Effectiveness of COVID-19 diagnosis and management tools: A review

Diagnostic Value of 99mTc-Ubiquicidin Scintigraphy in Differentiating Bacterial from Nonbacterial Pneumonia

Purpose: Differentiating purely viral from bacterial etiologies continues to be a challenging yet key step in the management of community-acquired pneumonia (CAP), further highlighted since the COVID-19 pandemic. This study aims to evaluate the utility of 99mTc-ubiquicidin (UBI) in the differentiation of bacterial from nonbacterial pneumonia. Methods: A total of 30 patients with CAP were allocated into groups A, bacterial (n = 15), and B, viral pneumonia (n = 15). All patients underwent 99mTc-UBI scan with planar and single-photon emission computed tomography (SPECT) images of thorax acquired at 30 and 180 min postinjection. Target-to-background (T/B) ratios were calculated with values >1.4 interpreted as positive for bacterial infection. Correlation was made with computed tomography (CT) scan and polymerase chain reaction (PCR) results. Results: UBI scan was positive in 43.3% (n = 13) of patients, with sensitivity, specificity, and accuracy of 86.7%, 100%, and 93.3%, respectively, and close correlation with chest CT scan and PCR results (p-value = 0.000). Planar images were generally not helpful. Receiver operating characteristic curve analysis indicated similar diagnostic performance for 30-min and 3-h SPECT images by implementing T/B thresholds of 1.2 and 1.33, respectively. Conclusions: 99mTc-UBI SPECT is a promising modality for differentiating purely viral from bacterial or superimposed bacterial pneumonia and provides reliable evidence either to mandate or withhold administration of antibiotics in patients with CAP.

Ursodeoxycholic acid relieves clinical severity of COVID-19 in patients with chronic liver diseases

Background

The potential effect of ursodeoxycholic acid (UDCA) on the clinical outcomes of SARS-CoV-2 in patients with chronic liver diseases has been a subject of ongoing debate since the onset of the SARS-CoV-2 pandemic in 2019. This study aims to investigate the effect of UDCA on the prognosis of SARS-CoV-2 infection in patients with chronic liver diseases.

Methods

A total of 926 patients with chronic liver diseases who contracted their first SARS-CoV-2 infection during December 2022 to January 2023, were included in this study. Participants were divided into two groups based on the use of UDCA: the UDCA cohort (n = 329) and the non-UDCA cohort (n = 597). After performing a 1:1 age-and sex-matching, the analysis proceeded with 309 patients from each group for further evaluation.

Results

In the UDCA-treated cohort, the incidence of asymptomatic SARS-CoV-2 infections was significantly higher, with 30.1% of patients affected, compared to 6.47% in the non-UDCA group (p < 0.0001). Multivariable analysis identified UDCA as a protective factor against symptomatic infections, yielding an odds ratio (OR) of 4.77 (95% CI: 2.70-8.44, p < 0.001). Furthermore, age over 50 was found to be a risk factor for asymptomatic infections in the UDCA cohort, with an adjusted OR of 1.51 (95% CI: 1.01-2.24, p = 0.05).

Conclusion

The study suggests that UDCA therapy may improve clinical outcomes in patients with chronic liver diseases patients who are infected with SARS-CoV-2, highlighting its potential role in improving prognosis within this vulnerable population. However, further research is required to validate these findings and to elucidate the mechanisms underlying UDCA's protective effect.

Survey on the distribution of medical imaging frequencies and dose levels for CT examinations in a comprehensive hospital in Shanghai

With the continuous advancement and clinical application of CT technology, the increasing collective dose burden from CT scans and associated potential health risks have become significant concerns in radiation protection. Current research increasingly focuses on the cumulative effective dose (CED) resulting from multiple CT scans, often revealing patients with high CEDs, even exceeding 100 mSv. However, reports on CEDs from multiple CT scans in China are scarce. Therefore, we investigated the distribution of CT scan frequencies and CEDs at a comprehensive hospital in Shanghai, examining data from 1 October 2022, to 30 April 2024, sourced from the hospital's radiology information system. The effective dose (E) was estimated using conversion factorskand DLP values from Radiation Dose Structured Reports (RDSR). We assessed the number of CT examinations conducted per patient and evaluated the CED over 1.6 years. During this period, 112 339 CT examinations were performed. Significant differences in CT examination frequencies were observed across different age groups and examination regions (P< 0.01). A total of 78.43% of patients underwent only one CT examination in 1.6 years, while 0.03% had more than 10 examinations, with a maximum of 15. Of the patients, 67.78% (76,142 individuals) received a CED less than 10 mSv, 0.05% (53 patients) received a CED over 50 mSv, and one patient exceeded 100 mSv. In conclusion, this study underscored the necessity of monitoring patients with high CT examination frequencies and CEDs, highlighting the importance of justification and optimization in medical radiation protection.

The Impact of Traditional Chinese Herbal Decoctions Combined with Rehabilitation Therapy on Pulmonary Function and Respiratory Muscle Strength in COVID-19 Recovery Patients

Objective

This study aims to evaluate the clinical efficacy of integrated traditional Chinese and Western medicine rehabilitation treatment during the recovery period of COVID-19, providing a scientific basis for developing more effective rehabilitation protocols.

Methods

The study included 120 COVID-19 (novel coronavirus) recovery patients treated at our hospital from November 2021 to April 2022. After registration, patients were randomly divided into two groups, namely the study group and the control group. The control group received conventional rehabilitation treatment, while the study group underwent integrated traditional Chinese and Western medicine rehabilitation treatment, with 60 cases in each group. The clinical observation indicators in this study include the results of the 6-minute walk test (6MWT), respiratory and circulatory parameters, pulmonary function, changes in respiratory muscle strength, and quality of life in both groups of patients.

Results

The 6MWT distance increased significantly in both groups, with the study group showing a larger improvement (P < 0.05). SpO2 and PaO2 values improved significantly in both groups, with greater increases in the study group (P < 0.05). Lung function parameters (FEV1 and FEV1/FVC) improved significantly in the study group compared to the control group (P < 0.05). Diaphragmatic thickness and mobility were also significantly higher in the study group (P < 0.05). The SF-36 quality of life scores were significantly better in the study group (P < 0.05).

Conclusion

Integrated traditional Chinese and Western medicine rehabilitation treatment has achieved significant efficacy during the recovery period of COVID-19. The complementary use of traditional Chinese medicine's differential diagnosis and treatment and modern medical approaches from Western medicine provides patients with comprehensive and personalized rehabilitation services, offering new ideas and methods to improve the quality of patient recovery.

Machine learning predictive modeling of the persistence of post-Covid19 disorders: Loss of smell and taste as case studies

The worldwide health crisis triggered by the novel coronavirus (COVID-19) epidemic has resulted in an extensive variety of symptoms in people who have been infected, the most prevalent disorders of which are loss of smell and taste senses. In some patients, these disorders might occasionally last for several months and can strongly affect patients' quality of life. The COVID-19-related loss of taste and smell does not presently have a particular therapy. However, with the help of an early prediction of these disorders, healthcare providers can direct the patients to control these symptoms and prevent complications by following special procedures. The purpose of this research is to develop a machine learning (ML) model that can predict the occurrence and persistence of post-COVID-19-related loss of smell and taste abnormalities. In this study, we used our dataset to describe the symptoms, functioning, and disability of 413 verified COVID-19 patients. In order to prepare accurate classification models, we combined several ML algorithms, including logistic regression, k-nearest neighbors, support vector machine, random forest, extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). The accuracy of the loss of taste model was 91.5 % with an area-under-cure (AUC) of 0.94, and the accuracy of the loss of smell model was 95 % with an AUC of 0.97. Our proposed modelling framework can be utilized by hospitals experts to assess these post-COVID-19 disorders in the early stages, which supports the development of treatment strategies.

A non-enhanced CT-based deep learning diagnostic system for COVID-19 infection at high risk among lung cancer patients

Background

Pneumonia and lung cancer have a mutually reinforcing relationship. Lung cancer patients are prone to contracting COVID-19, with poorer prognoses. Additionally, COVID-19 infection can impact anticancer treatments for lung cancer patients. Developing an early diagnostic system for COVID-19 pneumonia can help improve the prognosis of lung cancer patients with COVID-19 infection.

Method

This study proposes a neural network for COVID-19 diagnosis based on non-enhanced CT scans, consisting of two 3D convolutional neural networks (CNN) connected in series to form two diagnostic modules. The first diagnostic module classifies COVID-19 pneumonia patients from other pneumonia patients, while the second diagnostic module distinguishes severe COVID-19 patients from ordinary COVID-19 patients. We also analyzed the correlation between the deep learning features of the two diagnostic modules and various laboratory parameters, including KL-6.

Result

The first diagnostic module achieved an accuracy of 0.9669 on the training set and 0.8884 on the test set, while the second diagnostic module achieved an accuracy of 0.9722 on the training set and 0.9184 on the test set. Strong correlation was observed between the deep learning parameters of the second diagnostic module and KL-6.

Conclusion

Our neural network can differentiate between COVID-19 pneumonia and other pneumonias on CT images, while also distinguishing between ordinary COVID-19 patients and those with white lung. Patients with white lung in COVID-19 have greater alveolar damage compared to ordinary COVID-19 patients, and our deep learning features can serve as an imaging biomarker.

