1
|
Kang DH, Kim GHJ, Park SB, Lee SI, Koh JS, Brown MS, Abtin F, McNitt-Gray MF, Goldin JG, Lee JS. Quantitative Computed Tomography Lung COVID Scores with Laboratory Markers: Utilization to Predict Rapid Progression and Monitor Longitudinal Changes in Patients with Coronavirus 2019 (COVID-19) Pneumonia. Biomedicines 2024; 12:120. [PMID: 38255225 PMCID: PMC10813449 DOI: 10.3390/biomedicines12010120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 12/27/2023] [Accepted: 01/04/2024] [Indexed: 01/24/2024] Open
Abstract
Coronavirus disease 2019 (COVID-19), is an ongoing issue in certain populations, presenting rapidly worsening pneumonia and persistent symptoms. This study aimed to test the predictability of rapid progression using radiographic scores and laboratory markers and present longitudinal changes. This retrospective study included 218 COVID-19 pneumonia patients admitted at the Chungnam National University Hospital. Rapid progression was defined as respiratory failure requiring mechanical ventilation within one week of hospitalization. Quantitative COVID (QCOVID) scores were derived from high-resolution computed tomography (CT) analyses: (1) ground glass opacity (QGGO), (2) mixed diseases (QMD), and (3) consolidation (QCON), and the sum, quantitative total lung diseases (QTLD). Laboratory data, including inflammatory markers, were obtained from electronic medical records. Rapid progression was observed in 9.6% of patients. All QCOVID scores predicted rapid progression, with QMD showing the best predictability (AUC = 0.813). In multivariate analyses, the QMD score and interleukin(IL)-6 level were important predictors for rapid progression (AUC = 0.864). With >2 months follow-up CT, remained lung lesions were observed in 21 subjects, even after several weeks of negative reverse transcription polymerase chain reaction test. AI-driven quantitative CT scores in conjugation with laboratory markers can be useful in predicting the rapid progression and monitoring of COVID-19.
Collapse
Affiliation(s)
- Da Hyun Kang
- Department of Internal Medicine, College of Medicine, Chungnam National University, Daejeon 35015, Republic of Korea; (D.H.K.); (S.-I.L.); (J.S.K.)
| | - Grace Hyun J. Kim
- Department of Biostatistics, Fielding School of Public Health, University of California, Los Angeles, CA 90095, USA;
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA 90024, USA; (M.S.B.); (F.A.); (M.F.M.-G.)
| | - Sa-Beom Park
- Center of Biohealth Convergence and Open Sharing System, Hongik University, Seoul 04401, Republic of Korea;
| | - Song-I Lee
- Department of Internal Medicine, College of Medicine, Chungnam National University, Daejeon 35015, Republic of Korea; (D.H.K.); (S.-I.L.); (J.S.K.)
| | - Jeong Suk Koh
- Department of Internal Medicine, College of Medicine, Chungnam National University, Daejeon 35015, Republic of Korea; (D.H.K.); (S.-I.L.); (J.S.K.)
| | - Matthew S. Brown
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA 90024, USA; (M.S.B.); (F.A.); (M.F.M.-G.)
| | - Fereidoun Abtin
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA 90024, USA; (M.S.B.); (F.A.); (M.F.M.-G.)
| | - Michael F. McNitt-Gray
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA 90024, USA; (M.S.B.); (F.A.); (M.F.M.-G.)
| | - Jonathan G. Goldin
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA 90024, USA; (M.S.B.); (F.A.); (M.F.M.-G.)
