Correlation between lung infection severity and clinical laboratory indicators in patients with COVID-19: a cross-sectional study based on machine learning

COVID outcome in pemphigus: Does rituximab make pemphigus patients susceptible to more severe COVID-19?

BACKGROUND

The COVID-19 pandemic has raised some concerns regarding the management of chronic skin diseases, especially in patients on immunosuppressive therapy including patients with pemphigus vulgaris (PV). Literature review reveals conflicting results about the effect of monoclonal antibodies such as rituximab on clinical outcome of COVID-19.

OBJECTIVES

To assess the reciprocal interaction of COVID-19 and pemphigus and the effect of rituximab on prognosis of COVID-19 in patients.

METHODS

We set up a retrospective study on adult patients with a confirmed diagnosis of pemphigus vulgaris and a history of COVID-19 with or without symptoms during 2020.

RESULTS

Thirty-six adults with pemphigus vulgaris and SARS-CoV-2 infection were included. The SARS-CoV-2 infection was confirmed with positive RT-PCR test results in 31 cases (86.1%) and suspected in the 5 others (13.9%). Gender, total dose of rituximab, number of rituximab cycles, and involvement of head and neck were not associated to duration of COVID-19 symptoms (p values: 0.32, 0.23, 0.84, and 0.51, respectively), severity of disease (hospitalization) (p values: 0.46, 0.39, 0.23, and 0.72, respectively), or the percentage of lung involvement on CT scan (p values: 0.07, 0.36, 0.38, and 0.09, respectively). Regarding the impact of COVID-19 on pemphigus, the majority of patients did not experience any changes in their pemphigus regarding clinical phenotype (100%) or severity (83.3%), but PV was worsened in 6 (16.9%) patients which was controlled with increasing the prednisolone dosage.

CONCLUSION

Rituximab appears to be safe with no increased risk of severe form of COVID-19 in patients with pemphigus vulgaris.

Two Years after the Beginning of COVID-19: Comparing Families Who Had or Did not Have Patients with COVID-19 on Health Beliefs and Obsessive-Compulsive Symptoms

Objective: This study aimed to compare health beliefs and obsessive-compulsive symptoms (OCS) in families with (FIM+) or without an infected member (FIM-) two years after the beginning of COVID-19. Additionally, this research intended to predict a decrease in OCS from baseline (T1) to 40 days later (T2) based on health beliefs. Method : In a longitudinal survey, 227 participants in two groups, including FIM+ (n = 98; M = 30.44; SD = 5.39) and FIM- (n = 129; M = 29.24; SD = 4.93), were selected through purposive sampling. They responded to measurements consisting of demographic characteristics, the Obsessive-Compulsive Inventory-Revised (OCI-R), Patient Health Questionnaire (PHQ-9), Impact of Event Scale-Revised (IES-R), and COVID-19 Health Belief Questionnaire (COVID-19-HBQ) at the final assessment phase (T2). To investigate differences between the two groups and predict OCS changes from T1 to T2, data were analyzed using Chi-squared, t-tests, U-Mann-Whitney, Kruskal-Wallis, Pearson correlations, and linear regression analyses. Results: At T1, FIM+ demonstrated significantly greater OCS, health beliefs, posttraumatic stress symptoms (PTS), and depressive symptoms than FIM-. Furthermore, FIM+ showed a decrease in OCS from T1 to T2 after its infected member recovered from COVID-19 (P < 0.001). A decrease in OCS was correlated with a decrease in perceived susceptibility, severity, and barriers. Lack of a vulnerable family member, lower educational attainment, and being a primary caregiver were associated with a greater decrease in OCS. Changes in perceived severity and self-efficacy accounted for 17% of variation in OCS. Conclusion: Even two years after the onset of the pandemic, COVID-19 not only impacts the life of patients with COVID-19 but family members who care for such patients respond to the disease by engaging in excessive health behaviors in the form of OCS.