Exploring the Interplay of Dataset Size and Imbalance on CNN Performance in Healthcare: Using X-rays to Identify COVID-19 Patients

INTRODUCTION

Convolutional Neural Network (CNN) systems in healthcare are influenced by unbalanced datasets and varying sizes. This article delves into the impact of dataset size, class imbalance, and their interplay on CNN systems, focusing on the size of the training set versus imbalance-a unique perspective compared to the prevailing literature. Furthermore, it addresses scenarios with more than two classification groups, often overlooked but prevalent in practical settings.

METHODS

Initially, a CNN was developed to classify lung diseases using X-ray images, distinguishing between healthy individuals and COVID-19 patients. Later, the model was expanded to include pneumonia patients. To evaluate performance, numerous experiments were conducted with varied data sizes and imbalance ratios for both binary and ternary classifications, measuring various indices to validate the model's efficacy.

RESULTS

The study revealed that increasing dataset size positively impacts CNN performance, but this improvement saturates beyond a certain size. A novel finding is that the data balance ratio influences performance more significantly than dataset size. The behavior of three-class classification mirrored that of binary classification, underscoring the importance of balanced datasets for accurate classification.

CONCLUSIONS

This study emphasizes the fact that achieving balanced representation in datasets is crucial for optimal CNN performance in healthcare, challenging the conventional focus on dataset size. Balanced datasets improve classification accuracy, both in two-class and three-class scenarios, highlighting the need for data-balancing techniques to improve model reliability and effectiveness.

MOTIVATION

Our study is motivated by a scenario with 100 patient samples, offering two options: a balanced dataset with 200 samples and an unbalanced dataset with 500 samples (400 healthy individuals). We aim to provide insights into the optimal choice based on the interplay between dataset size and imbalance, enriching the discourse for stakeholders interested in achieving optimal model performance.

LIMITATIONS

Recognizing a single model's generalizability limitations, we assert that further studies on diverse datasets are needed.

Patients' Attitudes Toward the Use of Artificial Intelligence as a Diagnostic Tool in Radiology in Saudi Arabia: Cross-Sectional Study

BACKGROUND

Artificial intelligence (AI) is widely used in various medical fields, including diagnostic radiology as a tool for greater efficiency, precision, and accuracy. The integration of AI as a radiological diagnostic tool has the potential to mitigate delays in diagnosis, which could, in turn, impact patients' prognosis and treatment outcomes. The literature shows conflicting results regarding patients' attitudes to AI as a diagnostic tool. To the best of our knowledge, no similar study has been conducted in Saudi Arabia.

OBJECTIVE

The objectives of this study are to examine patients' attitudes toward the use of AI as a tool in diagnostic radiology at King Khalid University Hospital, Saudi Arabia. Additionally, we sought to explore potential associations between patients' attitudes and various sociodemographic factors.

METHODS

This descriptive-analytical cross-sectional study was conducted in a tertiary care hospital. Data were collected from patients scheduled for radiological imaging through a validated self-administered questionnaire. The main outcome was to measure patients' attitudes to the use of AI in radiology by calculating mean scores of 5 factors, distrust and accountability (factor 1), procedural knowledge (factor 2), personal interaction and communication (factor 3), efficiency (factor 4), and methods of providing information to patients (factor 5). Data were analyzed using the student t test, one-way analysis of variance followed by post hoc and multivariable analysis.

RESULTS

A total of 382 participants (n=273, 71.5% women and n=109, 28.5% men) completed the surveys and were included in the analysis. The mean age of the respondents was 39.51 (SD 13.26) years. Participants favored physicians over AI for procedural knowledge, personal interaction, and being informed. However, the participants demonstrated a neutral attitude for distrust and accountability and for efficiency. Marital status was found to be associated with distrust and accountability, procedural knowledge, and personal interaction. Associations were also found between self-reported health status and being informed and between the field of specialization and distrust and accountability.

CONCLUSIONS

Patients were keen to understand the work of AI in radiology but favored personal interaction with a radiologist. Patients were impartial toward AI replacing radiologists and the efficiency of AI, which should be a consideration in future policy development and integration. Future research involving multicenter studies in different regions of Saudi Arabia is required.

Clinical-Epidemiological Profile of COVID-19 Patients Admitted during Three Waves of the Pandemic in a Tertiary Care Center, in Belém, Pará, Amazon Region of Brazil

BACKGROUND

Coronavirus disease 2019 (COVID-19) is a disease with a broad clinical spectrum, which may result in hospitalization in healthcare units, intensive care, and progression to death. This study aimed to describe and compare the clinical and epidemiological profile of COVID-19 during the three waves of the disease, in patients admitted to a public hospital in the city of Belém, Pará, in the Amazon region of Brazil.

METHODS

This descriptive, observational, and cross-sectional study was population-based on individuals who were hospitalized with a diagnosis of COVID-19, confirmed by real-time reverse transcription-polymerase chain reaction (RT-PCR), and who were interviewed and monitored at the public hospital, from February 2020 to April 2022.

RESULTS

The prevalence was male patients, older than 60 years. The most frequent symptoms were dyspnea, cough, and fever. Systemic arterial hypertension was the most prevalent comorbidity followed by diabetes mellitus. Less than 15% of patients were vaccinated. The nasal oxygen cannula was the most used oxygen therapy interface followed by the non-rebreathing reservoir mask. Invasive mechanical ventilation predominated and the median time of invasive mechanical ventilation ranged from 2 to 6 days among waves. As for the hospital outcome, transfers prevailed, followed by deaths and discharges.

CONCLUSION

The presence of comorbidities, advanced age, and male sex were important factors in the severity and need for hospitalization of these patients, and the implementation of the vaccination policy was an essential factor in reducing the number of hospital admissions.

Long non-coding RNAs in biomarking COVID-19: a machine learning-based approach

BACKGROUND

The coronavirus pandemic that started in 2019 has caused the highest mortality and morbidity rates worldwide. Data on the role of long non-coding RNAs (lncRNAs) in coronavirus disease 2019 (COVID-19) is scarce. We aimed to elucidate the relationship of three important lncRNAs in the inflammatory states, H19, taurine upregulated gene 1 (TUG1), and colorectal neoplasia differentially expressed (CRNDE) with key factors in inflammation and fibrosis induction including signal transducer and activator of transcription3 (STAT3), alpha smooth muscle actin (α-SMA), tumor necrosis factor-alpha (TNF-α), and interleukin-6 (IL-6) in COVID-19 patients with moderate to severe symptoms.

METHODS

Peripheral blood mononuclear cells from 28 COVID-19 patients and 17 healthy controls were collected. The real-time quantitative polymerase chain reaction (RT-qPCR) was performed to evaluate the expression of RNAs and lncRNAs. Western blotting analysis was also performed to determine the expression levels of STAT3 and α-SMA proteins. Machine learning and receiver operating characteristic (ROC) curve analysis were carried out to evaluate the distinguishing ability of lncRNAs.

RESULTS

The expression levels of H19, TUG1, and CRNDE were significantly overexpressed in COVID-19 patients compared to healthy controls. Moreover, STAT3 and α-SMA expression levels were remarkedly increased at both transcript and protein levels in patients with COVID-19 compared to healthy subjects and were correlated with Three lncRNAs. Likewise, IL-6 and TNF-α were considerably upregulated in COVID-19 patients. Machine learning and ROC curve analysis showed that CRNDE-H19 panel has the proper ability to distinguish COVID-19 patients from healthy individuals (area under the curve (AUC) = 0.86).

CONCLUSION

The overexpression of three lncRNAs in COVID-19 patients observed in this study may align with significant manifestations of COVID-19. Furthermore, their co-expression with STAT3 and α-SMA, two critical factors implicated in inflammation and fibrosis induction, underscores their potential involvement in exacerbating cardiovascular, pulmonary and common symptoms and complications associated with COVID-19. The combination of CRNDE and H19 lncRNAs seems to be an impressive host-based biomarker panel for screening and diagnosis of COVID-19 patients from healthy controls. Research into lncRNAs can provide a robust platform to find new viral infection-related mediators and propose novel therapeutic strategies for viral infections and immune disorders.

Validated machine learning tools to distinguish immune checkpoint inhibitor, radiotherapy, COVID-19 and other infective pneumonitis

BACKGROUND

Pneumonitis is a well-described, potentially disabling, or fatal adverse effect associated with both immune checkpoint inhibitors (ICI) and thoracic radiotherapy. Accurate differentiation between checkpoint inhibitor pneumonitis (CIP) radiation pneumonitis (RP), and infective pneumonitis (IP) is crucial for swift, appropriate, and tailored management to achieve optimal patient outcomes. However, correct diagnosis is often challenging, owing to overlapping clinical presentations and radiological patterns.

METHODS

In this multi-centre study of 455 patients, we used machine learning with radiomic features extracted from chest CT imaging to develop and validate five models to distinguish CIP and RP from COVID-19, non-COVID-19 infective pneumonitis, and each other. Model performance was compared to that of two radiologists.

RESULTS

Models to distinguish RP from COVID-19, CIP from COVID-19 and CIP from non-COVID-19 IP out-performed radiologists (test set AUCs of 0.92 vs 0.8 and 0.8; 0.68 vs 0.43 and 0.4; 0.71 vs 0.55 and 0.63 respectively). Models to distinguish RP from non-COVID-19 IP and CIP from RP were not superior to radiologists but demonstrated modest performance, with test set AUCs of 0.81 and 0.8 respectively. The CIP vs RP model performed less well on patients with prior exposure to both ICI and radiotherapy (AUC 0.54), though the radiologists also had difficulty distinguishing this test cohort (AUC values 0.6 and 0.6).

