The pattern from the first three rounds of vaccination: declining vaccination rates.

Introduction: Vaccination rates for the COVID-19 vaccine have recently been stagnant worldwide. We aim to analyze the potential patterns of vaccination development from the first three doses to reveal the possible trends of the next round of vaccination and further explore the factors influencing vaccination in the selected populations. Methods: On July 2022, a stratified multistage random sampling method in the survey was conducted to select 6,781 people from 4 provinces China, who were above the age of 18 years. Participants were divided into two groups based on whether they had a chronic disease. The data were run through Cochran-Armitage trend test and multivariable regression analyses. Results: A total of 957 participants with chronic disease and 5,454 participants without chronic disease were included in this survey. Vaccination rates for the first, second and booster doses in chronic disease population were93.70% (95% CI: 92.19-95.27%), 91.12% (95%CI: 94.43-95.59%), and 83.18% (95%CI: 80.80-85.55%) respectively. By contrast, the first, second and booster vaccination rates for the general population were 98.02% (95% CI: 97.65-98.39%), 95.01% (95% CI: 94.43-95.59%) and 85.06% (95% CI: 84.11-86.00%) respectively. The widening gap in vaccination rates was observed as the number of vaccinations increases. Higher self-efficacy was a significant factor in promoting vaccination, which has been observed in all doses of vaccines. Higher education level, middle level physical activity and higher public prevention measures play a positive role in vaccination among the general population, while alcohol consumption acts as a significant positive factor in the chronic disease population (p < 0.05). Conclusion: As the number of vaccinations increases, the trend of decreasing vaccination rate is becoming more pronounced. In future regular vaccinations, we may face low vaccination rates as the increasing number of infections and the fatigue associated with the prolonged outbreak hamper vaccination. Measures need to be found to counter this downward trend such as improving the self-efficacy of the population.

Clinical observation of neutralizing antibody DXP-604 for treatment critical COVID-19 patients infected with SARS-CoV-2 Delta variant.

From January to March 2022, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Delta (B.1.617.2) infection was prevalent in Yuzhou and Zhengzhou. DXP-604 is a broad-spectrum antiviral monoclonal antibody, which has excellent viral neutralization ability in vitro and a long half-life in vivo, with good biosafety and tolerability. Preliminary results showed that DXP-604 can accelerate recovery from Coronavirus disease 2019 (COVID-19) caused by SARS-CoV-2 Delta variant in hospitalized patients with mild to moderate clinical symptoms. However, the efficacy of DXP-604 has not been fully studied in high-risk severe patients. Here, we prospectively enrolled 27 high-risk patients, two groups were divided, in addition to receiving standard of care (SOC), 14 of them additionally received the neutralizing antibody DXP-604 therapy, and another 13 intensive care unit (ICU) patients simultaneously underwent SOC as a control group matched for age, gender, and clinical type. The results revealed lower C-reactive protein, interleukin-6, lactic dehydrogenase and neutrophil counts, and higher lymphocyte and monocyte counts from Day 3 post-DXP-604 treatment compared with SOC treatment. Besides, thoracic CT images showed improvements in lesion areas and degrees, along with changes in blood inflammatory factors. Moreover, DXP-604 reduced the invasive mechanical ventilation and mortality of high-risk SARS-CoV-2 infected patients. The ongoing clinical trials of DXP-604 neutralizing antibody will clarify its utility as a new attractive countermeasure for high-risk COVID-19.

An Unusual Case of Systemic Lymphadenopathy - Kimura's Disease.

