1
|
Zhou Y, Feng J, Mei S, Tang R, Xing S, Qin S, Zhang Z, Xu Q, Gao Y, He Z. A deep learning model for predicting COVID-19 ARDS in critically ill patients. Front Med (Lausanne) 2023; 10:1221711. [PMID: 37564041 PMCID: PMC10411521 DOI: 10.3389/fmed.2023.1221711] [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: 05/12/2023] [Accepted: 07/06/2023] [Indexed: 08/12/2023] Open
Abstract
Background The coronavirus disease 2019 (COVID-19) is an acute infectious pneumonia caused by a severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection previously unknown to humans. However, predictive studies of acute respiratory distress syndrome (ARDS) in patients with COVID-19 are limited. In this study, we attempted to establish predictive models to predict ARDS caused by COVID-19 via a thorough analysis of patients' clinical data and CT images. Method The data of included patients were retrospectively collected from the intensive care unit in our hospital from April 2022 to June 2022. The primary outcome was the development of ARDS after ICU admission. We first established two individual predictive models based on extreme gradient boosting (XGBoost) and convolutional neural network (CNN), respectively; then, an integrated model was developed by combining the two individual models. The performance of all the predictive models was evaluated using the area under receiver operating characteristic curve (AUC), confusion matrix, and calibration plot. Results A total of 103 critically ill COVID-19 patients were included in this research, of which 23 patients (22.3%) developed ARDS after admission; five predictive variables were selected and further used to establish the machine learning models, and the XGBoost model yielded the most accurate predictions with the highest AUC (0.94, 95% CI: 0.91-0.96). The AUC of the CT-based convolutional neural network predictive model and the integrated model was 0.96 (95% CI: 0.93-0.98) and 0.97 (95% CI: 0.95-0.99), respectively. Conclusion An integrated deep learning model could be used to predict COVID-19 ARDS in critically ill patients.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | | | - Yuan Gao
- Department of Critical Care Medicine, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai, China
| | - Zhengyu He
- Department of Critical Care Medicine, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai, China
| |
Collapse
|
2
|
Qin R, He L, Yang Z, Jia N, Chen R, Xie J, Fu W, Chen H, Lin X, Huang R, Luo T, Liu Y, Yao S, Jiang M, Li J. Identification of Parameters Representative of Immune Dysfunction in Patients with Severe and Fatal COVID-19 Infection: a Systematic Review and Meta-analysis. Clin Rev Allergy Immunol 2023; 64:33-65. [PMID: 35040086 PMCID: PMC8763427 DOI: 10.1007/s12016-021-08908-8] [Citation(s) in RCA: 22] [Impact Index Per Article: 22.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/29/2021] [Indexed: 01/26/2023]
Abstract
Abnormal immunological indicators associated with disease severity and mortality in patients with COVID-19 have been reported in several observational studies. However, there are marked heterogeneities in patient characteristics and research methodologies in these studies. We aimed to provide an updated synthesis of the association between immune-related indicators and COVID-19 prognosis. We conducted an electronic search of PubMed, Scopus, Ovid, Willey, Web of Science, Cochrane library, and CNKI for studies reporting immunological and/or immune-related parameters, including hematological, inflammatory, coagulation, and biochemical variables, tested on hospital admission of COVID-19 patients with different severities and outcomes. A total of 145 studies were included in the current meta-analysis, with 26 immunological, 11 hematological, 5 inflammatory, 4 coagulation, and 10 biochemical variables reported. Of them, levels of cytokines, including IL-1β, IL-1Ra, IL-2R, IL-4, IL-6, IL-8, IL-10, IL-18, TNF-α, IFN-γ, IgA, IgG, and CD4+ T/CD8+ T cell ratio, WBC, neutrophil, platelet, ESR, CRP, ferritin, SAA, D-dimer, FIB, and LDH were significantly increased in severely ill patients or non-survivors. Moreover, non-severely ill patients or survivors presented significantly higher counts of lymphocytes, monocytes, lymphocyte/monocyte ratio, eosinophils, CD3+ T,CD4+T and CD8+T cells, B cells, and NK cells. The currently updated meta-analysis primarily identified a hypercytokinemia profile with the severity and mortality of COVID-19 containing IL-1β, IL-1Ra, IL-2R, IL-4, IL-6, IL-8, IL-10, IL-18, TNF-α, and IFN-γ. Impaired innate and adaptive immune responses, reflected by decreased eosinophils, lymphocytes, monocytes, B cells, NK cells, T cells, and their subtype CD4+ and CD8+ T cells, and augmented inflammation, coagulation dysfunction, and nonpulmonary organ injury, were marked features of patients with poor prognosis. Therefore, parameters of immune response dysfunction combined with inflammatory, coagulated, or nonpulmonary organ injury indicators may be more sensitive to predict severe patients and those non-survivors.