CONCLUSION

Our results demonstrate the potential utility of such tools as a second or concurrent reader to support oncologists, radiologists, and chest physicians in cases of diagnostic uncertainty. Further research is required for patients with exposure to both ICI and thoracic radiotherapy.

Association of Calf Circumference with Clinical and Biochemical Markers in Older Adults with COVID-19 Admitted at Intensive Care Unit: A Retrospective Cross-Sectional Study

BACKGROUND

COVID-19 is an infectious disease characterized by a severe catabolic and inflammatory state, leading to loss of muscle mass. The assessment of muscle mass can be useful to identify nutritional risk and assist in early management, especially in older adults who have high nutritional risks. The aim of this study was to evaluate the association of calf circumference (CC) with clinical and biochemical markers and mortality in older adults with COVID-19 admitted to the intensive care unit (ICU).

METHODS

A retrospective cross-sectional study was conducted in a public hospital. CC was adjusted for body mass index (BMI), reducing 3, 7, or 12 cm for a BMI of 25-29.9, 30-39.9, and ≥40 kg/m2, respectively, and classified as reduced when <33 cm for women and <34 cm for men. Pearson's correlation between BMI and CC was performed to assess the association between variables. Regression analysis was adjusted for sex, age, and BMI variables. Cox regression was used to assess survival related to CC.

RESULTS

A total of 208 older adults diagnosed with COVID-19 admitted to ICU were included, of which 84% (n = 176) were classified as having reduced CC. These patients were older, with lower BMI, higher nutritional risk, malnourished, and higher concentration of urea and urea-creatinine ratio (UCR) compared with the group with normal CC. There was an association between edematous patients at nutritional risk and malnourished with reduced CC in the Cox regression, either adjusted or not for confounding.

CONCLUSIONS

CC was not associated with severity, biochemical markers, or mortality in older adults with COVID-19 admitted to the ICU, but it was associated with moderately malnourished patients assessed by subjective global assessment (SGA).

Imaging in pulmonary infections of immunocompetent adult patients

Pneumonia is a clinical syndrome characterised by fever, cough and alveolar infiltration of purulent fluid, caused by infection with a microbial pathogen. It can be caused by infections with bacteria, viruses or fungi, but a causative organism is identified in less than half of cases. The most common type of pneumonia is community-acquired pneumonia, which is caused by infections acquired outside the hospital. Current guidelines for pneumonia diagnosis require imaging to confirm the clinical suspicion of pneumonia. Thus, imaging plays an important role in both the diagnosis and management of pneumonia, with each modality having specific advantages and limitations. Chest radiographs are commonly used but have limitations in terms of sensitivity and specificity. Lung ultrasound shows high sensitivity and specificity. Computed tomography scans offer higher diagnostic accuracy but involve higher radiation doses. Radiological patterns, including lobar, lobular and interstitial pneumonia, provide valuable insights into causative pathogens and treatment decisions. Understanding these radiological patterns is crucial for accurate diagnosis. In this review, we will summarise the most important aspects pertaining to the role of imaging in pneumonia and will highlight the imaging characteristics of the most common causative organisms.

Activatable Probes for Ratiometric Imaging of Endogenous Biomarkers In Vivo

Dynamic variations in the concentration and abnormal distribution of endogenous biomarkers are strongly associated with multiple physiological and pathological states. Therefore, it is crucial to design imaging systems capable of real-time detection of dynamic changes in biomarkers for the accurate diagnosis and effective treatment of diseases. Recently, ratiometric imaging has emerged as a widely used technique for sensing and imaging of biomarkers due to its advantage of circumventing the limitations inherent to conventional intensity-dependent signal readout methods while also providing built-in self-calibration for signal correction. Here, the recent progress of ratiometric probes and their applications in sensing and imaging of biomarkers are outlined. Ratiometric probes are classified according to their imaging mechanisms, and ratiometric photoacoustic imaging, ratiometric optical imaging including photoluminescence imaging and self-luminescence imaging, ratiometric magnetic resonance imaging, and dual-modal ratiometric imaging are discussed. The applications of ratiometric probes in the sensing and imaging of biomarkers such as pH, reactive oxygen species (ROS), reactive nitrogen species (RNS), glutathione (GSH), gas molecules, enzymes, metal ions, and hypoxia are discussed in detail. Additionally, this Review presents an overview of challenges faced in this field along with future research directions.

CCL18, CHI3L1, ANG2, IL-6 systemic levels are associated with the extent of lung damage and radiomic features in SARS-CoV-2 infection

OBJECTIVE AND DESIGN

We aimed to identify cytokines whose concentrations are related to lung damage, radiomic features, and clinical outcomes in COVID-19 patients.

MATERIAL OR SUBJECTS

Two hundred twenty-six patients with SARS-CoV-2 infection and chest computed tomography (CT) images were enrolled.

METHODS

CCL18, CHI3L1/YKL-40, GAL3, ANG2, IP-10, IL-10, TNFα, IL-6, soluble gp130, soluble IL-6R were quantified in plasma samples using Luminex assays. The Mann-Whitney U test, the Kruskal-Wallis test, correlation and regression analyses were performed. Mediation analyses were used to investigate the possible causal relationships between cytokines, lung damage, and outcomes. AVIEW lung cancer screening software, pyradiomics, and XGBoost classifier were used for radiomic feature analyses.

RESULTS

CCL18, CHI3L1, and ANG2 systemic levels mainly reflected the extent of lung injury. Increased levels of every cytokine, but particularly of IL-6, were associated with the three outcomes: hospitalization, mechanical ventilation, and death. Soluble IL-6R showed a slight protective effect on death. The effect of age on COVID-19 outcomes was partially mediated by cytokine levels, while CT scores considerably mediated the effect of cytokine levels on outcomes. Radiomic-feature-based models confirmed the association between lung imaging characteristics and CCL18 and CHI3L1.

CONCLUSION

Data suggest a causal link between cytokines (risk factor), lung damage (mediator), and COVID-19 outcomes.

Value of deep learning reconstruction of chest low-dose CT for image quality improvement and lung parenchyma assessment on lung window

OBJECTIVES

To explore the performance of low-dose computed tomography (LDCT) with deep learning reconstruction (DLR) for the improvement of image quality and assessment of lung parenchyma.

METHODS

Sixty patients underwent chest regular-dose CT (RDCT) followed by LDCT during the same examination. RDCT images were reconstructed with hybrid iterative reconstruction (HIR) and LDCT images were reconstructed with HIR and DLR, both using lung algorithm. Radiation exposure was recorded. Image noise, signal-to-noise ratio, and subjective image quality of normal and abnormal CT features were evaluated and compared using the Kruskal-Wallis test with Bonferroni correction.

RESULTS

The effective radiation dose of LDCT was significantly lower than that of RDCT (0.29 ± 0.03 vs 2.05 ± 0.65 mSv, p < 0.001). The mean image noise ± standard deviation was 33.9 ± 4.7, 39.6 ± 4.3, and 31.1 ± 3.2 HU in RDCT, LDCT HIR-Strong, and LDCT DLR-Strong, respectively (p < 0.001). The overall image quality of LDCT DLR-Strong was significantly better than that of LDCT HIR-Strong (p < 0.001) and comparable to that of RDCT (p > 0.05). LDCT DLR-Strong was comparable to RDCT in evaluating solid nodules, increased attenuation, linear opacity, and airway lesions (all p > 0.05). The visualization of subsolid nodules and decreased attenuation was better with DLR than with HIR in LDCT but inferior to RDCT (all p < 0.05).

CONCLUSION

LDCT DLR can effectively reduce image noise and improve image quality. LDCT DLR provides good performance for evaluating pulmonary lesions, except for subsolid nodules and decreased lung attenuation, compared to RDCT-HIR.

CLINICAL RELEVANCE STATEMENT

The study prospectively evaluated the contribution of DLR applied to chest low-dose CT for image quality improvement and lung parenchyma assessment. DLR can be used to reduce radiation dose and keep image quality for several indications.

KEY POINTS

• DLR enables LDCT maintaining image quality even with very low radiation doses. • Chest LDCT with DLR can be used to evaluate lung parenchymal lesions except for subsolid nodules and decreased lung attenuation. • Diagnosis of pulmonary emphysema or subsolid nodules may require higher radiation doses.

How predictive of SARS-CoV-2 infection are clinical characteristics at presentation among individuals with COVID-like symptoms treated at the Mexican Institute of Social Security

BACKGROUND

The COVID-19 pandemic has progressed rapidly, with the emergence of new virus variants that pose challenges in treating infected individuals. In Mexico, four epidemic waves have been recorded with varying disease severity. To understand the heterogeneity in clinical presentation over time and the sensitivity and specificity of signs and symptoms in identifying COVID-19 cases, an analysis of the changes in the clinical presentation of the disease was conducted.

AIM

To analyze the changes in the clinical presentation of COVID-19 among 3.38 million individuals tested for SARS-CoV-2 at the Mexican Social Security Institute (IMSS) from March 2020 to October 2021 and evaluate the predictivity of signs and symptoms in identifying COVID-19 cases.

METHODS

A retrospective analysis of clinical presentation patterns of COVID-19 among individuals treated at IMSS was performed, contrasting the signs and symptoms among SARS-CoV-2-positive individuals with those who tested negative for the virus but had respiratory infection symptoms. The sensitivity and specificity of each sign and symptom in identifying SARS-CoV-2 infection were estimated.