Background: Kimura's disease (KD) is a rare, chronic inflammatory disease. Clinically, subcutaneous nodules of the head and neck are typical manifestations, often accompanied by local lymphadenopathy or salivary gland enlargement, but there is also systemic damage, such as kidney involvement. Due to the lack of specific markers and imaging examination is not specific, it is difficult to clinically diagnose accurately and can be easy to misdiagnose. The treatment of KD is still not standardized and overtreatment can affect the quality of life. Case Presentation: The case of a 26-year-old man complaining of chest pain with self-conscious progressive lymphadenopathy after receiving Pfizer BioNTech COVID-19 vaccine for more than 1 month is presented. Eosinophil levels were normal and IgE elevated and the final diagnosis of KD was eventually confirmed by lymph node biopsy, which revealed lymphadenopathy with extensive eosinophilic infiltration in the right neck. Treatment was prednisone combined with methotrexate, resulting in satisfactory control. Conclusion: This case demonstrates that that Kimura disease can involve systemic lymphadenopathy, not only in the head and face or regional lymphadenopathy, suggested that KD should be excluded in patients with systemic lymphadenopathy. The current patient's response to treatment suggested that corticosteroid combined with disease-modifying antirheumatic drugs (DENARDs) was a promising treatment for KD patients with systemic damage. It is worth noting that the mechanism of immunity in the pathogenesis of KD still needs to be further studied.

How urban versus rural residency relates to COVID-19 vaccine hesitancy: A large-scale national Chinese study.

RATIONALE: Although urban-rural residency has been shown to influence individual COVID-19 vaccine hesitancy, the differences between urban and rural China have yet to be uncovered. OBJECTIVE: This study aims to assess the current prevalence and factors associated with COVID-19 vaccine hesitancy in urban and rural areas and explore whether the rural versus urban residency is associated with COVID-19 vaccine hesitancy. METHODS: A national, cross-sectional, online survey among Chinese urban and rural adults (≥18 years old) was conducted from 6th to August 9, 2021. A questionnaire was used to collect data on sociodemographic factors, perceptions of the COVID-19 pandemic and vaccination status. A multivariable logistic regression model was used to identify the factors that influence COVID-19 vaccine hesitancy. Propensity score matching (PSM) analysis was performed to explore the association between urban versus rural residency and COVID-19 vaccine hesitancy. RESULTS: In total, 29,925 participants (80.56% urban participants) were recruited. Urban participants had a higher COVID-19 vaccine hesitancy than their rural counterparts (9.39% vs. 4.26%). After adjusting for potential confounders, we found that COVID-19 vaccine hesitancy among females was lower than that in males in both urban (aOR = 0.78, 95% CI [0.69-0.88]) and rural areas (aOR = 0.54, 95% CI [0.39-0.75]). The lack of trust towards vaccine producers was found to be associated with vaccine hesitancy among the urban participants (aOR = 2.76, 95% CI [2.22-3.43]). The rural floating population had a lower COVID-19 vaccine hesitancy than the rural permanent residents (aOR = 0.58, 95% CI [0.42-0.80]). PSM analysis revealed a 2.38% difference in COVID-19 vaccine hesitancy between urban and rural participants. CONCLUSIONS: Urban participants were more hesitant to receive the COVID-19 vaccine than rural participants. Priority should be placed on boosting confidence in the healthcare system to reduce COVID-19 vaccine hesitancy among urban residents. Furthermore, we advocate for extra incentives and vaccination education for rural permanent residents.

Analysis of CT signs, radiomic features and clinical characteristics for delta variant COVID-19 patients with different vaccination status.

OBJECTIVE: To explore the characteristics of peripheral blood, high resolution computed tomography (HRCT) imaging and the radiomics signature (RadScore) in patients infected with delta variant virus under different coronavirus disease (COVID-19) vaccination status. METHODS: 123 patients with delta variant virus infection collected from November 1, 2021 to March 1, 2022 were analyzed retrospectively. According to COVID-19 vaccination Status, they were divided into three groups: Unvaccinated group, partially vaccinated group and full vaccination group. The peripheral blood, chest HRCT manifestations and RadScore of each group were analyzed and compared. RESULTS: The mean lymphocyte count 1.22 ± 0.49 × 10^9/L, CT score 7.29 ± 3.48, RadScore 0.75 ± 0.63 in the unvaccinated group; The mean lymphocyte count 1.55 ± 0.70 × 10^9/L, CT score 5.27 ± 2.72, RadScore 1.03 ± 0.46 in the partially vaccinated group; The mean lymphocyte count 1.87 ± 0.70 × 10^9/L, CT score 3.59 ± 3.14, RadScore 1.23 ± 0.29 in the fully vaccinated group. There were significant differences in lymphocyte count, CT score and RadScore among the three groups (all p < 0.05); Compared with the other two groups, the lung lesions in the unvaccinated group were more involved in multiple lobes, of which 26 cases involved the whole lung. CONCLUSIONS: Through the analysis of clinical features, pulmonary imaging features and radiomics, we confirmed the positive effect of COVID-19 vaccine on pulmonary inflammatory symptoms and lymphocyte count (immune system) during delta mutant infection.