Collapse
Affiliation(s)
- Rundong Qin
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Li He
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Zhaowei Yang
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Nan Jia
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Ruchong Chen
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Jiaxing Xie
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Wanyi Fu
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Hao Chen
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Xinliu Lin
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Renbin Huang
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Tian Luo
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Yukai Liu
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Siyang Yao
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Mei Jiang
- grid.470124.4National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| | - Jing Li
- grid.470124.4Department of Allergy and Clinical Immunology, National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong China
| |
Collapse
|
3
|
Validation of the T-Lymphocyte Subset Index (TLSI) as a Score to Predict Mortality in Unvaccinated Hospitalized COVID-19 Patients. Biomedicines 2022; 10:biomedicines10112788. [PMID: 36359306 PMCID: PMC9687349 DOI: 10.3390/biomedicines10112788] [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: 09/12/2022] [Revised: 10/30/2022] [Accepted: 10/31/2022] [Indexed: 11/06/2022] Open
Abstract
Lymphopenia has been consistently reported as associated with severe coronavirus disease 2019 (COVID-19). Several studies have described a profound decline in all T-cell subtypes in hospitalized patients with severe and critical COVID-19. The aim of this study was to assess the role of T-lymphocyte subset absolute counts measured at ward admission in predicting 30-day mortality in COVID-19 hospitalized patients, validating a new prognostic score, the T-Lymphocyte Subset Index (TLSI, range 0−2), based on the number of T-cell subset (CD4+ and CD8+) absolute counts that are below prespecified cutoffs. These cutoff values derive from a previously published work of our research group at Policlinico Tor Vergata, Rome, Italy: CD3+CD4+ < 369 cells/μL, CD3+CD8+ < 194 cells/μL. In the present single-center retrospective study, T-cell subsets were assessed on admission to the infectious diseases ward. Statistical analysis was performed using JASP (Version 0.16.2. JASP Team, 2022, Amsterdam, The Netherlands) and Prism8 (version 8.2.1. GraphPad Software, San Diego, CA, USA). Clinical and laboratory parameters of 296 adult patients hospitalized because of COVID-19 were analyzed. The overall mortality rate was 22.3% (66/296). Survivors (S) had a statistically significant lower TLSI score compared to non-survivors (NS) (p < 0.001). Patients with increasing TLSI scores had proportionally higher rates of 30-day mortality (p < 0.0001). In the multivariable logistic analysis, the TLSI was an independent predictor of in-hospital 30-day mortality (OR: 1.893, p = 0.003). Survival analysis showed that patients with a TLSI > 0 had an increased risk of death compared to patients with a TLSI = 0 (hazard ratio: 2.83, p < 0.0001). The TLSI was confirmed as an early and independent predictor of COVID-19 in-hospital 30-day mortality.