RESULTS

The set of signs and symptoms reported for COVID-19-suspected patients treated at IMSS were not highly specific for SARS-CoV-2 positivity. The signs and symptoms exhibited variability based on age and epidemic wave. The area under the receiver operating characteristic (ROC) curve was 0.62 when grouping the five main symptoms (headache, dyspnea, fever, arthralgia, and cough). Most of the individual symptoms had ROC values close to 0.5 (16 out of 22 between 0.48 and 0.52), indicating non-specificity.

CONCLUSIONS

The results highlight the difficulty in making a clinical diagnosis of COVID-19 due to the lack of specificity of signs and symptoms. The variability of clinical presentation over time and among age groups highlights the need for further research to differentiate whether the changes are due to changes in the virus, who is becoming infected, or the population, particularly with respect to prior infection and vaccination status.

Impairment of Social-Related Quality of Life in COVID-19 Pneumonia Survivors: A Prospective Longitudinal Study

The post-acute sequelae of SARS-CoV-2 (PASC) pose a threat to patients' health-related quality of life (HRQOL). Here, the impact of COVID-19 on HRQOL and the clinical factors associated with impaired HRQOL were examined. Discharged COVID-19 patients were assessed at 3 and 6 months after disease onset. The patients completed a medical examination and the SF-36 questionnaire at these two time points and underwent pulmonary function testing at 6 months after disease onset. All had undergone computed tomography (CT) imaging upon hospital admission. Of the 74 included patients, 38% reported respiratory symptoms at 3 months, and 26% reported respiratory symptoms at 6 months after disease onset. The aggregated SF-36 scores declined in the role/social component summary (RCS), a category related to social activity. Patients with lower RCS tended to have respiratory sequelae or a relatively lower forced vital capacity. The CT score that reflected the extent of COVID-19 pneumonia was inversely correlated with the RCS score (3 months, p = 0.0024; 6 months, p = 0.0464). A high CT score (≥10 points) predicted a low RCS score at 6 months (p = 0.013). This study highlights the impairment of RCS and its associations with respiratory sequelae. The study also emphasizes the importance of radiological findings in predicting long-term HRQOL outcomes after COVID-19.

Performance of an AI algorithm during the different phases of the COVID pandemics: what can we learn from the AI and vice versa

Background

Artificial intelligence (AI) has proved to be of great value in diagnosing and managing Sars-Cov-2 infection. ALFABETO (ALL-FAster-BEtter-TOgether) is a tool created to support healthcare professionals in the triage, mainly in optimizing hospital admissions.

Methods

The AI was trained during the pandemic's "first wave" (February-April 2020). Our aim was to assess the performance during the "third wave" of the pandemics (February-April 2021) and evaluate its evolution. The neural network proposed behavior (hospitalization vs home care) was compared with what was actually done. If there were discrepancies between ALFABETO's predictions and clinicians' decisions, the disease's progression was monitored. Clinical course was defined as "favorable/mild" if patients could be managed at home or in spoke centers and "unfavorable/severe" if patients need to be managed in a hub center.

Results

ALFABETO showed accuracy of 76%, AUROC of 83%; specificity was 78% and recall 74%. ALFABETO also showed high precision (88%). 81 hospitalized patients were incorrectly predicted to be in "home care" class. Among those "home-cared" by the AI and "hospitalized" by the clinicians, 3 out of 4 misclassified patients (76.5%) showed a favorable/mild clinical course. ALFABETO's performance matched the reports in literature.

Conclusions

The discrepancies mostly occurred when the AI predicted patients could stay at home but clinicians hospitalized them; these cases could be handled in spoke centers rather than hubs, and the discrepancies may aid clinicians in patient selection. The interaction between AI and human experience has the potential to improve both AI performance and our comprehension of pandemic management.

The analysis of the effect of the COVID-19 pandemic on patients with hereditary angioedema type I and type II

Due to the similarity between the pathomechanism of SARS-CoV-2 infections and hereditary angioedema due to C1-inhibitor deficiency (C1-INH-HAE), a possibility emerged that C1-INH-HAE may worsen the course of the infection, or that the infection may influence the severity of angioedema (HAE) attacks in C1-INH-HAE patients. Our study aimed to evaluate the effects of the COVID-19 pandemic on the quality of life (QoL) of Hungarian C1-INH-HAE patients, and to survey the acute course of the infection, post COVID symptoms (PCS), vaccination coverage and the side effects of vaccines in this patient population. 93 patients completed our questionnaire between 1st July 2021 and 31st October 2021. In this same period and between March 2019 and March 2020, 63 patients completed the angioedema quality of life questionnaire (AE-QoL). Out of those patients infected with SARS-CoV-2 in the examined period (18/93 patients; 19%), 5% required hospitalization, 28% experienced HAE attacks in the acute phase of the infection, and 44% experienced PCS. A total number of 142 doses of vaccines were administered to the patients. Serious vaccine reactions did not occur in any case, 4 (5%) out of the 73 vaccinated patients experienced HAE attacks. No significant difference (p = 0.59) was found in the median of the AE-QoL total score, or in the number of HAE attacks prior and during the pandemic. Based on our study, HAE patients did not experience more serious SARS-CoV-2 infection, and it did not aggravate the course of HAE either. Changes in the QoL were not significant, and vaccines were safe in HAE patients.

Chest computed tomography findings of patients infected with Covid-19 and their association with disease evolution stages

INTRODUCTION

To describe CT findings in patients with confirmed Covid-19 infection and correlate them with the disease evolution stages.

METHODS

This is a historical cohort observational analytical study carried out with outpatients, inpatients, and emergency patients from a private hospital in Maceió/AL, Brazil. The final sample consisted of 390 patients with positive RT-PCR for Covid-19 with available laboratory tests and chest CT results.

RESULTS

The most frequent initial symptoms were cough, fever, dyspnea and headache. The most commonly found comorbidities were hypertension, diabetes mellitus and obesity. A total of 22% of the CT scans showed no alterations; ground-glass opacity was the most frequently found one. There was a significant association between age, comorbidities, pulmonary involvement, ground-glass opacity, mosaic attenuation and percentage of pulmonary involvement with death. The analysis of the disease stages showed a significant association with laboratory data (CRP and platelet levels), ground-glass opacity and mosaic attenuation with the disease evolution stages in relation to the days since symptom onset.

CONCLUSION

The disease evolution of Covid-19 occurs in stages, and this study describes tomographic findings in patients with confirmed Covid-19 infection and shows they vary depending on the disease evolution stages.

IMPLICATIONS FOR PRACTICE

This paper provides important addition to the various records that have been accumulated through the Covid-19 pandemic.

Solanum nigrum L. in COVID-19 and post-COVID complications: a propitious candidate

COVID-19 is caused by severe acute respiratory syndrome coronavirus-2, SARS-CoV-2. COVID-19 has changed the world scenario and caused mortality around the globe. Patients who recovered from COVID-19 have shown neurological, psychological, renal, cardiovascular, pulmonary, and hematological complications. In some patients, complications lasted more than 6 months. However, significantly less attention has been given to post-COVID complications. Currently available drugs are used to tackle the complications, but new interventions must address the problem. Phytochemicals from natural sources have been evaluated in recent times to cure or alleviate COVID-19 symptoms. An edible plant, Solanum nigrum, could be therapeutic in treating COVID-19 as the AYUSH ministry of India prescribes it during the pandemic. S. nigrum demonstrates anti-inflammatory, immunomodulatory, and antiviral action to treat the SARS-CoV-2 infection and its post-complications. Different parts of the plant represent a reduction in proinflammatory cytokines and prevent multi-organ failure by protecting various organs (liver, kidney, heart, neuro, and lung). The review proposes the possible role of the plant S. nigrum in managing the symptoms of COVID-19 and its post-COVID complications based on in silico docking and pharmacological studies. Further systematic and experimental studies are required to validate our hypothesis.

Hybrid optimized feature selection and deep learning based COVID-19 disease prediction

The COVID-19 virus has affected many people around the globe with several issues. Moreover, it causes a worldwide pandemic, and it makes more than one million deaths. Countries around the globe had to announce a complete lockdown when the corona virus causes the community to spread. In real-time, Polymerase Chain Reaction (RT-PCR) test is conducted to detect COVID-19, which is not effective and sensitive. Hence, this research presents the proposed Caviar-MFFO-assisted Deep LSTM scheme for COVID-19 detection. In this research, the COVID-19 cases data is utilized to process the COVID-19 detection. This method extracts the various technical indicators that improve the efficiency of COVID-19 detection. Moreover, the significant features fit for COVID-19 detection are selected using proposed mayfly with fruit fly optimization (MFFO). In addition, COVID-19 is detected by Deep Long Short Term Memory (Deep LSTM), and the Conditional Autoregressive Value at Risk MFFO (Caviar-MFFO) is modeled to train the weight of Deep LSTM. The experimental analysis reveals that the proposed Caviar-MFFO assisted Deep LSTM method provided efficient performance based on the Mean Squared Error (MSE) and Root Mean Squared Error (RMSE), and achieved the recovered cases with the minimal values of 1.438 and 1.199, whereas the developed model achieved the death cases with the values of 4.582 and 2.140 for MSE and RMSE. In addition, 6.127 and 2.475 are achieved by the developed model based on infected cases.