Association between lifestyle and COVID-19 vaccination: A national cross-sectional study.

Objective: To assess lifestyles, COVID-19 vaccination coverage rates, and the relationships between lifestyles and COVID-19 vaccination among Chinese population. Methods: We collected data on sociodemographics, perception of the COVID-19 pandemic, lifestyles, and self-reported COVID-19 vaccination via an online survey in China. The chi-square goodness-of-fit test was used to monitor sample saturation throughout the formal online survey. The binary logistic regression analyses were conducted to examine the association between COVID-19 vaccination rate and lifestyle score. We assigned values to 12 lifestyles ranging from positive to negative, with positive lifestyles receiving a higher score and negative lifestyles receiving a lower score, ranging from 1 to 5. For each participant, the total lifestyle scored from 12 to 56. Restricted cubic spline (RCS) was used to visualize the trends and correlations between lifestyle score and COVID-19 vaccination coverage. Propensity score matching (PSM) was used to explore the association between specific lifestyles and COVID-19 vaccination. Results: A total of 29,925 participants (51.4% females) responded. The lifestyle score of the sample was 44.60 ± 6.13 (scoring range: 12-56). COVID-19 vaccination rate was found to be 89.4% (89.1-89.8%). Female participants reported a higher vaccination rate than male participants (91.5 vs. 87.1%). Compared to Q1, COVID-19 vaccination coverage rates increased with lifestyle total scores [OR Q2 = 1.901 (1.718-2.103), P < 0.001; OR Q3 = 2.373 (2.099-2.684), P < 0.001; and OR Q4 = 3.765 (3.209-4.417), P < 0.001]. After applying PSM, it was determined that all the 12 specific healthy lifestyles analyzed, including maintaining a healthy body weight, a healthy diet, regular physical exercises, adequate sleep, regular physical examination, and others, were found to be positive factors for COVID-19 vaccination. Conclusion: The majority of mainland Chinese lived a healthy lifestyle throughout the COVID-19 pandemic, and the rate of COVID-19 vaccination was high. Specific healthy lifestyles contributed to COVID-19 vaccination coverage rates significantly. According to the study's findings, global efforts to achieve herd immunity should be prioritized by continually promoting healthy lifestyles and improving public perception of COVID-19 vaccines.

Multimodality medical imaging in the diagnosis and evaluation of COVID-19

As the global COVID-19 pandemic progresses, many medical imaging methods such as X-ray, computed tomography (CT), magnetic resonance imaging, 18F-FDG PET/CT, and PET/MR have played important roles in the diagnosis and evaluation of COVID-19. Usually, X-ray and CT are the main tools for the diagnosis and evaluation of COVID-19. However, it is often difficult for a single imaging method to fully reflect the characteristics of the disease. Therefore the application of various imaging modalities for a comprehensive assessment of the condition will provide greater benefit to COVID-19 patients and to the understanding of the disease as COVID starts to become more widespread and less understood.

Bed-side DR and computed tomography manifestations and prognosis of critical COVID-19 cases

Critical COVID-19 cases are patients who meet any of the following criteria: (1) they have respiratory failure requiring mechanical assistance;(2) they are in shock;and/or (3) they have extrapulmonary organ failure, which means intensive care unit is needed. This chapter illustrates bed-side DR and computed tomography manifestations in critical cases. Bed-side DR is frequently used for progression evaluation. The lung area involved is extensive. The prognosis of these patients is also shown.

