterogeneity and limited amount of available data to train AI models.

[1]  M. Rivera-Izquierdo,et al.  Impact of the COVID-19 pandemic on osteoporotic vertebral fracture incidence and follow-up at the emergency department. A retrospective study of a tertiary hospital in southern Spain , 2022, Signa Vitae.

[2]  M. S. Tootooni,et al.  Image and structured data analysis for prognostication of health outcomes in patients presenting to the ED during the COVID-19 pandemic , 2021, International Journal of Medical Informatics.

[3]  G. Úrrutia,et al.  The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. , 2021, Revista espanola de cardiologia.

[4]  M. Rivera-Izquierdo,et al.  Sex Differences and Predictors of In-Hospital Mortality among Patients with COVID-19: Results from the ANCOHVID Multicentre Study , 2021, International journal of environmental research and public health.

[5]  S. Perlini,et al.  Deep learning and lung ultrasound for Covid-19 pneumonia detection and severity classification , 2021, Computers in Biology and Medicine.

[6]  M. Ortíz-Barrios,et al.  Process Improvement Approaches for Increasing the Response of Emergency Departments against the COVID-19 Pandemic: A Systematic Review , 2021, International journal of environmental research and public health.

[7]  M. Rivera-Izquierdo,et al.  Factors associated with readmission to the Emergency Department in a cohort of COVID-19 hospitalized patients , 2021, Signa Vitae.

[8]  S. Calza,et al.  Early prediction of in-hospital death of COVID-19 patients: a machine-learning model based on age, blood analyses, and chest x-ray score , 2021, medRxiv.

[9]  D. Fleischmann,et al.  Machine Learning to Predict In-Hospital Mortality in COVID-19 Patients Using Computed Tomography-Derived Pulmonary and Vascular Features , 2021, Journal of personalized medicine.

[10]  E. Jiménez-Mejías,et al.  Sequelae, persistent symptomatology and outcomes after COVID-19 hospitalization: the ANCOHVID multicentre 6-month follow-up study , 2021, BMC Medicine.

[11]  A. J. Láinez Ramos-Bossini,et al.  Percutaneous vertebroplasty versus conservative treatment and placebo in osteoporotic vertebral fractures: meta-analysis and critical review of the literature , 2021, European Radiology.

[12]  K. Nikita,et al.  Artificial intelligence in clinical care amidst COVID-19 pandemic: A systematic review , 2021, Computational and Structural Biotechnology Journal.

[13]  Yong Fan,et al.  Prognostication of patients with COVID-19 using artificial intelligence based on chest x-rays and clinical data: a retrospective study , 2021, The Lancet Digital Health.

[14]  Thomas J. Re,et al.  Prediction of Patient Management in COVID-19 Using Deep Learning-Based Fully Automated Extraction of Cardiothoracic CT Metrics and Laboratory Findings , 2021, Korean journal of radiology.

[15]  A. J. Láinez Ramos-Bossini,et al.  Pneumoperitoneum and COVID-19. A causal association? , 2021, Revista espanola de enfermedades digestivas : organo oficial de la Sociedad Espanola de Patologia Digestiva.

[16]  S. Lal,et al.  COVID-19: A Review on the Novel Coronavirus Disease Evolution, Transmission, Detection, Control and Prevention , 2021, Viruses.

[17]  M. Mascalchi,et al.  The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission , 2021, Scientific Reports.

[18]  J. Callejas-Rubio,et al.  Anakinra after treatment with corticosteroids alone or with tocilizumab in patients with severe COVID-19 pneumonia and moderate hyperinflammation. A retrospective cohort study , 2021, Internal and Emergency Medicine.

[19]  E. Yiğit,et al.  Fused Deep Features Based Classification Framework for COVID-19 Classification with Optimized MLP , 2020, ArXiv.

[20]  Mark Finkelstein,et al.  Combining Initial Radiographs and Clinical Variables Improves Deep Learning Prognostication in Patients with COVID-19 from the Emergency Department , 2020, Radiology. Artificial intelligence.

[21]  Şaban Öztürk,et al.  Classification of Coronavirus (COVID‐19) from X‐ray and CT images using shrunken features , 2020, Int. J. Imaging Syst. Technol..

[22]  Farah E. Shamout,et al.  An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department , 2020, ArXiv.

[23]  S. Morozov,et al.  CT-Based COVID-19 triage: Deep multitask learning improves joint identification and severity quantification , 2020, Medical Image Analysis.

[24]  R. Ospina.  Data-driven tools for assessing and combating COVID-19 outbreaks in Brazil based on analytics and statistical methods , 2021, Signa Vitae.

[25]  Eric H. Chou,et al.  The impact of coronavirus disease 2019 (COVID-19) on alternatives to opioids protocol for opioid reduction in emergency department , 2021, Signa Vitae.