Collapse
|
4
|
Zinellu A, Mangoni AA. A systematic review and meta-analysis of the association between the neutrophil, lymphocyte, and platelet count, neutrophil-to-lymphocyte ratio, and platelet-to-lymphocyte ratio and COVID-19 progression and mortality. Expert Rev Clin Immunol 2022; 18:1187-1202. [PMID: 36047369 DOI: 10.1080/1744666x.2022.2120472] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
BACKGROUND AND AIMS Severe manifestations of coronavirus disease 2019 (COVID-19) are associated with alterations in blood cells that regulate immunity, inflammation, and hemostasis. We conducted an updated systematic review and meta-analysis of the association between the neutrophil, lymphocyte, and platelet count, neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR), and COVID-19 progression and mortality. METHODS A systematic literature search was conducted in PubMed, Web of Science, and Scopus for studies published between January 2020 and June 2022. RESULTS In 71 studies reporting the investigated parameters within 48 hours of admission, higher NLR (HR 1.21, 95% CI 1.16 to 1.27, p < 0.0001), relative neutrophilia (HR 1.62, 95% CI 1.46 to 1.80, p < 0.0001), relative lymphopenia (HR 1.62, 95% CI 1.27 to 2.08, p < 0.001), and relative thrombocytopenia (HR 1.74, 95% CI 1.36 to 2.22, p < 0.001), but not PLR (p = 0.11), were significantly associated with disease progression and mortality. Between-study heterogeneity was large-to-extreme. The magnitude and direction of the effect size were not modified in sensitivity analysis. CONCLUSIONS NLR and neutrophil, lymphocyte, and platelet count significantly discriminate COVID-19 patients with different progression and survival outcomes. (PROSPERO registration number: CRD42021267875).
Collapse
Affiliation(s)
- Angelo Zinellu
- Department of Biomedical Sciences, University of Sassari, Sassari, Italy
| | - Arduino A Mangoni
- Discipline of Clinical Pharmacology, College of Medicine and Public Health, Flinders University, Adelaide, Australia.,Department of Clinical Pharmacology, Flinders Medical Centre, Southern Adelaide Local Health Network, Adelaide, Australia
| |
Collapse
|
5
|
Zang X, Xiong L, Zhu J, Zhao F, Wang S, Zeng W, Yu K, Zhai Y. The Value of Early Positive Nucleic Acid Test and Negative Conversion Time of SARS-CoV-2 RNA in the Clinical Outcome of COVID-19 Patients. Front Med (Lausanne) 2022; 9:826900. [PMID: 35572983 PMCID: PMC9095906 DOI: 10.3389/fmed.2022.826900] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2021] [Accepted: 03/31/2022] [Indexed: 11/25/2022] Open
Abstract
Background The outbreak of coronavirus disease (COVID-19) poses a great threat to global public health. At present, the number of newly confirmed COVID-19 cases and deaths is increasing worldwide. The strategy of comprehensive and scientific detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) through quantitative real-time polymerase chain reaction (qRT-PCR) for special populations and environments provides great support for the prevention and control of this pandemic in China. Our study focused on determining the factors associated with the length of time from symptom onset to the first positive nucleic acid test of throat swabs in COVID-19 patients, evaluating the effect of early positive nucleic acid detection on the disease severity and its significance in prognosis, and predicting the factors associated with the time from positive SARS-CoV-2 RNA test to negative conversion (negative conversion of SARS-CoV-2 virus) in COVID-19 patients. Methods This study included 116 hospitalized patients with COVID-19 from January 30, 2020 to March 4, 2020 in Wuhan, China. Throat swab samples were collected for qRT-PCR testing of SARS-CoV-2 RNA, and all patients included in this study were positive for this test. Results The multivariate Cox proportional hazards model showed that disease severity (HR = 0.572; 95% CI 0.348–0.942; p = 0.028) was a protective factor for the time from symptom onset to positive nucleic acid detection. Meanwhile, the time from symptom onset to positive nucleic acid detection (HR = 1.010; 95% CI 1.005–1.020; p = 0.0282) was an independent risk factor for the delay in negative conversion time of SARS-CoV-2 virus. However, the severity of the disease (HR=1.120; 95% CI 0.771–1.640; p = 0.544) had no correlation with the negative conversion time of SARS-CoV-2 virus. Conclusions Patients with more severe disease had a shorter time from symptom onset to a positive nucleic acid test. Prolonged time from symptom onset to positive nucleic acid test was an independent risk factor for the delay in negative conversion time of SARS-CoV-2 virus, and the severity of the disease had no correlation with negative conversion time of SARS-CoV-2 virus.