Computed tomography manifestations and prognosis of severe COVID-19 cases

Severe COVID-19 cases are patients meeting any of the following criteria: (1) respiratory distress, respiration rate ≥ 30 breaths/min;(2) oxygen saturation <93% at rest;and (3) partial pressure of oxygen/fraction of inspired oxygen≤300mm Hg. Besides, patients with rapid progression (>50%) within 24–48h based on computed tomography (CT) imaging results are deemed as the severe type. The lung areas of pneumonia involved in the severe type are more extended than that in the common type. Besides plain radiography and CT, Positron Emission Tomography (PET)/CT images in seven cases and PET/MR images in one case are also illustrated in this chapter. Increased or normal metabolic activity is noticed in the pneumonia area. Increased metabolic activity is noticed in the mediastinal lymph nodes.

Computed tomography manifestations and prognosis of common COVID-19 cases

Common COVID-19 cases are those with fever, respiratory symptoms, and positive imaging findings. This chapter illustrates 16 common cases with serial computed tomography examinations showing findings from the early phase to the advanced phase and then to the absorption phase. In the early phase, single or multiple ground-glass opacities (GGOs) with crazy-paving sign, mainly in the subpleural area of unilateral or bilateral lungs, are noticed, and then in the advanced phase, some of these GGOs turn into consolidations with air bronchogram inside;and finally, in the absorption phase, the GGOs and consolidations totally disappear or some parenchymal bands remain in the lung area, especially in the subpleural area.

Computed tomography manifestations and prognosis of mild COVID-19 cases

Computed tomography (CT) manifestations of asymptomatic patients with familial cluster transmission and of patients progressing from mild to common type are compiled in this chapter. Holding on to the thought that the imaging findings of asymptomatic infection and mild cases can be negative, we point out the fact that asymptomatic infection cases refer to individuals with positive nucleic acid results from respiratory tract specimens while with no reported symptoms or clinical signs recognized. Having said that, we emphasize asymptomatic infection is highly contagious through illustrating how the SARS-CoV-2 virus carried by an asymptomatic patient spreads into his family. Mild COVID-19 cases are infection cases with mild clinical symptoms and negative imaging findings. Some patients with mild type turned into the common type as the disease progressed, the CT manifestations of these cases are demonstrated.

Two-stage hybrid network for segmentation of COVID-19 pneumonia lesions in CT images: a multicenter study.

COVID-19 has been spreading continuously since its outbreak, and the detection of its manifestations in the lung via chest computed tomography (CT) imaging is essential to investigate the diagnosis and prognosis of COVID-19 as an indispensable step. Automatic and accurate segmentation of infected lesions is highly required for fast and accurate diagnosis and further assessment of COVID-19 pneumonia. However, the two-dimensional methods generally neglect the intraslice context, while the three-dimensional methods usually have high GPU memory consumption and calculation cost. To address these limitations, we propose a two-stage hybrid UNet to automatically segment infected regions, which is evaluated on the multicenter data obtained from seven hospitals. Moreover, we train a 3D-ResNet for COVID-19 pneumonia screening. In segmentation tasks, the Dice coefficient reaches 97.23% for lung segmentation and 84.58% for lesion segmentation. In classification tasks, our model can identify COVID-19 pneumonia with an area under the receiver-operating characteristic curve value of 0.92, an accuracy of 92.44%, a sensitivity of 93.94%, and a specificity of 92.45%. In comparison with other state-of-the-art methods, the proposed approach could be implemented as an efficient assisting tool for radiologists in COVID-19 diagnosis from CT images.

The association between lifestyle and COVID-19 vaccine hesitancy in China: A large-scale cross-sectional survey.