| | - Jeong Seok Lee
- Graduate School of Medical Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea
| |
Collapse
|
2
|
Wolszczak-Biedrzycka B, Dorf J, Wojewódzka-Żelezniakowicz M, Żendzian-Piotrowska M, Dymicka-Piekarska VJ, Matowicka-Karna J, Maciejczyk M. Unveiling COVID-19 Secrets: Harnessing Cytokines as Powerful Biomarkers for Diagnosis and Predicting Severity. J Inflamm Res 2023; 16:6055-6070. [PMID: 38107380 PMCID: PMC10723593 DOI: 10.2147/jir.s439217] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2023] [Accepted: 11/21/2023] [Indexed: 12/19/2023] Open
Abstract
Introduction In coronavirus disease (COVID-19), inflammation takes center stage, with a cascade of cytokines released, contributing to both inflammation and lung damage. The objective of this study is to identify biomarkers for diagnosing and predicting the severity of COVID-19. Materials and Methods Cytokine levels were determined in the serum from venous blood samples collected from 100 patients with COVID-19 and 50 healthy controls. COVID-19 patients classified based on the Modified Early Warning (MEWS) score. Cytokine concentrations were determined with a multiplex ELISA kit (Bio-Plex Pro™ Human Cytokine Screening Panel). Results The concentrations of all analyzed cytokines were elevated in the serum of COVID-19 patients relative to the control group, but no significant differences were observed in interleukin-9 (IL-9) and IL-12 p70 levels. In addition, the concentrations of IL-1α, IL-1β, IL-1ra, IL-2Rα, IL-6, IL-12 p40, IL-18, and tumor necrosis factor alpha (TNFα) were significantly higher in symptomatic patients with accompanying pneumonia without respiratory failure (stage 2) than in asymptomatic/mildly symptomatic patients (stage 1). Conclusion The study revealed that IL-1ra, IL-2Rα, IL-6, IL-8, IL-12 p40, IL-16, and IL-18 levels serve as potential diagnostic biomarkers in COVID-19 patients. Furthermore, elevated IL-1α levels proved to be valuable in assessing the severity of COVID-19.
Collapse
Affiliation(s)
- Blanka Wolszczak-Biedrzycka
- Department of Psychology and Sociology of Health and Public Health, University of Warmia and Mazury in Olsztyn, Olsztyn, 10-900, Poland
| | - Justyna Dorf
- Department of Clinical Laboratory Diagnostics, Medical University of Bialystok, Bialystok, 15-089, Poland
| | | | | | | | - Joanna Matowicka-Karna
- Department of Clinical Laboratory Diagnostics, Medical University of Bialystok, Bialystok, 15-089, Poland
| | - Mateusz Maciejczyk
- Department of Hygiene, Epidemiology and Ergonomics, Medical University of Bialystok, Bialystok, 15-089, Poland
| |
Collapse
|
3
|
Atceken Z, Celik Y, Atasoy C, Peker Y. The Diagnostic Utility of Artificial Intelligence-Guided Computed Tomography-Based Severity Scores for Predicting Short-Term Clinical Outcomes in Adults with COVID-19 Pneumonia. J Clin Med 2023; 12:7039. [PMID: 38002652 PMCID: PMC10672493 DOI: 10.3390/jcm12227039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Revised: 11/08/2023] [Accepted: 11/09/2023] [Indexed: 11/26/2023] Open
Abstract
Chest computed tomography (CT) imaging with the use of an artificial intelligence (AI) analysis program has been helpful for the rapid evaluation of large numbers of patients during the COVID-19 pandemic. We have previously demonstrated that adults with COVID-19 infection with high-risk obstructive sleep apnea (OSA) have poorer clinical outcomes than COVID-19 patients with low-risk OSA. In the current secondary analysis, we evaluated the association of AI-guided CT-based severity scores (SSs) with short-term outcomes in the same cohort. In total, 221 patients (mean age of 52.6 ± 15.6 years, 59% men) with eligible chest CT images from March to May 2020 were included. The AI program scanned the CT images in 3D, and the algorithm measured volumes of lobes and lungs as well as high-opacity areas, including ground glass and consolidation. An SS was defined as the ratio of the volume of high-opacity areas to that of the total lung volume. The primary outcome was the need for supplemental oxygen and hospitalization over 28 days. A receiver operating characteristic (ROC) curve analysis of the association between an SS and the need for supplemental oxygen revealed a cut-off score of 2.65 on the CT images, with a sensitivity of 81% and a specificity of 56%. In a multivariate logistic regression model, an SS > 2.65 predicted the need for supplemental oxygen, with an odds ratio (OR) of 3.98 (95% confidence interval (CI) 1.80-8.79; p < 0.001), and hospitalization, with an OR of 2.40 (95% CI 1.23-4.71; p = 0.011), adjusted for age, sex, body mass index, diabetes, hypertension, and coronary artery disease. We conclude that AI-guided CT-based SSs can be used for predicting the need for supplemental oxygen and hospitalization in patients with COVID-19 pneumonia.