Diagnostic Efficacy of Chest Computed Tomography with a Dual-Reviewer Approach in Patients Diagnosed with Pneumonia Secondary to Severe Acute Respiratory Syndrome Coronavirus 2

To compare the diagnostic effectiveness of chest computed tomography (CT) utilizing a single- versus a dual-reviewer approach in patients with pneumonia secondary to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), we conducted a retrospective observational study of data from a cross-section of 4809 patients with probable SARS-CoV-2 from March to November 2020. All patients had a CT radiological report and reverse-transcription polymerase chain reaction (PCR) results. A dual-reviewer approach was applied to two groups while conducting a comparative examination of the data. Reviewer 1 reported 108 patients negative and 374 patients positive for coronavirus disease 2019 (COVID-19) in group A, and 266 negative and 142 positive in group B. Reviewer 2 reported 150 patients negative and 332 patients positive for COVID-19 in group A, and 277 negative and 131 positive in group B. The consensus result reported 87 patients negative and 395 positive for COVID-19 in group A and 274 negative and 134 positive in group B. These findings suggest that a dual-reviewer approach improves chest CT diagnosis compared to a conventional single-reviewer approach.

Generative Adversarial Network (Generative Artificial Intelligence) in Pediatric Radiology: A Systematic Review

Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1-158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely.

Development of the first PCR for detection of Psoroptes ovis var. cuniculi infection and its comparison to microscopic examination and serological assay in rabbits

Psoroptes mites are the common ecto-parasites of wild and domestic animals worldwide, which causes considerable economic losses in livestock industry. Microscopy is deemed to be the 'gold standard' for the diagnosis of Psoroptes mite infection but it has poor sensitivity for low mite infections and/or sub-clinical infections. To overcome these shortcomings, we screened four genes to develop a sensitive and specific PCR for the detection of Psoroptes mite infection in rabbits, and confirmed its practicability in detecting early infection and monitoring treatment outcome with traditional microscopy and serological tests. Results showed that PCR assay targeting ITS2 (ITS2-PCR) had a high specificity and sensitivity (detection limit: 40.3 pg/μL DNA) for detecting P. ovis DNA. In rabbits artificially infected with P. ovis, all three diagnostic tests showed the same detection rate from 14 days post infection (dpi) to 42 days dpi. However, these diagnostic tests behave differently at 7 dpi and after treatment: at 7 dpi, the detection rate of ITS2-PCR was higher than rPsoSP3-based iELISA and traditional microscopy (ITS2-PCR: 88.9%, rPsoSP3-iELISA: 77.7%, microscopy: 33.3%); at 7 days post treatment (dpt), positivity rates of ITS2-PCR and microscopy rapidly decreased to 0.00% and 11.1%, whereas rPsoSP3-iELISA remained 100% positive rate. Furthermore, the comprehensive comparisons of diagnostic performance and features of three diagnostic tests at 7 dpi were performed. Compared to ITS2-PCR or rPsoSP3-iELISA, microscopy had the lowest sensitivity, and the agreement between these assays was low (κ < 0.3). Field study showed that ITS2-PCR showed a higher detection rate than microscopy (19.4% and 11.1%, respectively). Our results suggested that the ITS2-PCR developed in this study provided a new laboratory tool for diagnosis of P. ovis var. cuniculi infection, and it had advantages over microscopic examination in detection low-level mite infections and serological assay in monitoring treatment outcome.

Pulmonary artery diameter and NT-proBNP in patients with Covid-19: Predicting prognosis and mortality

Background

The diverse and complex presentations of COVID-19 continue to impact the world. Factors related to prognosis and mortality are still not fully illuminated.

Objectives

We aimed to asses the relationship of N-terminal pro B-type natriuretic peptide (NT-proBNP) and main pulmonary artery diameter (MPAD) with COVID-19 prognosis and mortality.

Methods

152 COVID-19 patients over the age of 18, were included in the study. Thoracic CT, NT-proBNP values, laboratory and demographic data of these patients were obtained by retrospectively examining the patient files and scanning the results through the patient registry.

Results

According to multivariate logistic regression (LR) analysis, high NT-proBNP level (OR=3.542; 95% CI=1.745-9.463; p=0.021) and MPAD/ascending aortic diameter (AAD) ratio>0.75 (OR=2.692; 95% CI=1.264-9.312; p=0.036) were determined as independent risk factors predicting mortality in COVID-19 patients. A significant positive correlation was observed between NT-proBNP level and MPA diameter (r=0.296, p<0.001). The cut-off value was measured as 27.5 mm for MPA diameter and 742 pg/ml for NT-proBNP.

Conclusions

Accurate and effective interpretation of available radiological and laboratory data is essential to reveal the factors predicting prognosis and mortality in COVID-19. In this study,we evaluated that the thorax CTs and determined that the MPAD/AAD and NT-proBNP level were independent risk factors in predicting mortality.

Qualitative and semi-quantitative ultrasound assessment in delta and Omicron Covid-19 patients: data from high volume reference center

OBJECTIVE

to evaluate the efficacy of US, both qualitatively and semi-quantitatively, in the selection of treatment for the Covid-19 patient, using patient triage as the gold standard.

METHODS

Patients admitted to the Covid-19 clinic to be treated with monoclonal antibodies (mAb) or retroviral treatment and undergoing lung ultrasound (US) were selected from the radiological data set between December 2021 and May 2022 according to the following inclusion criteria: patients with proven Omicron variant and Delta Covid-19 infection; patients with known Covid-19 vaccination with at least two doses. Lung US (LUS) was performed by experienced radiologists. The presence, location, and distribution of abnormalities, such as B-lines, thickening or ruptures of the pleural line, consolidations, and air bronchograms, were evaluated. The anomalous findings in each scan were classified according to the LUS scoring system. Nonparametric statistical tests were performed.

RESULTS

The LUS score median value in the patients with Omicron variant was 1.5 (1-20) while the LUS score median value in the patients with Delta variant was 7 (3-24). A difference statistically significant was observed for LUS score values among the patients with Delta variant between the two US examinations (p value = 0.045 at Kruskal Wallis test). There was a difference in median LUS score values between hospitalized and non-hospitalized patients for both the Omicron and Delta groups (p value = 0.02 on the Kruskal Wallis test). For Delta patients groups the sensitivity, specificity, positive and negative predictive values, considering a value of 14 for LUS score for the hospitalization, were of 85.29%, 44.44%, 85.29% and 76.74% respectively.

CONCLUSIONS

LUS is an interesting diagnostic tool in the context of Covid-19, it could allow to identify the typical pattern of diffuse interstitial pulmonary syndrome and could guide the correct management of patients.

Predicting omicron pneumonia severity and outcome: a single-center study in Hangzhou, China

Background

In December 2022, there was a large Omicron epidemic in Hangzhou, China. Many people were diagnosed with Omicron pneumonia with variable symptom severity and outcome. Computed tomography (CT) imaging has been proven to be an important tool for COVID-19 pneumonia screening and quantification. We hypothesized that CT-based machine learning algorithms can predict disease severity and outcome in Omicron pneumonia, and we compared its performance with the pneumonia severity index (PSI)-related clinical and biological features.

Methods

Our study included 238 patients with the Omicron variant who have been admitted to our hospital in China from 15 December 2022 to 16 January 2023 (the first wave after the dynamic zero-COVID strategy stopped). All patients had a positive real-time polymerase chain reaction (PCR) or lateral flow antigen test for SARS-CoV-2 after vaccination and no previous SARS-CoV-2 infections. We recorded patient baseline information pertaining to demographics, comorbid conditions, vital signs, and available laboratory data. All CT images were processed with a commercial artificial intelligence (AI) algorithm to obtain the volume and percentage of consolidation and infiltration related to Omicron pneumonia. The support vector machine (SVM) model was used to predict the disease severity and outcome.

Results

The receiver operating characteristic (ROC) area under the curve (AUC) of the machine learning classifier using PSI-related features was 0.85 (accuracy = 87.40%, p < 0.001) for predicting severity while that using CT-based features was only 0.70 (accuracy = 76.47%, p = 0.014). If combined, the AUC was not increased, showing 0.84 (accuracy = 84.03%, p < 0.001). Trained on outcome prediction, the classifier reached the AUC of 0.85 using PSI-related features (accuracy = 85.29%, p < 0.001), which was higher than using CT-based features (AUC = 0.67, accuracy = 75.21%, p < 0.001). If combined, the integrated model showed a slightly higher AUC of 0.86 (accuracy = 86.13%, p < 0.001). Oxygen saturation, IL-6, and CT infiltration showed great importance in both predicting severity and outcome.

Conclusion

Our study provided a comprehensive analysis and comparison between baseline chest CT and clinical assessment in disease severity and outcome prediction in Omicron pneumonia. The predictive model accurately predicts the severity and outcome of Omicron infection. Oxygen saturation, IL-6, and infiltration in chest CT were found to be important biomarkers. This approach has the potential to provide frontline physicians with an objective tool to manage Omicron patients more effectively in time-sensitive, stressful, and potentially resource-constrained environments.

A Survey of COVID-19 Diagnosis Using Routine Blood Tests with the Aid of Artificial Intelligence Techniques

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), causing a disease called COVID-19, is a class of acute respiratory syndrome that has considerably affected the global economy and healthcare system. This virus is diagnosed using a traditional technique known as the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, RT-PCR customarily outputs a lot of false-negative and incorrect results. Current works indicate that COVID-19 can also be diagnosed using imaging resolutions, including CT scans, X-rays, and blood tests. Nevertheless, X-rays and CT scans cannot always be used for patient screening because of high costs, radiation doses, and an insufficient number of devices. Therefore, there is a requirement for a less expensive and faster diagnostic model to recognize the positive and negative cases of COVID-19. Blood tests are easily performed and cost less than RT-PCR and imaging tests. Since biochemical parameters in routine blood tests vary during the COVID-19 infection, they may supply physicians with exact information about the diagnosis of COVID-19. This study reviewed some newly emerging artificial intelligence (AI)-based methods to diagnose COVID-19 using routine blood tests. We gathered information about research resources and inspected 92 articles that were carefully chosen from a variety of publishers, such as IEEE, Springer, Elsevier, and MDPI. Then, these 92 studies are classified into two tables which contain articles that use machine Learning and deep Learning models to diagnose COVID-19 while using routine blood test datasets. In these studies, for diagnosing COVID-19, Random Forest and logistic regression are the most widely used machine learning methods and the most widely used performance metrics are accuracy, sensitivity, specificity, and AUC. Finally, we conclude by discussing and analyzing these studies which use machine learning and deep learning models and routine blood test datasets for COVID-19 detection. This survey can be the starting point for a novice-/beginner-level researcher to perform on COVID-19 classification.