[26]  Guillermo Droppelmann,et al.  Machine learning techniques as an efficient alternative diagnostic tool for COVID-19 cases , 2021, Signa Vitae.

[27]  V. Leiva,et al.  A statistical analysis for the epidemiological surveillance of COVID-19 in Chile , 2021, Signa Vitae.

[28]  A. J. Láinez Ramos-Bossini,et al.  Spontaneous pneumoperitoneum and pneumatosis intestinalis as sole manifestations of a COVID-19 infection. An extremely rare complication. , 2020, Revista espanola de enfermedades digestivas : organo oficial de la Sociedad Espanola de Patologia Digestiva.

[29]  Liyuan Tao,et al.  Influence of Cigarettes and Alcohol on the Severity and Death of COVID-19: A Multicenter Retrospective Study in Wuhan, China , 2020, Frontiers in Physiology.

[30]  Sinu Jose,et al.  Burnout and Resilience among Frontline Nurses during COVID-19 Pandemic: A Cross-sectional Study in the Emergency Department of a Tertiary Care Center, North India , 2020, Indian journal of critical care medicine : peer-reviewed, official publication of Indian Society of Critical Care Medicine.

[31]  Ş. Öztürk.  Image Inpainting based Compact Hash Code Learning using Modified U-Net , 2020, 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT).

[32]  Philip S. Yu,et al.  Detection of COVID-19 Using Deep Learning Algorithms on Chest Radiographs , 2020, Journal of thoracic imaging.

[33]  Jun Liu,et al.  Deep learning-based triage and analysis of lesion burden for COVID-19: a retrospective study with external validation , 2020, The Lancet Digital Health.

[34]  A. Zangrillo,et al.  Initial chest radiographs and artificial intelligence (AI) predict clinical outcomes in COVID-19 patients: analysis of 697 Italian patients , 2020, European Radiology.

[35]  Jayashree Kalpathy-Cramer,et al.  Improvement and Multi-Population Generalizability of a Deep Learning-Based Chest Radiograph Severity Score for COVID-19 , 2020, medRxiv.

[36]  E. Jiménez-Mejías,et al.  Therapeutic agents tested in 238 COVID-19 hospitalized patients and their relationship with mortality. , 2020, Medicina clinica.

[37]  P. Lardelli-Claret,et al.  Sociodemographic, clinical and laboratory factors on admission associated with COVID-19 mortality in hospitalized patients: A retrospective observational study , 2020, PloS one.

[38]  Franco Fusi,et al.  Comprehensive Analysis of Radiomic Datasets by RadAR , 2020, Cancer Research.

[39]  P. Lardelli-Claret,et al.  Clinical Factors, Preventive Behaviours and Temporal Outcomes Associated with COVID-19 Infection in Health Professionals at a Spanish Hospital , 2020, International journal of environmental research and public health.

[40]  Mark Finkelstein,et al.  Clinical and Chest Radiography Features Determine Patient Outcomes in Young and Middle-aged Adults with COVID-19 , 2020, Radiology.

[41]  O. Perski,et al.  The association of smoking status with SARS-CoV-2 infection, hospitalisation and mortality from COVID-19: A living rapid evidence review (version 5) , 2020, Qeios.

[42]  Jong Chul Ye,et al.  Deep Learning COVID-19 Features on CXR Using Limited Training Data Sets , 2020, IEEE Transactions on Medical Imaging.

[43]  Z. Fayad,et al.  CT Imaging Features of 2019 Novel Coronavirus (2019-nCoV) , 2020, Radiology.

[44]  E. Kucewicz-Czech,et al.  Triage during the COVID-19 pandemic. , 2020, Anaesthesiology intensive therapy.

[45]  Shalini Govil,et al.  Can Artificial Intelligence Reliably Report Chest X-Rays?: Radiologist Validation of an Algorithm trained on 2.3 Million X-Rays , 2018 .

[46]  Tatsuki Koyama,et al.  Severity scoring of lung oedema on the chest radiograph is associated with clinical outcomes in ARDS , 2018, Thorax.

[47]  Şaban Öztürk,et al.  Comparison of HOG, MSER, SIFT, FAST, LBP and CANNY features for cell detection in histopathological images , 2018 .

[48]  Ronald M. Summers,et al.  ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.

[49]  G. Iotti,et al.  Modified Lung Ultrasound Score for Assessing and Monitoring Pulmonary Aeration , 2017, Ultraschall in der Medizin - European Journal of Ultrasound.

[50]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[52]  P. Tugwell,et al.  The Newcastle-Ottawa Scale (NOS) for Assessing the Quality of Nonrandomised Studies in Meta-Analyses , 2014 .

[53]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[54]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .