1
|
Jiang X, Yang D, Feng L, Zhu Y, Wang M, Feng Y, Bai C, Fang H. Contrastive learning with token projection for Omicron pneumonia identification from few-shot chest CT images. Front Med (Lausanne) 2024; 11:1360143. [PMID: 38756944 PMCID: PMC11096503 DOI: 10.3389/fmed.2024.1360143] [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: 12/22/2023] [Accepted: 04/05/2024] [Indexed: 05/18/2024] Open
Abstract
Introduction Deep learning-based methods can promote and save critical time for the diagnosis of pneumonia from computed tomography (CT) images of the chest, where the methods usually rely on large amounts of labeled data to learn good visual representations. However, medical images are difficult to obtain and need to be labeled by professional radiologists. Methods To address this issue, a novel contrastive learning model with token projection, namely CoTP, is proposed for improving the diagnostic quality of few-shot chest CT images. Specifically, (1) we utilize solely unlabeled data for fitting CoTP, along with a small number of labeled samples for fine-tuning, (2) we present a new Omicron dataset and modify the data augmentation strategy, i.e., random Poisson noise perturbation for the CT interpretation task, and (3) token projection is utilized to further improve the quality of the global visual representations. Results The ResNet50 pre-trained by CoTP attained accuracy (ACC) of 92.35%, sensitivity (SEN) of 92.96%, precision (PRE) of 91.54%, and the area under the receiver-operating characteristics curve (AUC) of 98.90% on the presented Omicron dataset. On the contrary, the ResNet50 without pre-training achieved ACC, SEN, PRE, and AUC of 77.61, 77.90, 76.69, and 85.66%, respectively. Conclusion Extensive experiments reveal that a model pre-trained by CoTP greatly outperforms that without pre-training. The CoTP can improve the efficacy of diagnosis and reduce the heavy workload of radiologists for screening of Omicron pneumonia.
Collapse
Affiliation(s)
- Xiaoben Jiang
- School of Information Science and Technology, East China University of Science and Technology, Shanghai, China
| | - Dawei Yang
- Department of Pulmonary and Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, China
- Shanghai Engineering Research Center of Internet of Things for Respiratory Medicine, Shanghai, China
- Department of Pulmonary and Critical Care Medicine, Zhongshan Hospital (Xiamen), Fudan University, Xiamen, Fujian, China
| | - Li Feng
- Department of Nursing, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Yu Zhu
- School of Information Science and Technology, East China University of Science and Technology, Shanghai, China
| | - Mingliang Wang
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Yinzhou Feng
- Department of Pulmonary and Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Chunxue Bai
- Department of Pulmonary and Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, China
- Shanghai Engineering Research Center of Internet of Things for Respiratory Medicine, Shanghai, China
| | - Hao Fang
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China
- Department of Anesthesiology, Shanghai Geriatric Medical Center, Shanghai, China
| |
Collapse
|
2
|
Yu X, Li X, Xia S, Lu T, Zong M, Suo C, Man Q, Xiong L. Development and validation of a prognostic model based on clinical laboratory biomarkers to predict admission to ICU in Omicron variant-infected hospitalized patients complicated with myocardial injury. Front Immunol 2024; 15:1268213. [PMID: 38361939 PMCID: PMC10868580 DOI: 10.3389/fimmu.2024.1268213] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Accepted: 01/03/2024] [Indexed: 02/17/2024] Open
Abstract
Aims The aim of this study was to develop and validate a prognostic model based on clinical laboratory biomarkers for the early identification of high-risk patients who require intensive care unit (ICU) admission among those hospitalized with the Omicron variant of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and complicated with myocardial injury (MI). Methods This single-center study enrolled 263 hospitalized patients with confirmed Omicron variant infection and concurrent MI. The patients were randomly divided into training and validation cohorts. Relevant variables were collected upon admission, and the least absolute shrinkage and selection operator (LASSO) was used to select candidate variables for constructing a Cox regression prognostic model. The model's performance was evaluated in both training and validating cohorts based on discrimination, calibration, and net benefit. Results Of the 263 eligible patients, 210 were non-ICU patients and 53 were ICU patients. The prognostic model was built using four selected predictors: white blood cell (WBC) count, procalcitonin (PCT) level, C-reactive protein (CRP) level, and blood urea nitrogen (BUN) level. The model showed good discriminative ability in both the training cohort (concordance index: 0.802, 95% CI: 0.716-0.888) and the validation cohort (concordance index: 0.799, 95% CI: 0.681-0.917). For calibration, the predicted probabilities and observed proportions were highly consistent, indicating the model's reliability in predicting outcomes. In the 21-day decision curve analysis, the model had a positive net benefit for threshold probability ranges of 0.2 to 0.8 in the training cohort and nearly 0.2 to 1 in the validation cohort. Conclusion In this study, we developed a clinically practical model with high discrimination, calibration, and net benefit. It may help to early identify severe and critical cases among Omicron variant-infected hospitalized patients with MI.
Collapse
Affiliation(s)
- Xueying Yu
- Department of Clinical Laboratory, Shanghai Fourth People’s Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Xiaoguang Li
- Department of Thyroid, Breast and Vascular Surgery, Shanghai Fourth People’s Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Shuai Xia
- Key Laboratory of Medical Molecular Virology (Ministry of Education/National Health Commission/Chinese Academy of Medical Sciences, MOE/NHC/CAMS), Shanghai Institute of Infectious Disease and Biosecurity, School of Basic Medical Sciences, Shanghai Frontiers Science Center of Pathogenic Microbes and Infection, Fudan University, Shanghai, China
| | - Tianyu Lu
- Key Laboratory of Medical Molecular Virology (Ministry of Education/National Health Commission/Chinese Academy of Medical Sciences, MOE/NHC/CAMS), Shanghai Institute of Infectious Disease and Biosecurity, School of Basic Medical Sciences, Shanghai Frontiers Science Center of Pathogenic Microbes and Infection, Fudan University, Shanghai, China
| | - Ming Zong
- Department of Clinical Laboratory, Shanghai Fourth People’s Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Chen Suo
- Department of Epidemiology and Ministry of Education Key Laboratory of Public Health Safety, School of Public Health, Fudan University, Shanghai, China
| | - Qiuhong Man
- Department of Clinical Laboratory, Shanghai Fourth People’s Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Lize Xiong
- Shanghai Key Laboratory of Anesthesiology and Brain Functional Modulation, Clinical Research Center for Anesthesiology and Perioperative Medicine, Translational Research Institute of Brain and Brain-Like Intelligence, Shanghai Fourth People’s Hospital, School of Medicine, Tongji University, Shanghai, China
| |
Collapse
|
3
|
Yan W, Shang Z, Wu L, Lv H, Jia Y, Zhan J, Wang J, Ouyang H, Liu W, Chen W. The impact of isolation on comorbidity of PTSD symptoms and depression: evidence from PTRP-5-6 in China. BMC Public Health 2024; 24:21. [PMID: 38166952 PMCID: PMC10762958 DOI: 10.1186/s12889-023-17450-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Accepted: 12/11/2023] [Indexed: 01/05/2024] Open
Abstract
BACKGROUND The Omicron pandemic struck Shanghai, China, resulting in impairments of both physical and psychological health on those patients who were confirmed and transferred to the Fangcang shelters. The way of isolation led to high risk of posttraumatic stress symptoms (PTSS) and depressive symptoms among the patients in Fangcang shelters. We aim to estimate the prevalence and comorbidity of PTSS and depressive symptoms in patients from China's Fangcang shelters during the epidemic. METHODS Demographic information questionnaire, the posttraumatic stress disorder checklist for DSM-5 (PCL-5), and Patient Health Questionnaire (PHQ-9) were used in the study. The data were collected online via mobile phones during 10th April to 20th April, 2022, as part of our Psychological Trauma Recover Project-5-6 (PTRP-5-6), a longitudinal study focusing on individuals who have experienced trauma. RESULTS A total of 336 subjects were included in the analysis. The results revealed (1) the prevalence of depressive symptoms, and PTSS were 30.1% (cut-off = 10) and 6% (cut-off = 33); (2) Multiple logistic regression showed that female (OR = 3.04, p < 0.05), suffering from dyspnea (OR = 5.83, p < 0.05) or gastrointestinal symptoms (OR = 6.38, p < 0.05) were risk factors for PTSS; higher education level (OR = 3.27, p < 0.05) and suffering from dizziness or headache (OR = 2.46, p < 0.05) were risk factors for depressive symptoms; (3)Respectively, 85% of the patients who reported PTSS also experienced depressive symptoms, 16.8% of the patients who reported depressive symptoms presented PTSS. CONCLUSION In the context of COVID-19, the comorbidity rate of PTSS and depressive symptoms among patients in Fangcang shelters increased with the severity of depressive symptoms.
Collapse
Affiliation(s)
- Wenjie Yan
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China
| | - Zhilei Shang
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China
| | - Lili Wu
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China
| | - Hongli Lv
- Department of Gastroenterology and Hepatology, Jinling Hospital, Clinical School of Medical College, Nanjing University, Nanjing, 210000, P. R. China
| | - Yanpu Jia
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China
| | - Jingye Zhan
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China
| | - Jing Wang
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China
| | - Hui Ouyang
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China.
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China.
| | - Weizhi Liu
- Lab for Post-traumatic Stress Disorder, Faculty of Psychology and Mental Health, Naval Medical University, 800 Xiangyin Road, Shanghai, 200433, China.
- The Emotion & Cognition Lab, Faculty of Psychology and Mental Health, Naval Medical University, Shanghai, 200433, China.
| | - Wenfang Chen
- Department of Urology, Jinling Hospital, Clinical School of Medical College, Nanjing University, 305 East Zhongshan Road, Nanjing, 210000, P. R. China.
| |
Collapse
|
4
|
Li R, Jin C, Zhang L, Kong D, Hu K, Xuan M, Liu Q, Li S, Zhang K, Xue Y. Clinical characteristics and risk factors analysis of viral shedding time in mildly symptomatic and asymptomatic patients with SARS-CoV-2 Omicron variant infection in Shanghai. Front Public Health 2023; 10:1073387. [PMID: 36684919 PMCID: PMC9845758 DOI: 10.3389/fpubh.2022.1073387] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2022] [Accepted: 12/08/2022] [Indexed: 01/06/2023] Open
Abstract
Objective To analyze the clinical characteristics and risk factors of viral shedding time in mildly symptomatic and asymptomatic patients with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Omicron variant (BA.2 and BA2.2) infection in Shanghai, and the effect of traditional Chinese medicine (TCM) treatment, so as to provide a reference basis for epidemic prevention, control and clinical treatment. Methods A total of 6,134 asymptomatic or mildly symptomatic Omicron-infected patients admitted to Tianhua Road fangcang shelter hospital in Jinshan, Shanghai, between April 2022 and May 2022 were included. Demographic characteristics and clinical histories were collected and compared in subgroups according to the different durations of viral shedding. Spearman's correlation analysis was performed to explore the association between virus shedding time and clinical variables. Multiple linear regression was used to evaluate the risk factors for viral shedding time. Result Most patients with asymptomatic and mildly symptomatic Omicron infection were male, and more than half of patients had a viral shedding time of 8-15 days. The patients were divided into three groups according to the time of viral shedding: short-duration (≤ 7 days), intermediate-duration (8-15 days) and long-duration group (≥16 days). The proportion of patients aged ≤ 29 years was the highest in the short-duration group (30.2%), whereas the proportion of patients aged 50-64 yeas was the highest in the long-duration group (37.9%). The proportion of patients with the chronic non-communicable diseases among the short-, intermediate- and long-duration groups was 6.2, 9.4, and 14.9%, respectively. Among them, hypertension was the most found (4.9, 7.8, and 11.7%, respectively). By multivariate analyses, we identified that viral shedding time of Omicron variants was independently negatively correlated with male patients, TCM treatment, and manual laborers, while it was independently positively associated with age and hypertension. Additionally, TCM treatment could significantly shorten the length of viral shedding time, especially for men, age ≥30 years, comorbid chronic non-communicable diseases, unemployed people and manual worker. Conclusions Our results suggested that age and hypertension were independent risk factors for the duration of viral shedding in asymptomatic and mildly symptomatic omicron infected patients. TCM can effectively shorten viral shedding time.