Evidence of a cognitive bias in the quantification of COVID-19 with CT: an artificial intelligence randomised clinical trial

Chest computed tomography (CT) has played a valuable, distinct role in the screening, diagnosis, and follow-up of COVID-19 patients. The quantification of COVID-19 pneumonia on CT has proven to be an important predictor of the treatment course and outcome of the patient although it remains heavily reliant on the radiologist's subjective perceptions. Here, we show that with the adoption of CT for COVID-19 management, a new type of psychophysical bias has emerged in radiology. A preliminary survey of 40 radiologists and a retrospective analysis of CT data from 109 patients from two hospitals revealed that radiologists overestimated the percentage of lung involvement by 10.23 ± 4.65% and 15.8 ± 6.6%, respectively. In the subsequent randomised controlled trial, artificial intelligence (AI) decision support reduced the absolute overestimation error (P < 0.001) from 9.5% ± 6.6 (No-AI analysis arm, n = 38) to 1.0% ± 5.2 (AI analysis arm, n = 38). These results indicate a human perception bias in radiology that has clinically meaningful effects on the quantitative analysis of COVID-19 on CT. The objectivity of AI was shown to be a valuable complement in mitigating the radiologist's subjectivity, reducing the overestimation tenfold.Trial registration: https://Clinicaltrial.gov . Identifier: NCT05282056, Date of registration: 01/02/2022.

Application of Machine Learning and Deep Learning Techniques for COVID-19 Screening Using Radiological Imaging: A Comprehensive Review

Lung, being one of the most important organs in human body, is often affected by various SARS diseases, among which COVID-19 has been found to be the most fatal disease in recent times. In fact, SARS-COVID 19 led to pandemic that spreads fast among the community causing respiratory problems. Under such situation, radiological imaging-based screening [mostly chest X-ray and computer tomography (CT) modalities] has been performed for rapid screening of the disease as it is a non-invasive approach. Due to scarcity of physician/chest specialist/expert doctors, technology-enabled disease screening techniques have been developed by several researchers with the help of artificial intelligence and machine learning (AI/ML). It can be remarkably observed that the researchers have introduced several AI/ML/DL (deep learning) algorithms for computer-assisted detection of COVID-19 using chest X-ray and CT images. In this paper, a comprehensive review has been conducted to summarize the works related to applications of AI/ML/DL for diagnostic prediction of COVID-19, mainly using X-ray and CT images. Following the PRISMA guidelines, total 265 articles have been selected out of 1715 published articles till the third quarter of 2021. Furthermore, this review summarizes and compares varieties of ML/DL techniques, various datasets, and their results using X-ray and CT imaging. A detailed discussion has been made on the novelty of the published works, along with advantages and limitations.

After the virus has cleared-Can preclinical models be employed for Long COVID research?

Severe Acute Respiratory Syndrome Coronavirus (SARS-CoV-2) can cause the life-threatening acute respiratory disease called COVID-19 (Coronavirus Disease 2019) as well as debilitating multiorgan dysfunction that persists after the initial viral phase has resolved. Long COVID or Post-Acute Sequelae of COVID-19 (PASC) is manifested by a variety of symptoms, including fatigue, dyspnea, arthralgia, myalgia, heart palpitations, and memory issues sometimes affecting between 30% and 75% of recovering COVID-19 patients. However, little is known about the mechanisms causing Long COVID and there are no widely accepted treatments or therapeutics. After introducing the clinical aspects of acute COVID-19 and Long COVID in humans, we summarize the work in animals (mice, Syrian hamsters, ferrets, and nonhuman primates (NHPs)) to model human COVID-19. The virology, pathology, immune responses, and multiorgan involvement are explored. Additionally, any studies investigating time points longer than 14 days post infection (pi) are highlighted for insight into possible long-term disease characteristics. Finally, we discuss how the models can be leveraged for treatment evaluation, including pharmacological agents that are currently in human clinical trials for treating Long COVID. The establishment of a recognized Long COVID preclinical model representing the human condition would allow the identification of mechanisms causing disease as well as serve as a vehicle for evaluating potential therapeutics.

Screening and assessment for post-acute COVID-19 syndrome (PACS), guidance by personal pilots and support with individual digital trainings within intersectoral care: a study protocol of a randomized controlled trial

Background

Because the clinical patterns and symptoms that persist after a COVID-19 infection are diverse, a diagnosis of post-acute COVID-19 syndrome (PACS) is difficult to implement. The current research project therefore aims to evaluate the feasibility and the practicability of a comprehensive, interdisciplinary, and cross-sectoral treatment program consisting of a low-threshold online screening and holistic assessment for PACS. Furthermore, it aims to evaluate digital interventions and the use of so-called personal guides that may help to facilitate the recovery of PACS.