Collapse
Affiliation(s)
- Zeynep Atceken
- Department of Radiology, Koc University School of Medicine, Istanbul 34010, Turkey; (Z.A.); (C.A.)
| | - Yeliz Celik
- Center for Translational Medicine (KUTTAM), Department of Pulmonary Medicine, Koc University School of Medicine, and Koc University Research, Koc University, Istanbul 34010, Turkey;
| | - Cetin Atasoy
- Department of Radiology, Koc University School of Medicine, Istanbul 34010, Turkey; (Z.A.); (C.A.)
| | - Yüksel Peker
- Center for Translational Medicine (KUTTAM), Department of Pulmonary Medicine, Koc University School of Medicine, and Koc University Research, Koc University, Istanbul 34010, Turkey;
- Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg, 40530 Gothenburg, Sweden
- Department of Clinical Sciences, Respiratory Medicine and Allergology, Faculty of Medicine, Lund University, 22185 Lund, Sweden
- Division of Pulmonary, Allergy, and Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA 15213, USA
- Division of Sleep and Circadian Disorders, Harvard Medical School, Brigham and Women’s Hospital, Boston, MA 02115, USA
| |
Collapse
|
4
|
Topal Ü, Yılmaz G, Şahin AS. Are the thorax Computed Tomography findings of ICU patients diagnosed with COVID-19 pneumonia related to the duration of hospital stay and mortality? J Infect Chemother 2023; 29:495-501. [PMID: 36627082 PMCID: PMC9825141 DOI: 10.1016/j.jiac.2022.12.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 12/06/2022] [Accepted: 12/31/2022] [Indexed: 01/09/2023]
Abstract
INTRODUCTION Quantitative thorax Computed Tomography (CT) is used to determine the severity of COVID-19 pneumonia. With a new approach, quantitative thoracic CT is to contribute to the triage of patients with severe COVID-19 pneumonia in the ICU and to evaluate its relation with mortality by taking into account the vaccination status. METHODS Fifty-six patients who had a diagnosis of COVID-19 pneumonia confirmed in the adult ICU were evaluated retrospectively. To evaluate the degree of parenchymal involvement, the quantitative CT "craniocaudal diameter of the thorax/craniocaudal largest lesion diameter (CCDT/CCDL)" ratio and semi-quantitative total CT severity scores (TCTSS) (0:0%; 1:1-25%; 2:26-50%; 3:51-75% and 4:76-100%) were calculated. Both methods were analyzed with comparative ROC curves for predicting mortality. The effects of vaccines on thorax CT findings and laboratory parameters were also investigated. RESULTS The sensitivities and specificities were found to be 72.5%, 75.61%, and 80%, 73.33% when CCDT/CCDL and TCTSS cutoff value was taken <1.4, and >9, respectively, to predict mortality in COVID-19 pneumonia (Area Under the Curve = AUC = 0.797 and 0.752). Both methods predicted mortality well and no statistical differences were detected between them (p = 0.3618). In vaccinated patients, CRP was higher (p = 0.045), and LDH and ferritin were lower (p = 0.049, p = 0.004). The number of lobes involved was lower in the vaccinated group (p = 0.001). CONCLUSIONS The quantitative CT score (CCDT/CCDL) may play as important a role as TCTSS in diagnosing COVID-19 pneumonia, determining the severity of the disease, and predicting the related mortality. COVID-19 vaccines may affect laboratory parameters and cause less pneumonia on thoracic CT than in unvaccinated individuals.