OBJECTIVE: To assess the association between lifestyle and COVID-19 vaccine hesitancy among Chinese adults and provide recommendations for increasing vaccination rates. METHODS: From August 6, 2021 to August 9, 2021, we recruited 29,925 participants from 31 Chinese provinces via an online questionnaire. We designed a question to assess COVID-19 vaccine hesitancy and used 16 items to assess lifestyle by calculating lifestyle scores. Odds ratios (OR) with 95 % confidence intervals (CI) were used to estimate the association by using binary logistic regression models. RESULTS: The overall prevalence of COVID-19 vaccine hesitancy was 8.40 % (95 % CI: 8.09-8.72), and the median lifestyle score was 65.00 (interquartile range: 59.00-71.00). After adjusting for potential confounders, the COVID-19 vaccine hesitancy rate decreased significantly with an increase in lifestyle score (P for Trend <0.001). Low COVID-19 vaccine hesitancy rate was associated with lifestyle factors including adequate sleep, never smoking, intermittent drinking, good relationships, working and studying, using hand sanitizer, wearing masks, less gathering activities, and keeping social distance (P < 0.05). CONCLUSION: Our findings indicate that high lifestyle score is associated with low vaccine hesitancy rate among Chinese. The government should view the smokers (or the drinkers) as the key to further boosting the vaccination rate. In addition, the publicity and education about wearing masks and keeping social distance should be prioritized.

Identifying the individual metabolic abnormities from a systemic perspective using whole-body PET imaging.

INTRODUCTION: Distinct physiological states arise from complex interactions among the various organs present in the human body. PET is a non-invasive modality with numerous successful applications in oncology, neurology, and cardiology. However, while PET imaging has been applied extensively in detecting focal lesions or diseases, its potential in detecting systemic abnormalities is seldom explored, mostly because total-body imaging was not possible until recently. METHODS: In this context, the present study proposes a framework capable of constructing an individual metabolic abnormality network using a subject's whole-body 18F-FDG SUV image and a normal control database. The developed framework was evaluated in the patients with lung cancer, the one discharged after suffering from Covid-19 disease, and the one that had gastrointestinal bleeding with the underlying cause unknown. RESULTS: The framework could successfully capture the deviation of these patients from healthy subjects at the level of both system and organ. The strength of the altered network edges revealed the abnormal metabolic connection between organs. The overall deviation of the network nodes was observed to be highly correlated to the organ SUV measures. Therefore, the molecular connectivity of glucose metabolism was characterized at a single subject level. CONCLUSION: The proposed framework represents a significant step toward the use of PET imaging for identifying metabolic dysfunction from a systemic perspective. A better understanding of the underlying biological mechanisms and the physiological interpretation of the interregional connections identified in the present study warrant further research.

The Psychological Experience of COVID-19 Vaccination and Its Impact on the Willingness to Receive Booster Vaccines among the Chinese Population: Evidence from a National Cross-Sectional Study.

The purpose of this study was to assess the psychological experience of COVID-19 basic vaccination, the willingness to receive booster vaccines, and to determine their relationships among Chinese people. Between 6 August 2021 and 9 August 2021, a research firm performed a national cross-sectional online survey among Chinese individuals (aged over 18), using the snowball sampling approach, with 26,755 participants. Factor analysis and binary logistic regression were used to evaluate the existing associations. The overall COVID-19 vaccination psychological experience score of the participants was 25.83 (25.78~25.89; scores ranged from 7-35). A total of 93.83% (95%CI = 93.54~94.12) of respondents indicated a willingness to receive booster vaccines. After classifying psychological experiences associated with COVID-19 vaccination into positive and negative experiences and adjusting for confounding factors, for the former, the willingness to receive booster vaccines for participants with the highest scores of 13-15 was 3.933 times higher (OR = 3.933, 95%CI = 3.176~4.871) than participants who obtained scores of 3-9, and for the latter, the willingness to receive booster vaccines for participants with the highest scores of 19-20 was 8.871 times higher (OR = 8.871, 95%CI = 6.240~12.612) than participants who obtained scores of 4-13. Our study suggests that a good psychological experience with vaccination is positively associated with an increased willingness to receive booster vaccines.

Guardians' willingness to vaccinate their teenagers against COVID-19 in China: A national cross-sectional survey.