Methods

This German study consists of a low-threshold online screening for PACS where positively screened participants will be supported throughout by personal pilots. The personal pilots are aimed at empowering patients and helping them to navigate through the study and different treatment options. Patients will then be randomly assigned either to an intervention group (IG) or an active control group (ACG). The IG will receive a comprehensive assessment of physiological and psychological functioning to inform future treatment. The ACG does not receive the assessment but both groups will receive a treatment consisting of an individual digital treatment program (digital intervention platform and an intervention via a chatbot). This digital intervention is based on the needs identified during the assessment for participants in the IG. Compared to that, the ACG will receive a more common digital treatment program aiming to reduce PACS symptoms. Importantly, a third comparison group (CompG) will be recruited that does not receive any treatment. A propensity score matching will take place, ensuring comparability between the participants. Primary endpoints of the study are symptom reduction and return to work. Secondary outcomes comprise, for example, social participation and activities in daily life. Furthermore, the feasibility and applicability of the online screening tool, the holistic assessment, digital trainings, and personal pilots will be evaluated.

Discussion

This is one of the first large-scale studies to improve the diagnosis and the care of patients with PACS by means of empowerment. It is to be evaluated whether the methods utilized can be used for the German and international population.

Trial registration ClinicalTrials.gov Identifier: NCT05238415; date of registration: February 14, 2022

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07584-z.

The Delta SARS-CoV-2 Variant of Concern Induces Distinct Pathogenic Patterns of Respiratory Disease in K18-hACE2 Transgenic Mice Compared to the Ancestral Strain from Wuhan

Compared to the original ancestral strain of SARS-CoV-2, the Delta variant of concern has shown increased transmissibility and resistance toward COVID-19 vaccines and therapies. However, the pathogenesis of the disease associated with Delta is still not clear. In this study, using K18-hACE2 transgenic mice, we assessed the pathogenicity of the Delta variant by characterizing the immune response following infection. We found that Delta induced the same clinical disease manifestations as the ancestral SARS-CoV-2, but with significant dissemination to multiple tissues, such as brain, intestine, and kidney. Histopathological analysis showed that tissue pathology and cell infiltration in the lungs of Delta-infected mice were the same as in mice infected with the ancestral SARS-CoV-2. Delta infection caused perivascular inflammation in the brain and intestinal wall thinning in K18-hACE2 transgenic mice. Increased cell infiltration in the kidney was observed in both ancestral strain- and Delta-infected mice, with no clear visible tissue damage identified in either group. Interestingly, compared with mice infected with the ancestral strain, the numbers of CD45+ cells, T cells, B cells, inflammatory monocytes, and dendritic cells were all significantly lower in the lungs of the Delta-infected mice, although there was no significant difference in the levels of proinflammatory cytokines between the two groups. Our results showed distinct immune response patterns in the lungs of K18-hACE2 mice infected with either the ancestral SARS-CoV-2 or Delta variant of concern, which may help to guide therapeutic interventions for emerging SARS-CoV-2 variants. IMPORTANCE SARS-CoV-2 variants, with the threat of increased transmissibility, infectivity, and immune escape, continue to emerge as the COVID-19 pandemic progresses. Detailing the pathogenesis of disease caused by SARS-CoV-2 variants, such as Delta, is essential to better understand the clinical threat caused by emerging variants and associated disease. This study, using the K18-hACE2 mouse model of severe COVID-19, provides essential observation and analysis on the pathogenicity and immune response of Delta infection. These observations shed light on the changing disease profile associated with emerging SARS-CoV-2 variants and have potential to guide COVID-19 treatment strategies.

Machine Learning and Lean Six Sigma to Assess How COVID-19 Has Changed the Patient Management of the Complex Operative Unit of Neurology and Stroke Unit: A Single Center Study