Collapse
Affiliation(s)
- Ümmihan Topal
- Department of Radiology, Health Sciences University, Kanuni Sultan Süleyman Training and Research Hospital, Istanbul, 34303, Turkey,Corresponding author
| | - Gülseren Yılmaz
- Department of Anesthesiology and Reanimation, HSU, Kanuni Sultan Suleyman Education and Training Hospital, Istanbul, Turkey
| | - Ayça Sultan Şahin
- Department of Anesthesiology and Reanimation, HSU, Kanuni Sultan Suleyman Education and Training Hospital, Istanbul, Turkey
| |
Collapse
|
5
|
Guiot J, Maes N, Winandy M, Henket M, Ernst B, Thys M, Frix AN, Morimont P, Rousseau AF, Canivet P, Louis R, Misset B, Meunier P, Charbonnier JP, Lambermont B. Automatized lung disease quantification in patients with COVID-19 as a predictive tool to assess hospitalization severity. Front Med (Lausanne) 2022; 9:930055. [PMID: 36106317 PMCID: PMC9465374 DOI: 10.3389/fmed.2022.930055] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2022] [Accepted: 07/25/2022] [Indexed: 11/13/2022] Open
Abstract
The pandemic of COVID-19 led to a dramatic situation in hospitals, where staff had to deal with a huge number of patients in respiratory distress. To alleviate the workload of radiologists, we implemented an artificial intelligence (AI) - based analysis named CACOVID-CT, to automatically assess disease severity on chest CT scans obtained from those patients. We retrospectively studied CT scans obtained from 476 patients admitted at the University Hospital of Liege with a COVID-19 disease. We quantified the percentage of COVID-19 affected lung area (% AA) and the CT severity score (total CT-SS). These quantitative measurements were used to investigate the overall prognosis and patient outcome: hospital length of stay (LOS), ICU admission, ICU LOS, mechanical ventilation, and in-hospital death. Both CT-SS and % AA were highly correlated with the hospital LOS, the risk of ICU admission, the risk of mechanical ventilation and the risk of in-hospital death. Thus, CAD4COVID-CT analysis proved to be a useful tool in detecting patients with higher hospitalization severity risk. It will help for management of the patients flow. The software measured the extent of lung damage with great efficiency, thus relieving the workload of radiologists.
Collapse
Affiliation(s)
- Julien Guiot
- Respiratory Department, University Hospital of Liège, Liège, Belgium
- *Correspondence: Julien Guiot,
| | - Nathalie Maes
- Biostatistics and Medico-Economic Information Department, University Hospital of Liège, Liège, Belgium
| | - Marie Winandy
- Respiratory Department, University Hospital of Liège, Liège, Belgium
| | - Monique Henket
- Respiratory Department, University Hospital of Liège, Liège, Belgium
| | - Benoit Ernst
- Respiratory Department, University Hospital of Liège, Liège, Belgium
| | - Marie Thys
- Biostatistics and Medico-Economic Information Department, University Hospital of Liège, Liège, Belgium
| | - Anne-Noelle Frix
- Respiratory Department, University Hospital of Liège, Liège, Belgium
| | - Philippe Morimont
- Intensive Care Department, University Hospital of Liège, Liège, Belgium
| | | | - Perrine Canivet
- Department of Radiology, University Hospital of Liège, Liège, Belgium
| | - Renaud Louis
- Respiratory Department, University Hospital of Liège, Liège, Belgium
| | - Benoît Misset
- Intensive Care Department, University Hospital of Liège, Liège, Belgium
| | - Paul Meunier
- Department of Radiology, University Hospital of Liège, Liège, Belgium
| | | | | |
Collapse
|
6
|
Chandra TB, Singh BK, Jain D. Disease Localization and Severity Assessment in Chest X-Ray Images using Multi-Stage Superpixels Classification. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 222:106947. [PMID: 35749885 PMCID: PMC9403875 DOI: 10.1016/j.cmpb.2022.106947] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/05/2022] [Revised: 05/25/2022] [Accepted: 06/08/2022] [Indexed: 05/13/2023]
Abstract
BACKGROUND AND OBJECTIVES Chest X-ray (CXR) is a non-invasive imaging modality used in the prognosis and management of chronic lung disorders like tuberculosis (TB), pneumonia, coronavirus disease (COVID-19), etc. The radiomic features associated with different disease manifestations assist in detection, localization, and grading the severity of infected lung regions. The majority of the existing computer-aided diagnosis (CAD) system used these features for the classification task, and only a few works have been dedicated to disease-localization and severity scoring. Moreover, the existing deep learning approaches use class activation map and Saliency map, which generate a rough localization. This study aims to generate a compact disease boundary, infection map, and grade the infection severity using proposed multistage superpixel classification-based disease localization and severity assessment framework. METHODS The proposed method uses a simple linear iterative clustering (SLIC) technique to subdivide the lung field into small superpixels. Initially, the different radiomic texture and proposed shape features are extracted and combined to train different benchmark classifiers in a multistage framework. Subsequently, the predicted class labels are used to generate an infection map, mark disease boundary, and grade the infection severity. The performance is evaluated using a publicly available Montgomery dataset and validated using Friedman average ranking and Holm and Nemenyi post-hoc procedures. RESULTS The proposed multistage classification approach achieved accuracy (ACC)= 95.52%, F-Measure (FM)= 95.48%, area under the curve (AUC)= 0.955 for Stage-I and ACC=85.35%, FM=85.20%, AUC=0.853 for Stage-II using calibration dataset and ACC = 93.41%, FM = 95.32%, AUC = 0.936 for Stage-I and ACC = 84.02%, FM = 71.01%, AUC = 0.795 for Stage-II using validation dataset. Also, the model has demonstrated the average Jaccard Index (JI) of 0.82 and Pearson's correlation coefficient (r) of 0.9589. CONCLUSIONS The obtained classification results using calibration and validation dataset confirms the promising performance of the proposed framework. Also, the average JI shows promising potential to localize the disease, and better agreement between radiologist score and predicted severity score (r) confirms the robustness of the method. Finally, the statistical test justified the significance of the obtained results.