Collapse
Affiliation(s)
- Xin Zang
- Department of Infectious Disease, Shengjing Hospital of China Medical University, Shenyang, China
| | - Liangkun Xiong
- Department of Hepatobiliary Surgery, Renmin Hospital of Wuhan University, Wuhan, China
| | - Junyao Zhu
- Department of Infectious Disease, Shengjing Hospital of China Medical University, Shenyang, China
| | - Fangfang Zhao
- Department of Infectious Disease, Fujian Medical University Affiliated First Quanzhou Hospital, Quanzhou, China
| | - Shihong Wang
- Department of Paediatrics, Renmin Hospital of Wuhan University, Wuhan, China
| | - Wenhui Zeng
- Department of Hepatobiliary Surgery, Renmin Hospital of Wuhan University, Wuhan, China
| | - Kaihuan Yu
- Department of Hepatobiliary Surgery, Renmin Hospital of Wuhan University, Wuhan, China
- *Correspondence: Kaihuan Yu
| | - Yongzhen Zhai
- Department of Infectious Disease, Shengjing Hospital of China Medical University, Shenyang, China
- Yongzhen Zhai
| |
Collapse
|
6
|
Ligotti ME, Pojero F, Accardi G, Aiello A, Caruso C, Duro G, Candore G. Immunopathology and Immunosenescence, the Immunological Key Words of Severe COVID-19. Is There a Role for Stem Cell Transplantation? Front Cell Dev Biol 2021; 9:725606. [PMID: 34595175 PMCID: PMC8477205 DOI: 10.3389/fcell.2021.725606] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2021] [Accepted: 08/06/2021] [Indexed: 01/08/2023] Open
Abstract
The outcomes of Coronavirus disease-2019 (COVID-19) vary depending on the age, health status and sex of an individual, ranging from asymptomatic to lethal. From an immunologic viewpoint, the final severe lung damage observed in COVID-19 should be caused by cytokine storm, driven mainly by interleukin-6 and other pro-inflammatory cytokines. However, which immunopathogenic status precedes this "cytokine storm" and why the male older population is more severely affected, are currently unanswered questions. The aging of the immune system, i.e., immunosenescence, closely associated with a low-grade inflammatory status called "inflammageing," should play a key role. The remodeling of both innate and adaptive immune response observed with aging can partly explain the age gradient in severity and mortality of COVID-19. This review discusses how aging impacts the immune response to the virus, focusing on possible strategies to rejuvenate the immune system with stem cell-based therapies. Indeed, due to immunomodulatory and anti-inflammatory properties, multipotent mesenchymal stem cells (MSCs) are a worth-considering option against COVID-19 adverse outcomes.
Collapse
Affiliation(s)
- Mattia Emanuela Ligotti
- Laboratory of Immunopathology and Immunosenescence, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy
- Institute for Biomedical Research and Innovation, National Research Council of Italy, Palermo, Italy
| | - Fanny Pojero
- Laboratory of Immunopathology and Immunosenescence, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy
| | - Giulia Accardi
- Laboratory of Immunopathology and Immunosenescence, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy
| | - Anna Aiello
- Laboratory of Immunopathology and Immunosenescence, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy
| | - Calogero Caruso
- Laboratory of Immunopathology and Immunosenescence, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy
- International Society on Aging and Disease, Fort Worth, TX, United States
| | - Giovanni Duro
- Institute for Biomedical Research and Innovation, National Research Council of Italy, Palermo, Italy
| | - Giuseppina Candore
- Laboratory of Immunopathology and Immunosenescence, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy
| |
Collapse
|