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records

BACKGROUND

An artificial-intelligence (AI) model for predicting the prognosis or mortality of coronavirus disease 2019 (COVID-19) patients will allow efficient allocation of limited medical resources. We developed an early mortality prediction ensemble model for COVID-19 using AI models with initial chest X-ray and electronic health record (EHR) data.

RESULTS

We used convolutional neural network (CNN) models (Inception-ResNet-V2 and EfficientNet) for chest X-ray analysis and multilayer perceptron (MLP), Extreme Gradient Boosting (XGBoost), and random forest (RF) models for EHR data analysis. The Gradient-weighted Class Activation Mapping and Shapley Additive Explanations (SHAP) methods were used to determine the effects of these features on COVID-19. We developed an ensemble model (Area under the receiver operating characteristic curve of 0.8698) using a soft voting method with weight differences for CNN, XGBoost, MLP, and RF models. To resolve the data imbalance, we conducted F1-score optimization by adjusting the cutoff values to optimize the model performance (F1 score of 0.77).

CONCLUSIONS

Our study is meaningful in that we developed an early mortality prediction model using only the initial chest X-ray and EHR data of COVID-19 patients. Early prediction of the clinical courses of patients is helpful for not only treatment but also bed management. Our results confirmed the performance improvement of the ensemble model achieved by combining AI models. Through the SHAP method, laboratory tests that indicate the factors affecting COVID-19 mortality were discovered, highlighting the importance of these tests in managing COVID-19 patients.

Artificial intelligence for reducing the radiation burden of medical imaging for the diagnosis of coronavirus disease

Medical imaging has been intensively employed in screening, diagnosis and monitoring during the COVID-19 pandemic. With the improvement of RT-PCR and rapid inspection technologies, the diagnostic references have shifted. Current recommendations tend to limit the application of medical imaging in the acute setting. Nevertheless, efficient and complementary values of medical imaging have been recognized at the beginning of the pandemic when facing unknown infectious diseases and a lack of sufficient diagnostic tools. Optimizing medical imaging for pandemics may still have encouraging implications for future public health, especially for long-lasting post-COVID-19 syndrome theranostics. A critical concern for the application of medical imaging is the increased radiation burden, particularly when medical imaging is used for screening and rapid containment purposes. Emerging artificial intelligence (AI) technology provides the opportunity to reduce the radiation burden while maintaining diagnostic quality. This review summarizes the current AI research on dose reduction for medical imaging, and the retrospective identification of their potential in COVID-19 may still have positive implications for future public health.

Global prevalence of coronavirus disease 2019 reinfection: a systematic review and meta-analysis

BACKGROUND

In December 2019, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) emerged with a high transmissibility rate and resulted in numerous negative impacts on global life. Preventive measures such as face masks, social distancing, and vaccination helped control the pandemic. Nonetheless, the emergence of SARS-CoV-2 variants, such as Omega and Delta, as well as coronavirus disease 2019 (COVID-19) reinfection, raise additional concerns. Therefore, this study aimed to determine the overall prevalence of reinfection on global and regional scales.

METHODS

A systematic search was conducted across three databases, PubMed, Scopus, and ProQuest Central, including all articles pertaining to COVID-19 reinfection without language restriction. After critical appraisal and qualitative synthesis of the identified relevant articles, a meta-analysis considering random effects was used to pool the studies.

RESULTS

We included 52 studies conducted between 2019 and 2022, with a total sample size of 3,623,655 patients. The overall prevalence of COVID-19 reinfection was 4.2% (95% confidence interval [CI]: 3.7-4.8%; n = 52), with high heterogeneity between studies. Africa had the highest prevalence of 4.7% (95% CI: 1.9-7.5%; n = 3), whereas Oceania and America had lower estimates of 0.3% (95% CI: 0.2-0.4%; n = 1) and 1% (95% CI: 0.8-1.3%; n = 7), respectively. The prevalence of reinfection in Europe and Asia was 1.2% (95% CI: 0.8-1.5%; n = 8) and 3.8% (95% CI: 3.4-4.3%; n = 43), respectively. Studies that used a combined type of specimen had the highest prevalence of 7.6% (95% CI: 5.8-9.5%; n = 15) compared with those that used oropharyngeal or nasopharyngeal swabs only that had lower estimates of 6.7% (95% CI: 4.8-8.5%; n = 8), and 3.4% (95% CI: 2.8-4.0%; n = 12) respectively.

CONCLUSION

COVID-19 reinfection occurs with varying prevalence worldwide, with the highest occurring in Africa. Therefore, preventive measures, including vaccination, should be emphasized to ensure control of the pandemic.

Pulmonary computed tomographic manifestations of COVID-19 in vaccinated and non-vaccinated patients

This study aimed to analyze computed tomographic (CT) imaging features of vaccinated and non-vaccinated COVID-19 patients. The study population of this retrospective single-center cohort study consisted of hospitalized COVID-19 patients who received a chest CT at the study site between July 2021 and February 2022. Qualitative scoring systems (RSNA, CO-RADS, COV-RADS), imaging pattern analysis and semi-quantitative scoring of lung changes were assessed. 105 patients (70,47% male, 62.1 ± 16.79 years, 53.3% fully vaccinated) were included in the data analysis. A significant association between vaccination status and the presence of the crazy-paving pattern was observed in univariate analysis and persisted after step-wise adjustment for possible confounders in multivariate analysis (RR: 2.19, 95% CI: [1.23, 2.62], P = 0.024). Scoring systems for probability assessment of the presence of COVID-19 infection showed a significant correlation with the vaccination status in univariate analysis; however, the associations were attenuated after adjustment for virus variant and stage of infection. Semi-quantitative assessment of lung changes due to COVID-19 infection revealed no association with vaccination status. Non-vaccinated patients showed a two-fold higher probability of the crazy-paving pattern compared to vaccinated patients. COVID-19 variants could have a significant impact on the CT-graphic appearance of COVID-19.

Effectiveness of Using the FreeStyle Libre® System for Monitoring Blood Glucose during the COVID-19 Pandemic in Diabetic Individuals: Systematic Review

BACKGROUND

Artificial Intelligence (AI) is an area of computer science/engineering that is aiming to spread technological systems. The COVID-19 pandemic caused economic and public health turbulence around the world. Among the many possibilities for using AI in the medical field is FreeStyle Libre^® (FSL), which uses a disposable sensor inserted into the user's arm, and a touchscreen device/reader is used to scan and retrieve other continuous monitoring of glucose (CMG) readings. The aim of this systematic review is to summarize the effectiveness of FSL blood glucose monitoring during the COVID-19 pandemic.

METHODS

This systematic review was carried out in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) and was registered in the international prospective register of systematic reviews (PROSPERO: CRD42022340562). The inclusion criteria considered studies involving the use of the FSL device during the COVID-19 pandemic and published in English. No publication date restrictions were set. The exclusion criteria were abstracts, systematic reviews, studies with patients with other diseases, monitoring with other equipment, patients with COVID-19, and bariatrics patients. Seven databases were searched (PubMed, Scopus, Embase, Web of Science, Scielo, PEDro and Cochrane Library). The ACROBAT-NRSI tool (A Cochrane Risk of Bias Assessment Tool for Non-Randomized Studies) was used to evaluate the risk of bias in the selected articles.

RESULTS

A total of 113 articles were found. Sixty-four were excluded because they were duplicates, 39 were excluded after reading the titles and abstracts, and twenty articles were considered for full reading. Of the 10 articles analyzed, four articles were excluded because they did not meet the inclusion criteria. Thus, six articles were included in the current systematic review. It was observed that among the selected articles, only two were classified as having serious risk of bias. It was shown that FSL had a positive impact on glycemic control and on reducing the number of individuals with hypoglycemia.

CONCLUSION

The findings suggest that the implementation of FSL during COVID-19 confinement in this population can be confidently stated to have been effective in diabetes mellitus patients.

Magnetic biosensors for identification of SARS-CoV-2, Influenza, HIV, and Ebola viruses: a review

Infectious diseases such as novel coronavirus (SARS-CoV-2), Influenza, HIV, Ebola, etc kill many people around the world every year (SARS-CoV-2 in 2019, Ebola in 2013, HIV in 1980, Influenza in 1918). For example, SARS-CoV-2 has plagued higher than 317 000 000 people around the world from December 2019 to January 13, 2022. Some infectious diseases do not yet have not a proper vaccine, drug, therapeutic, and/or detection method, which makes rapid identification and definitive treatments the main challenges. Different device techniques have been used to detect infectious diseases. However, in recent years, magnetic materials have emerged as active sensors/biosensors for detecting viral, bacterial, and plasmids agents. In this review, the recent applications of magnetic materials in biosensors for infectious viruses detection have been discussed. Also, this work addresses the future trends and perspectives of magnetic biosensors.