Collapse
Affiliation(s)
- Tej Bahadur Chandra
- Department of Computer Applications, National Institute of Technology Raipur, Chhattisgarh, India.
| | - Bikesh Kumar Singh
- Department of Biomedical Engineering, National Institute of Technology Raipur, Chhattisgarh, India
| | - Deepak Jain
- Department of Radiodiagnosis, Pt. Jawahar Lal Nehru Memorial Medical College, Raipur, Chhattisgarh, India
| |
Collapse
|
7
|
Abdulkareem KH, Mostafa SA, Al-Qudsy ZN, Mohammed MA, Al-Waisy AS, Kadry S, Lee J, Nam Y. Automated System for Identifying COVID-19 Infections in Computed Tomography Images Using Deep Learning Models. JOURNAL OF HEALTHCARE ENGINEERING 2022; 2022:5329014. [PMID: 35368962 PMCID: PMC8968354 DOI: 10.1155/2022/5329014] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/31/2021] [Revised: 01/29/2022] [Accepted: 02/18/2022] [Indexed: 12/24/2022]
Abstract
Coronavirus disease 2019 (COVID-19) is a novel disease that affects healthcare on a global scale and cannot be ignored because of its high fatality rate. Computed tomography (CT) images are presently being employed to assist doctors in detecting COVID-19 in its early stages. In several scenarios, a combination of epidemiological criteria (contact during the incubation period), the existence of clinical symptoms, laboratory tests (nucleic acid amplification tests), and clinical imaging-based tests are used to diagnose COVID-19. This method can miss patients and cause more complications. Deep learning is one of the techniques that has been proven to be prominent and reliable in several diagnostic domains involving medical imaging. This study utilizes a convolutional neural network (CNN), stacked autoencoder, and deep neural network to develop a COVID-19 diagnostic system. In this system, classification undergoes some modification before applying the three CT image techniques to determine normal and COVID-19 cases. A large-scale and challenging CT image dataset was used in the training process of the employed deep learning model and reporting their final performance. Experimental outcomes show that the highest accuracy rate was achieved using the CNN model with an accuracy of 88.30%, a sensitivity of 87.65%, and a specificity of 87.97%. Furthermore, the proposed system has outperformed the current existing state-of-the-art models in detecting the COVID-19 virus using CT images.
Collapse
Affiliation(s)
| | - Salama A. Mostafa
- Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, 86400 Batu Pahat, Johor, Malaysia
| | - Zainab N. Al-Qudsy
- Computer Sciences Department, Baghdad College of Economic Sciences University, Baghdad, Iraq
| | - Mazin Abed Mohammed
- College of Computer Science and Information Technology, University of Anbar, 11 Ramadi, Anbar, Iraq
| | - Alaa S. Al-Waisy
- Communications Engineering Techniques Department Information Technology Collage, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq
| | - Seifedine Kadry
- Faculty of Applied Computing and Technology, Noroff University College, Kristiansand, Norway
| | - Jinseok Lee
- Department of Biomedical Engineering, College of Electronics and Information, Kyung Hee University, Yongin-si, Gyeonggi-do 17104, Republic of Korea
| | - Yunyoung Nam
- Department of Computer Science and Engineering, Soonchunhyang University, Asan 31538, Republic of Korea
| |
Collapse
|