OBJECTIVE: To investigate Chinese guardians' willingness to vaccinate teenagers (WVT) against COVID-19, we conducted a national wide survey in 31 provinces in mainland China. METHODS: We involved 16133 guardians from 31 provinces in Chinese Mainland from August 6th to 9th, 2021. The question "Are you willing to vaccinate teenagers of COVID-19 vaccine?" was designed to capture WVT. Odds ratios (OR) with 95% Confidence Intervals (CI) for potential factors of WVT were estimated using multiple logistic regression models. RESULTS: In total, 13327 (82.61%) of the respondents expressed positive WVT, 12.90% of the respondents were uncertain but inclined to vaccinate their teenagers. Meanwhile, 3.89% of the respondents were uncertain and inclined to reject, and 0.60% of the respondents rejected the vaccines. After adjusting for potential confounders, the married, total family income last year, reject to Categoly1 vaccines, access information about the COVID-19 vaccines from community workers, low COVID-19 vaccine conspiracy, guardian's vaccination behavior, and the importance of vaccinating teenagers were all independent factors that affected the guardians' likely to accept. Further, the current study found that lower trust in doctors and vaccine developers was associated with negative WVT. The reasons for negative WVT included teenagers' young age and guardians' worries on the safety and effectiveness of COVID-19 vaccines. CONCLUSION: This large-scale study assessed Chinese guardians' WVT against COVID-19, as well as its potential influencing factors, which is useful for international and national decision-makers.

COVID-19 Vaccination Acceptance Among Chinese Population and Its Implications for the Pandemic: A National Cross-Sectional Study

Objective To examine the COVID-19 vaccination rate among a representative sample of adults from 31 provinces on the Chinese mainland and identify its influencing factors. Methods We gathered sociodemographic information, data on people's awareness and behavior regarding COVID-19 and the COVID-19 vaccine, the accessibility of COVID-19 vaccination services, community environmental factors influencing people's awareness and behavior regarding the vaccination, information about people's skepticism on COVID-19 vaccine, and information about people's trust in doctors as well as vaccine developers through an online nationwide cross-sectional survey among Chinese adults (18 years and older). The odds ratios (OR) and 95% confidence intervals (CI) for the statistical associations were estimated using logistic regression models. Results A total of 29,925 participants (51.4% females and 48.6% males) responded. 89.4% of the participants had already received a COVID-19 vaccination. After adjusting for demographic characteristics, awareness of COVID-19 pandemic/ COVID-19 vaccine, community environmental factors, awareness and behavior of general vaccinations, we discovered that having no religious affiliation, having the same occupational status as a result of coronavirus epidemic, being a non-smoker, always engaging in physical activity, having a lower social status, perceiving COVID-19 to be easily curable, and having easier access to vaccination are all associated with high vaccination rate (all P <0.05). Conclusions 31 provinces in mainland China currently have a relatively high rate of COVID-19 vaccination. To further increase the rate of COVID-19 vaccination, we must remove barriers associated with the community context and improve access to COVID-19 vaccine services. In addition, taking proactive and effective measures to address the reasons for non-vaccination with COVID-19 will aid in epidemic prevention and control.

COVID-19 Vaccine Hesitancy Among Chinese Population: A Large-Scale National Study.

Globally, vaccine hesitancy is a growing public health problem. It is detrimental to the consolidation of immunization program achievements and elimination of vaccine-targeted diseases. The objective of this study was to estimate the prevalence of COVID-19 vaccine hesitancy in China and explore its contributing factors. A national cross-sectional online survey among Chinese adults (≥18 years old) was conducted between August 6, 2021 and August 9 via a market research company. We collected sociodemographic information; lifestyle behavior; quality of life; the knowledge, awareness, and behavior of COVID-19; the knowledge, awareness, and behavior of COVID-19 vaccine; willingness of COVID-19 vaccination; accessibility of COVID-19 vaccination services; skepticism about COVID-19 and COVID-19 vaccine; doctor and vaccine developer scale; and so on. Odds ratios (OR) with 95% confidence intervals (CI) were used to estimate the associations by using logistic regression models. A total of 29,925 residents (48.64% men) were enrolled in our study with mean age of 30.99 years. We found an overall prevalence of COVID-19 vaccine hesitancy at 8.40% (95% CI, 8.09-8.72) in primary vaccination and 8.39% (95% CI, 8.07-8.70) in booster vaccination. In addition, after adjusting for potential confounders, we found that women, higher educational level, married residents, higher score of health condition, never smoked, increased washing hands, increased wearing mask, increased social distance, lower level of vaccine conspiracy beliefs, disease risks outweigh vaccine risk, higher level of convenient vaccination, and higher level of trust in doctor and developer were more willing to vaccinate than all others (all p < 0.05). Age, sex, educational level, marital status, chronic disease condition, smoking, healthy behaviors, the curability of COVID-19, the channel of accessing information of COVID-19 vaccine, endorsement of vaccine conspiracy beliefs, weigh risks of vaccination against risks of the disease, making a positive influence on the health of others around you, and lower trust in healthcare system may affect the variation of willingness to take a COVID-19 vaccine (all p < 0.05). The prevalence of COVID-19 vaccine hesitancy was modest in China, even with the slight resulting cascade of changing vaccination rates between the primary and booster vaccination. Urgent action to address vaccine hesitancy is needed in building trust in medical personnel and vaccine producers, promoting the convenience of vaccination services, and spreading reliable information of COVID-19 vaccination via the Internet and other media.