Utility of RT-PCR versus electronic track and trace system for pre-procedural COVID-19 screening- a retrospective cohort study

Background and aims

COVID-19 has disrupted the patient workflow in all healthcare settings. Procedures such as bronchoscopy and spirometry require additional pre-procedure screening for SARS-CoV-2. However, there is uncertainty regarding the utility of this universal pre-procedure screening. The State of Qatar has a robust contact tracing system in place in the form of the mobile application 'Ehteraz.' This study assesses the utility of various pre-procedural screening measures in asymptomatic patients and generate recommendations for any potential improvement in the workflow.

Methods

This is a cross-sectional study of asymptomatic patients who had SARS-CoV-2 RT-PCR screening performed before bronchoscopy or lung function testing scheduled on an elective basis. Descriptive statistics were used to summarize and determine the sample characteristics. The rate of the positive PCR test result was subsequently calculated.

Results

Two patients (0.34%) tested positive for COVID-19 on their pre-procedural screen. Four patients (0.68%) had an inconclusive result.

Conclusion

The positivity rate of SARS-CoV-2 RT-PCR is extremely low in asymptomatic individuals screened before bronchoscopy and spirometry. The authors recommend pre-procedural symptom and electronic application-based contact screening instead of universal pre-procedural SARS-CoV-2 RT-PCR for screening asymptomatic individuals.

Relationship between Underlying Diseases with Morbidity and Mortality in Patients with COVID-19

Background

This study aims to investigate the clinical and demographic features of underlying medical conditions and the potential relationship between underlying diseases and the increased rate of morbidity and mortality due to COVID-19.

Materials and Methods

This study was conducted on 350 COVID-19 patients hospitalized at the Masih Daneshvari Hospital from February-July 2021. All participants had confirmed COVID-19 diagnosis based on symptoms and/or positive PCR test or chest X-ray results. Data was collected from medical records on demographics, disease severity, symptoms, underlying conditions like diabetes, hypertension, coronary heart disease, obesity, renal disease/transplantation, and outcomes like hospital stay, ICU admission, and mortality. Relationships between age, underlying diseases, and mortality were analyzed using chi-square and Fisher's exact tests."

Results

A total of 350 patients diagnosed with COVID-19 were included in the study, with an average estimated age of (60.8±15.4). The age group of 56 and above had the highest morbidity rate, which accounted for 50% of the total participants. Among the COVID-19 patients, diabetes was the most common underlying medical condition, accounting for 31.4% of the cases. High blood pressure was present in 27.1% of the patients, and 17.1% of the total participants had coronary heart disease (CHD). Additionally, 10.9% of the participants were overweight, and 30 of them had previously experienced kidney failure or transplantation. Moreover, the study found that 40% of patients with diabetes died, while the mortality rate was 38.3% in patients with CHD and 47.4% in overweight participants. High blood pressure patients had a mortality rate of 43.2%, and patients with renal failure or kidney transplantation had a significantly increased risk of mortality at 83.3%. The research also revealed a significant and direct relationship between mortality rate, age group, and underlying disease among the patients (P<0.05).

Conclusion

The findings of the present study hold significant implications for preventive interventions and policy adoption, particularly in relation to the use of calendar age as the key criterion for risk evaluation. These results underscore the need for a more precise and focused approach to prioritizing patients with identified risk factors.

The impact of Covid-19 pandemic on modification of medical teaching in Italy: A narrative review

During the first wave of Covid-19 in Italy, there was a problem with University. Universities couldn't do face-to-face (FTF) lessons and started to do online lessons (OL). This study investigates the impressions of students, teachers, and institutions during the first wave situation. A search was conducted on the main international databases, and only studies conducted in Italy starting during the Covid-19 pandemic are considered. 9 studies tell about the impressions of students about OL lessons, and 10 studies speak about medical resident's situation and teacher's impressions. Studies about students give conflicting results, teachers are generally satisfied with the contents, but agree on the difficulty of not having relationships with students. Medical residents have reduced significantly the clinical and surgical practice, sometimes increasing the research. In the future, it is indispensable to create a system that guarantees the efficacy of FTF lessons for practice, it is still low in sanitary and medical courses in Italy during the pandemic period.

The Role of Computed Tomography in the Management of Hospitalized Patients With COVID-19

The emergence of SARS-CoV-2 at the end of 2019 sparked the beginning of the COVID-19 pandemic. Even though it was a novel virus, the workup of suspected COVID-19 included standard protocols used for the investigation of similar respiratory infections and pneumonia. One of the most important diagnostic tests in this regard is computed tomography (CT). CT scans have a high sensitivity in diagnosing COVID-19, and many of the characteristic imaging findings of COVID-19 are used in its diagnosis. The role of CT in COVID-19 management is expanding as more and more hospital practices adopt regular CT use in both the initial workup and continued care of COVID-19 patients. CT has helped hospitalists diagnose complications such as pulmonary embolism, subcutaneous emphysema, pneumomediastinum, pneumothoraces, and nosocomial pneumonia. Although mainly used as a diagnostic tool, the prognostic role of CT in COVID-19 patients is developing. In this review, we explore the role of CT in the management of hospitalized patients with COVID-19, specifically elucidating its use as a diagnostic and prognostic modality, as well as its ability to guide hospital decision-making regarding complex cases. We will highlight important time points when CT scans are used: the initial encounter, the time at admission, and during hospitalization.

Active regression model for clinical grading of COVID-19

Background

In the therapeutic process of COVID-19, the majority of indicators that physicians have for assisting treatment have come from clinical tests represented by proteins, metabolites, and immune levels in patients' blood. Therefore, this study constructs an individualized treatment model based on deep learning methods, aiming to realize timely intervention based on clinical test indicator data of COVID-19 patients and provide an important theoretical basis for optimizing medical resource allocation.

Methods

This study collected clinical data from a total of 1,799 individuals, including 560 controls for non-respiratory infectious diseases (Negative), 681 controls for other respiratory virus infections (Other), and 558 coronavirus infections (Positive) for COVID-19. We first used the Student T-test to screen for statistically significant differences (Pvalue<0.05); we then used the Adaptive-Lasso method stepwise regression to screen the characteristic variables and filter the features with low importance; we then used analysis of covariance to calculate the correlation between variables and filter the highly correlated features; and finally, we analyzed the feature contribution and screened the best combination of features.

Results

Feature engineering reduced the feature set to 13 feature combinations. The correlation coefficient between the projected results of the artificial intelligence-based individualized diagnostic model and the fitted curve of the actual values in the test group was 0.9449 which could be applied to the clinical prognosis of COVID-19. In addition, the depletion of platelets in patients with COVID-19 is an important factor affecting their severe deterioration. With the progression of COVID-19, there is a slight decrease in the total number of platelets in the patient's body, particularly as the volume of larger platelets sharply decreases. The importance of plateletCV (count*mean platelet volume) in evaluating the severity of COVID-19 patients is higher than the count of platelets and mean platelet volume.

Conclusion

In general, we found that for patients with COVID-19, the increase in mean platelet volume was a predictor for SARS-Cov-2. The rapid decrease of platelet volume and the decrease of total platelet volume are dangerous signals for the aggravation of SARS-Cov-2 infection. The analysis and modeling results of this study provide a new perspective for individualized accurate diagnosis and treatment of clinical COVID-19 patients.

Increasing cardiac troponin-I level as a cardiac injury index correlates with in-hospital mortality and biofactors in severe hospitalised COVID-19 patients

BACKGROUND

Severe acute respiratory syndrome coronavirus-2 raised in 2019 (COVID-19) affects the lung tissue and other organs, specifically the heart.

METHODS

The current study evaluated 120 hospitalised patients with severe COVID-19 between March 2021 and February 2022. Patients' demographics, vital signs, electrocardiogram abnormalities, clinical laboratory tests, including troponin I (TPI), mortality, and discharge type, were recorded.

RESULTS

Among the 120 hospitalised patients with severe COVID-19, 54 (45.0%) patients were male, with an average age of 63.2 ± 1.4. Many patients have chronic comorbidities, including hypertension (51.6%), diabetes mellitus (34.1%), and ischemic heart disease (17.5%). The in-hospital and six months after the discharge mortality were 45.8% and 21.5%, respectively. Cardiac injury was observed in 14 (11.7%) patients with a mean TPI level of 8.386 ± 17.89 μg/L, and patients with cardiac injury had higher mortality than those without cardiac injury (P < 0.001). Furthermore, the cardiac injury was meaningfully correlated with age (ρ = 0.182, P = 0.019), history of ischemic heart disease (ρ = 0.176, P = 0.05), hospitalisation result and mortality (ρ = 0.261, P = 0.004), inpatient in ICU (ρ = 0.219, P = 0.016), and serum levels of urea (ρ = 0.244, P = 0.008) and creatinine (ρ = 0.197, P = 0.033). Additionally, the discharge results were significantly correlated with oxygen saturation with (ρ = -0.23, P = 0.02) and without (ρ = -0.3, P = 0.001) oxygen therapy, D-dimer (ρ = 0.328, P = 0.019), LDH (ρ = 0.308, P = 0.003), urea (ρ = 0.2, P = 0.03), and creatinine (ρ = 0.17, P = 0.06) levels.

CONCLUSION

Elevated TPI levels are associated with increased mortality in severe COVID-19 patients. Therefore, TPI may be a beneficial biofactor for early diagnosis of cardiac injury and preventing a high mortality rate.