Collapse
Affiliation(s)
- Ran Li
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Chen Jin
- Department of Orthopedics, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Liya Zhang
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Dehong Kong
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Kerong Hu
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Miao Xuan
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Qi Liu
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Shaohui Li
- Department of Otorhinolaryngology - Head and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Keqin Zhang
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Ying Xue
- Department of Endocrinology and Metabolism, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| |
Collapse
|
5
|
Liu D, Zhang Y, Chen D, Wang X, Huang F, Long L, Zheng X. Evaluation of the presence of SARS-CoV-2 in vaginal and anal swabs of women with omicron variants of SARS-CoV-2 infection. Front Microbiol 2022; 13:1035359. [DOI: 10.3389/fmicb.2022.1035359] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Accepted: 10/20/2022] [Indexed: 11/11/2022] Open
Abstract
ObjectivesThe study aimed to determine whether SARS-CoV-2 Omicron variant could be detected in the vaginal fluid and anal swabs of reproductive-aged and postmenopausal women infected with SARS-CoV-2 Omicron variant.MethodsIncluded in this study were 63 women who were laboratory confirmed as having SARS-CoV-2 Omicron variant infection and admitted to the responsible ward of Daping Hospital of at the National Exhibition and Convention Center(Shanghai) Makeshift Hospital from May 1–24, 2022.From them, vaginal and anal swabs were obtained with informed consent. The demographic and baseline clinical characteristics and the swab test results were analyzed.ResultsThe 63 included patients ranged in age from 18 to 72 years with a median of 47.71 ± 15.21 years. Of them, 38 women (60.3%) were in their reproductive years. Most of the participants (77.8%) were healthy without significant underlying diseases. Fourteen patients (22.2%) had asymptomatic infection and the remaining 49 (77.8%) had mild infection. The upper respiratory tract symptoms including cough (40/63.5%) and sore throat (18/28.6%)were the most common clinical manifestations of these mildly infected patients. Only 5 patients (7.8%) had gastrointestinal (GI) symptoms, including simple diarrhea in 4 patients, and diarrhea with vomiting in one patient. Pharyngeal,vaginal and anal swabs were collected simultaneously from all 63 patients 8–16 (mean 11.25 ± 2.23) days after SARS-Cov-2 Omicron variant infection. The vaginal swabs were negative for SARS-CoV-2 in all 63 patients, and the anal swabs were positive in 4 patients (6.5%). The overall median hospitalization duration was 16.73 ± 3.16 days.ConclusionThe results of the present study suggest that there is a low possibility of SARS-Cov-2 Omicron variant transmission via the digestive tract and vaginal fluid. The correlation between the GI symptoms and the presence of viral RNA in anal swabs is uncertain.
Collapse
|
6
|
Mechanisms of Estrogen Influence on Skeletal Muscle: Mass, Regeneration, and Mitochondrial Function. Sports Med 2022; 52:2853-2869. [PMID: 35907119 DOI: 10.1007/s40279-022-01733-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/24/2022] [Indexed: 10/16/2022]
Abstract
Human menopause is widely associated with impaired skeletal muscle quality and significant metabolic dysfunction. These observations pose significant challenges to the quality of life and mobility of the aging population, and are of relevance when considering the significantly greater losses in muscle mass and force-generating capacity of muscle from post-menopausal females relative to age-matched males. In this regard, the influence of estrogen on skeletal muscle has become evident across human, animal, and cell-based studies. Beneficial effects of estrogen have become apparent in mitigation of muscle injury and enhanced post-damage repair via various mechanisms, including prophylactic effects on muscle satellite cell number and function, as well as membrane stability and potential antioxidant influences following injury, exercise, and/or mitochondrial stress. In addition to estrogen replacement in otherwise deficient states, exercise has been found to serve as a means of augmenting and/or mimicking the effects of estrogen on skeletal muscle function in recent literature. Detailed mechanisms behind the estrogenic effect on muscle mass, strength, as well as the injury response are beginning to be elucidated and point to estrogen-mediated molecular cross talk amongst signalling pathways, such as apoptotic signaling, contractile protein modifications, including myosin regulatory light chain phosphorylation, and the maintenance of muscle satellite cells. This review discusses current understandings and highlights new insights regarding the role of estrogen in skeletal muscle, with particular regard to muscle mass, mitochondrial function, the response to muscle damage, and the potential implications for human physiology and mobility.
Collapse
|