Mix Contrast for COVID-19 Mild-to-Critical Prediction.

OBJECTIVE: In a few patients with mild COVID-19, there is a possibility of the infection becoming severe or critical in the future. This work aims to identify high-risk patients who have a high probability of changing from mild to critical COVID-19 (only account for 5% of cases). METHODS: Using traditional convolutional neural networks for classification may not be suitable to identify this 5% of high risk patients from an entire dataset due to the highly imbalanced label distribution. To address this problem, we propose a Mix Contrast model, which matches original features with mixed features for contrastive learning. Three modules are proposed for training the model: 1) a cumulative learning strategy for synthesizing the mixed feature; 2) a commutative feature combination module for learning the commutative law of feature concatenation; 3) a united pairwise loss assigning adaptive weights for sample pairs with different class anchors based on their current optimization status. RESULTS: We collect a multi-center computed tomography dataset including 918 confirmed COVID-19 patients from four hospitals and evaluate the proposed method on both the COVID-19 mild-to-critical prediction and COVID-19 diagnosis tasks. For mild-to-critical prediction, the experimental results show a recall of 0.80 and a specificity of 0.815. For diagnosis, the model shows comparable results with deep neural networks using a large dataset. Our method demonstrates improvements when the amount of training data is small or imbalanced. SIGNIFICANCE: Identifying mild-to-critical COVID-19 patients is important for early prevention and personalized treatment planning.

A Deep Learning Radiomics Model to Identify Poor Outcome in COVID-19 Patients With Underlying Health Conditions: A Multicenter Study.

OBJECTIVE: Coronavirus disease 2019 (COVID-19) has caused considerable morbidity and mortality, especially in patients with underlying health conditions. A precise prognostic tool to identify poor outcomes among such cases is desperately needed. METHODS: Total 400 COVID-19 patients with underlying health conditions were retrospectively recruited from 4 centers, including 54 dead cases (labeled as poor outcomes) and 346 patients discharged or hospitalized for at least 7 days since initial CT scan. Patients were allocated to a training set (n = 271), a test set (n = 68), and an external test set (n = 61). We proposed an initial CT-derived hybrid model by combining a 3D-ResNet10 based deep learning model and a quantitative 3D radiomics model to predict the probability of COVID-19 patients reaching poor outcome. The model performance was assessed by area under the receiver operating characteristic curve (AUC), survival analysis, and subgroup analysis. RESULTS: The hybrid model achieved AUCs of 0.876 (95% confidence interval: 0.752-0.999) and 0.864 (0.766-0.962) in test and external test sets, outperforming other models. The survival analysis verified the hybrid model as a significant risk factor for mortality (hazard ratio, 2.049 [1.462-2.871], P < 0.001) that could well stratify patients into high-risk and low-risk of reaching poor outcomes (P < 0.001). CONCLUSION: The hybrid model that combined deep learning and radiomics could accurately identify poor outcomes in COVID-19 patients with underlying health conditions from initial CT scans. The great risk stratification ability could help alert risk of death and allow for timely surveillance plans.