1
|
Fang C, Yan W, Chen Y, Dou Z, Liu T, Luo F, Chen W, Li X, Chen Y, Wu W, Yuan Z, Niu Y, Wang P, Zhu W, Luo X, Chen T, Bai X, Wang X, Ning Q. Long-term SARS-CoV-2 neutralizing antibody level prediction using multimodal deep learning: A prospective cohort study on longitudinal data in Wuhan, China. J Med Virol 2023; 95:e29036. [PMID: 37621210 DOI: 10.1002/jmv.29036] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2023] [Revised: 07/07/2023] [Accepted: 08/02/2023] [Indexed: 08/26/2023]
Abstract
The ongoing epidemic of SARS-CoV-2 is taking a substantial financial and health toll on people worldwide. Assessing the level and duration of SARS-CoV-2 neutralizing antibody (Nab) would provide key information for government to make sound healthcare policies. Assessed at 3-, 6-, 12-, and 18-month postdischarge, we described the temporal change of IgG levels in 450 individuals with moderate to critical COVID-19 infection. Moreover, a data imputation framework combined with a novel deep learning model was implemented to predict the long-term Nab and IgG levels in these patients. Demographic characteristics, inspection reports, and CT scans during hospitalization were used in this model. Interpretability of the model was further validated with Shapely Additive exPlanation (SHAP) and Gradient-weighted Class Activation Mapping (GradCAM). IgG levels peaked at 3 months and remained stable in 12 months postdischarge, followed by a significant decline in 18 months postdischarge. However, the Nab levels declined from 6 months postdischarge. By training on the cohort of 450 patients, our long-term antibody prediction (LTAP) model could predict long-term IgG levels with relatively high area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1-score, which far exceeds the performance achievable by commonly used models. Several prognostic factors including FDP levels, the percentages of T cells, B cells and natural killer cells, older age, sex, underlying diseases, and so forth, served as important indicators for IgG prediction. Based on these top 15 prognostic factors identified in IgG prediction, a simplified LTAP model for Nab level prediction was established and achieved an AUC of 0.828, which was 8.9% higher than MLP and 6.6% higher than LSTM. The close correlation between IgG and Nab levels making it possible to predict long-term Nab levels based on the factors selected by our LTAP model. Furthermore, our model identified that coagulation disorders and excessive immune response, which indicate disease severity, are closely related to the production of IgG and Nab. This universal model can be used as routine discharge tests to identify virus-infected individuals at risk for recurrent infection and determine the optimal timing of vaccination for general populations.
Collapse
Affiliation(s)
- Cong Fang
- School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
| | - Weiming Yan
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Yuying Chen
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Zhiyong Dou
- School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
| | - Tingting Liu
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Fengning Luo
- Department of Computer Science, University of Toronto, Toronto, Canada
| | - Weiwei Chen
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xitang Li
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Yajie Chen
- School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
| | - Wenhui Wu
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Zhize Yuan
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Yuxin Niu
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Peng Wang
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Wenzhen Zhu
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaoping Luo
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department of Pediatrics, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Tao Chen
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiang Bai
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaojing Wang
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Qin Ning
- State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Department and Institute of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|
2
|
Maki FM, Al-Thwani AN, Jiad KS, Musafer KNJ. Immunoglobulin G follow-up and immune response longevity analysis in SARS-CoV-2 convalescent patients and vaccinated individuals: A longitudinal analysis. Hum Antibodies 2023:HAB230004. [PMID: 37334588 DOI: 10.3233/hab-230004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/20/2023]
Abstract
BACKGROUND Although the detection of immunoglobulin G (IgG) molecules has long been considered to be crucial for successful humoral immune defence against infections and harmful metabolites, it has become increasingly important in relation to SARS-CoV-2 research. OBJECTIVE To compare longitudinal changes in IgG titres in post-infection and post-vaccination Iraqi participants, and to estimate the protective benefits of the two principal vaccines used in Iraq. METHODS This quantitative study used samples from SARS-CoV-2 recovered patients (n= 75), those vaccinated with two doses of Pfizer or Sinopharm vaccine (n= 75), and healthy unvaccinated individuals (n= 50) who formed a control group. Participant ages (range 20-80 years) and sex (52.7% men, 47.3% females). An enzyme-linked immunosorbent assay was used to measure IgG. RESULTS IgG antibody levels peaked in the first month and tapered off in the following three months in both convalescent and vaccinated groups. The latter showed a significant decrease in IgG titres than in the convalescent group. Samples from the group given the mRNA vaccination that targeted spike (S) proteins might have a cross-reactivity between nucleocapsid (N) and spike (S) proteins. CONCLUSIONS Participants who had recovered from or who were vaccinated against SARS-CoV-2 exhibited a protective, persistent and durable humoral immune response for at least a month. This was more potent in the SARS-CoV-2 convalescent group compared to the vaccinated cohort. The IgG titres decayed faster after vaccination with Sinopharm than following the Pfizer-BioNTech vaccine.
Collapse
Affiliation(s)
- Fadia Mothafar Maki
- Genetic Engineering and Biotechnology Institute, University of Baghdad, Baghdad, Iraq
| | - Anima Namma Al-Thwani
- Genetic Engineering and Biotechnology Institute, University of Baghdad, Baghdad, Iraq
| | | | | |
Collapse
|
3
|
Łysek-Gładysińska M, Starz M, Borowiec-Sęk A, Sufin I, Wieczorek A, Chrapek M, Zarębska-Michaluk D, Sufin P, Głuszek S, Adamus-Białek W. The Levels of Anti-SARS-CoV-2 Spike Protein IgG Antibodies Before and After the Third Dose of Vaccination Against COVID-19. J Inflamm Res 2023; 16:145-160. [PMID: 36660373 PMCID: PMC9843475 DOI: 10.2147/jir.s394760] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Accepted: 12/21/2022] [Indexed: 01/12/2023] Open
Abstract
Purpose The COVID-19 pandemic has been going on for almost three years, and so far, many preventive and therapeutic strategies have been developed. The issue of subsequent booster vaccinations is currently being discussed. We aimed to analyze how the third dose of vaccination against COVID-19 correlates with the dynamics of IgG anti-SARS-CoV-2 spike protein antibody levels in a group of healthy people. Patients and Methods The prospective study included 93 participants before and after a second booster of COVID-19 vaccination, from whom 4 blood samples were collected at intervals. The levels of IgG anti-SARS-CoV-2 in serum were identified using the chemiluminescent immunoassay specific for the receptor-binding domain (RBD) of the S1 protein. The analysis of the results was performed using appropriate statistical methods, considering p <0.05 as a statistically significant value. Results The IgG levels were significantly higher and less diverse after the same follow-up time from the second booster vaccination compared to the first booster. The antibody levels were positively correlated with female, healthcare workers, the elderly and participants with a negative COVID-19 history. Furthermore, the increase in IgG antibodies after the second booster vaccination correlated inversely with the baseline level of antibodies before the vaccination. The latest results showed that antibody levels dropped 1.5-fold after approx. 10 months from the second booster vaccination but still remained at a protective level. Conclusion Booster vaccinations seem to better stimulate immune memory, and in the case of borderline IgG level induces the greatest increase in antibodies. It is worth considering the individual parameters of patients and measuring antibodies before vaccination.
Collapse
Affiliation(s)
| | | | | | | | - Anna Wieczorek
- Institute of Biology, Jan Kochanowski University, Kielce, Poland
| | - Magdalena Chrapek
- Department of Mathematics, Jan Kochanowski University, Kielce, Poland
| | | | | | - Stanisław Głuszek
- Institute of Medical Sciences, Jan Kochanowski University, Kielce, Poland
| | - Wioletta Adamus-Białek
- Institute of Medical Sciences, Jan Kochanowski University, Kielce, Poland,Correspondence: Wioletta Adamus-Białek, Jan Kochanowski University, Institute of Medical Sciences, IX Wieków Kielc 19a, Kielce, 25-516, Poland, Tel +48 788 860 604, Email
| |
Collapse
|
4
|
Hopkins FR, Govender M, Svanberg C, Nordgren J, Waller H, Nilsdotter-Augustinsson Å, Henningsson AJ, Hagbom M, Sjöwall J, Nyström S, Larsson M. Major alterations to monocyte and dendritic cell subsets lasting more than 6 months after hospitalization for COVID-19. Front Immunol 2023; 13:1082912. [PMID: 36685582 PMCID: PMC9846644 DOI: 10.3389/fimmu.2022.1082912] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Accepted: 12/05/2022] [Indexed: 01/06/2023] Open
Abstract
Introduction After more than two years the Coronavirus disease-19 (COVID-19) pandemic continues to burden healthcare systems and economies worldwide, and it is evident that the effects on the immune system can persist for months post-infection. The activity of myeloid cells such as monocytes and dendritic cells (DC) is essential for correct mobilization of the innate and adaptive responses to a pathogen. Impaired levels and responses of monocytes and DC to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is likely to be a driving force behind the immune dysregulation that characterizes severe COVID-19. Methods Here, we followed a cohort of COVID-19 patients hospitalized during the early waves of the pandemic for 6-7 months. The levels and phenotypes of circulating monocyte and DC subsets were assessed to determine both the early and long-term effects of the SARS-CoV-2 infection. Results We found increased monocyte levels that persisted for 6-7 months, mostly attributed to elevated levels of classical monocytes. Myeloid derived suppressor cells were also elevated over this period. While most DC subsets recovered from an initial decrease, we found elevated levels of cDC2/cDC3 at the 6-7 month timepoint. Analysis of functional markers on monocytes and DC revealed sustained reduction in program death ligand 1 (PD-L1) expression but increased CD86 expression across almost all cell types examined. Finally, C-reactive protein (CRP) correlated positively to the levels of intermediate monocytes and negatively to the recovery of DC subsets. Conclusion By exploring the myeloid compartments, we show here that alterations in the immune landscape remain more than 6 months after severe COVID-19, which could be indicative of ongoing healing and/or persistence of viral antigens.
Collapse
Affiliation(s)
- Francis R. Hopkins
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| | - Melissa Govender
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| | - Cecilia Svanberg
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| | - Johan Nordgren
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| | - Hjalmar Waller
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| | - Åsa Nilsdotter-Augustinsson
- Division of Infection and Inflammation, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
- Department of Infectious Diseases, Linköping University, Linköping, Sweden
| | - Anna J. Henningsson
- Division of Infection and Inflammation, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
- Division of Clinical Microbiology, Department of Laboratory Medicine in Jönköping, Ryhov County Hospital, Jönköping, Sweden
| | - Marie Hagbom
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| | - Johanna Sjöwall
- Division of Infection and Inflammation, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
- Department of Infectious Diseases, Linköping University, Linköping, Sweden
| | - Sofia Nyström
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
- Department of Clinical Immunology and Transfusion Medicine, Linköping University, Linköping, Sweden
| | - Marie Larsson
- Division of Molecular Medicine and Virology, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, Sweden
| |
Collapse
|