A deep convolutional neural network ensemble for composite identification of pulmonary nodules and incidental findings on routine PET/CT

AIM

To evaluate primary and secondary pathologies of interest using an artificial intelligence (AI) platform, AI-Rad Companion, on low-dose computed tomography (CT) series from integrated positron-emission tomography (PET)/CT to detect CT findings that might be overlooked.

MATERIALS AND METHODS

One hundred and eighty-nine sequential patients who had undergone PET/CT were included. Images were evaluated using an ensemble of convolutional neural networks (AI-Rad Companion, Siemens Healthineers, Erlangen, Germany). The primary outcome was detection of pulmonary nodules for which the accuracy, identity, and intra-rater reliability was calculated. For secondary outcomes (binary detection of coronary artery calcium, aortic ectasia, vertebral height loss), accuracy and diagnostic performance were calculated.

RESULTS

The overall per-nodule accuracy for detection of lung nodules was 0.847. The overall sensitivity and specificity for detection of lung nodules was 0.915 and 0.781. The overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia, and vertebral height loss was 0.979, 0.966, and 0.840, respectively. The sensitivity and specificity for coronary artery calcium was 0.989 and 0.969. The sensitivity and specificity for aortic ectasia was 0.806 and 1.

CONCLUSION

The neural network ensemble accurately assessed the number of pulmonary nodules and presence of coronary artery calcium and aortic ectasia on low-dose CT series of PET/CT. The neural network was highly specific for the diagnosis of vertebral height loss, but not sensitive. The use of the AI ensemble can help radiologists and nuclear medicine physicians to catch CT findings that might be overlooked.

Two Cases of Familial Mediterranean Fever Involving MEFV Variants: The Importance of Differentiating the Diagnosis from COVID-19

Familial Mediterranean fever (FMF) is an inherited autoinflammatory disease associated with the MEFV gene. FMF is common in Mediterranean peoples but not highly recognized in Japan. We herein report two cases of Japanese FMF patients who were diagnosed by genetic testing for the MEFV gene during the coronavirus disease 2019 (COVID-19) pandemic. Both patients presented with symptoms similar to COVID-19, which delayed the definitive diagnosis. Patients with a confirmed diagnosis of FMF may be eligible for physical, emotional, and financial benefits. Therefore, the COVID-19 pandemic highlights the importance of differentiating the diagnosis by genetic testing.

Novel Affibody Molecules Specifically Bind to SARS-CoV-2 Spike Protein and Efficiently Neutralize Delta and Omicron Variants

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has been an unprecedented public health disaster in human history, and its spike (S) protein is the major target for vaccines and antiviral drug development. Although widespread vaccination has been well established, the viral gene is prone to rapid mutation, resulting in multiple global spread waves. Therefore, specific antivirals are needed urgently, especially those against variants. In this study, the domain of the receptor binding motif (RBM) and fusion peptide (FP) (amino acids [aa] 436 to 829; denoted RBMFP) of the SARS-CoV-2 S protein was expressed as a recombinant RBMFP protein in Escherichia coli and identified as being immunogenic and antigenically active. Then, the RBMFP proteins were used for phage display to screen the novel affibody. After prokaryotic expression and selection, four novel affibody molecules (Z14, Z149, Z171, and Z327) were obtained. Through surface plasmon resonance (SPR) and pseudovirus neutralization assay, we showed that affibody molecules specifically bind to the RBMFP protein with high affinity and neutralize against SARS-CoV-2 pseudovirus infection. Especially, Z14 and Z171 displayed strong neutralizing activities against Delta and Omicron variants. Molecular docking predicted that affibody molecule interaction sites with RBM overlapped with ACE2. Thus, the novel affibody molecules could be further developed as specific neutralization agents against SARS-CoV-2 variants. IMPORTANCE SARS-CoV-2 and its variants are threatening the whole world. Although a full dose of vaccine injection showed great preventive effects and monoclonal antibody reagents have also been used for a specific treatment, the global pandemic persists. So, developing new vaccines and specific agents are needed urgently. In this work, we expressed the recombinant RBMFP protein as an antigen, identified its antigenicity, and used it as an antigen for affibody phage-display selection. After the prokaryotic expression, the specific affibody molecules were obtained and tested for pseudovirus neutralization. Results showed that the serum antibody induced by RBMFP neutralized Omicron variants. The screened affibody molecules specifically bound the RBMFP of SARS-CoV-2 with high affinity and neutralized the Delta and Omicron pseudovirus in vitro. So, the RBMFP induced serum provides neutralizing effects against pseudovirus in vitro, and the affibodies have the potential to be developed into specific prophylactic agents for SARS-CoV-2 and its variants.

Alzheimer's disease and COVID-19: Interactions, intrinsic linkages, and the role of immunoinflammatory responses in this process

Alzheimer's disease (AD) and COVID-19 share many common risk factors, such as advanced age, complications, APOE genotype, etc. Epidemiological studies have also confirmed the internal relationship between the two diseases. For example, studies have found that AD patients are more likely to suffer from COVID-19, and after infection with COVID-19, AD also has a much higher risk of death than other chronic diseases, and what's more interesting is that the risk of developing AD in the future is significantly higher after infection with COVID-19. Therefore, this review gives a detailed introduction to the internal relationship between Alzheimer's disease and COVID-19 from the perspectives of epidemiology, susceptibility and mortality. At the same time, we focused on the important role of inflammation and immune responses in promoting the onset and death of AD from COVID-19.

COVID-19 and hepatic injury: cellular and molecular mechanisms in diverse liver cells

The coronavirus disease 2019 (COVID-19) represents a global health and economic challenge. Hepatic injuries have been approved to be associated with severe acute respiratory syndrome coronavirus (SARS-CoV-2) infection. The viral tropism pattern of SARS-CoV-2 can induce hepatic injuries either by itself or by worsening the conditions of patients with hepatic diseases. Besides, other factors have been reported to play a crucial role in the pathological forms of hepatic injuries induced by SARS-CoV-2, including cytokine storm, hypoxia, endothelial cells, and even some treatments for COVID-19. On the other hand, several groups of people could be at risk of hepatic COVID-19 complications, such as pregnant women and neonates. The present review outlines and discusses the interplay between SARS-CoV-2 infection and hepatic injury, hepatic illness comorbidity, and risk factors. Besides, it is focused on the vaccination process and the role of developed vaccines in preventing hepatic injuries due to SARS-CoV-2 infection.

A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative

BACKGROUND

Recently, artificial intelligence (AI)-based applications for chest imaging have emerged as potential tools to assist clinicians in the diagnosis and management of patients with coronavirus disease 2019 (COVID-19).

OBJECTIVES

To develop a deep learning-based clinical decision support system for automatic diagnosis of COVID-19 on chest CT scans. Secondarily, to develop a complementary segmentation tool to assess the extent of lung involvement and measure disease severity.

METHODS

The Imaging COVID-19 AI initiative was formed to conduct a retrospective multicentre cohort study including 20 institutions from seven different European countries. Patients with suspected or known COVID-19 who underwent a chest CT were included. The dataset was split on the institution-level to allow external evaluation. Data annotation was performed by 34 radiologists/radiology residents and included quality control measures. A multi-class classification model was created using a custom 3D convolutional neural network. For the segmentation task, a UNET-like architecture with a backbone Residual Network (ResNet-34) was selected.

RESULTS

A total of 2,802 CT scans were included (2,667 unique patients, mean [standard deviation] age = 64.6 [16.2] years, male/female ratio 1.3:1). The distribution of classes (COVID-19/Other type of pulmonary infection/No imaging signs of infection) was 1,490 (53.2%), 402 (14.3%), and 910 (32.5%), respectively. On the external test dataset, the diagnostic multiclassification model yielded high micro-average and macro-average AUC values (0.93 and 0.91, respectively). The model provided the likelihood of COVID-19 vs other cases with a sensitivity of 87% and a specificity of 94%. The segmentation performance was moderate with Dice similarity coefficient (DSC) of 0.59. An imaging analysis pipeline was developed that returned a quantitative report to the user.

CONCLUSION

We developed a deep learning-based clinical decision support system that could become an efficient concurrent reading tool to assist clinicians, utilising a newly created European dataset including more than 2,800 CT scans.

Total severity score and age predict long-term hospitalization in COVID-19 pneumonia

Background

Severe COVID-19 pneumonia implies increased oxygen demands and length of hospitalization (LOS). We aimed to assess a possible correlation between LOS and COVID-19 patients' clinical laboratory data of admission, including the total severity score (TSS) from chest computed tomography (CT).

Methods

Data were assessed retrospectively at the General Hospital "Agios Pavlos" in Greece. Clinical laboratory data, TSS, and LOS were recorded.

Results

A total of 317 patients, 136 women and 181 men, with a mean age of 66.58 ± 16.02 years were studied. Significant comorbidities were hypertension (56.5%), dyslipidemia (33.8%), type 2 diabetes mellitus (22.7%), coronary heart disease (12.9%), underlying pulmonary disease (10.1%), and malignancy (4.4%). Inpatient time was related to age (p < 0.001), TSS (p < 0.001), time from symptom onset to hospitalization (p = 0.006), inhaled oxygen fraction (p < 0.001), fibrinogen (p = 0.024), d-dimers (p < 0.001), and C-reactive protein (p = 0.025), as well as a history of hypertension (p < 0.001) and type 2 diabetes mellitus (p < 0.008). The multivariate analysis showed a significant association of the LOS with age (p < 0.001) and TSS (p < 0.001) independent of the above-mentioned factors.

Conclusion

Early identification of disease severity using the TSS and patients' age could be useful for inpatient resource allocation and for maintaining vigilance for those requiring long-term hospitalizations.