Background: In health, it is important to promote the effectiveness, efficiency and adequacy of the services provided; these concepts become even more important in the era of the COVID-19 pandemic, where efforts to manage the disease have absorbed all hospital resources. The COVID-19 emergency led to a profound restructuring-in a very short time-of the Italian hospital system. Some factors that impose higher costs on hospitals are inappropriate hospitalization and length of stay (LOS). The length of stay (LOS) is a very useful parameter for the management of services within the hospital and is an index evaluated for the management of costs. Methods: This study analyzed how COVID-19 changed the activity of the Complex Operative Unit (COU) of the Neurology and Stroke Unit of the San Giovanni di Dio e Ruggi d'Aragona University Hospital of Salerno (Italy). The methodology used in this study was Lean Six Sigma. Problem solving in Lean Six Sigma is the DMAIC roadmap, characterized by five operational phases. To add even more value to the processing, a single clinical case, represented by stroke patients, was investigated to verify the specific impact of the pandemic. Results: The results obtained show a reduction in LOS for stroke patients and an increase in the value of the diagnosis related group relative weight. Conclusions: This work has shown how, thanks to the implementation of protocols for the management of the COU of the Neurology and Stroke Unit, the work of doctors has improved, and this is evident from the values of the parameters taken into consideration.

Medical imaging of pulmonary disease in SARS-CoV-2-exposed non-human primates

Chest X-ray (CXR), computed tomography (CT), and positron emission tomography-computed tomography (PET-CT) are noninvasive imaging techniques widely used in human and veterinary pulmonary research and medicine. These techniques have recently been applied in studies of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-exposed non-human primates (NHPs) to complement virological assessments with meaningful translational readouts of lung disease. Our review of the literature indicates that medical imaging of SARS-CoV-2-exposed NHPs enables high-resolution qualitative and quantitative characterization of disease otherwise clinically invisible and potentially provides user-independent and unbiased evaluation of medical countermeasures (MCMs). However, we also found high variability in image acquisition and analysis protocols among studies. These findings uncover an urgent need to improve standardization and ensure direct comparability across studies.

Precision Postbiotics and Mental Health: the Management of Post-COVID-19 Complications

The health catastrophe originated by COVID-19 pandemic construed profound impact on a global scale. However, a plethora of research studies corroborated convincing evidence conferring severity of infection of SARS-CoV-2 with the aberrant gut microbiome that strongly speculated its importance for development of novel therapeutic modalities. The intense exploration of probiotics has been envisaged to promote the healthy growth of the host, and restore intestinal microecological balance through various metabolic and physiological processes. The demystifying effect of probiotics cannot be defied, but there exists a strong skepticism related to their safety and efficacy. Therefore, molecular signature of probiotics termed as "postbiotics" are of paramount importance and there is continuous surge of utilizing postbiotics for enhancing health benefits, but little is explicit about their antiviral effects. Therefore, it is worth considering their prospective role in post-COVID regime that pave the way for exploring the pastoral vistas of postbiotics. Based on previous research investigations, the present article advocates prospective role of postbiotics in alleviating the health burden of viral infections, especially SARS-CoV-2. The article also posits current challenges and proposes a futuristic model describing the concept of "precision postbiotics" for effective therapeutic and preventive interventions that can be used for management of this deadly disease.

A Promising and Challenging Approach: Radiologists' Perspective on Deep Learning and Artificial Intelligence for Fighting COVID-19

Chest X-rays (CXR) and computed tomography (CT) are the main medical imaging modalities used against the increased worldwide spread of the 2019 coronavirus disease (COVID-19) epidemic. Machine learning (ML) and artificial intelligence (AI) technology, based on medical imaging fully extracting and utilizing the hidden information in massive medical imaging data, have been used in COVID-19 research of disease diagnosis and classification, treatment decision-making, efficacy evaluation, and prognosis prediction. This review article describes the extensive research of medical image-based ML and AI methods in preventing and controlling COVID-19, and summarizes their characteristics, differences, and significance in terms of application direction, image collection, and algorithm improvement, from the perspective of radiologists. The limitations and challenges faced by these systems and technologies, such as generalization and robustness, are discussed to indicate future research directions.

Artificial Intelligence in Surveillance, Diagnosis, Drug Discovery and Vaccine Development against COVID-19

As of August 6th, 2021, the World Health Organization has notified 200.8 million laboratory-confirmed infections and 4.26 million deaths from COVID-19, making it the worst pandemic since the 1918 flu. The main challenges in mitigating COVID-19 are effective vaccination, treatment, and agile containment strategies. In this review, we focus on the potential of Artificial Intelligence (AI) in COVID-19 surveillance, diagnosis, outcome prediction, drug discovery and vaccine development. With the help of big data, AI tries to mimic the cognitive capabilities of a human brain, such as problem-solving and learning abilities. Machine Learning (ML), a subset of AI, holds special promise for solving problems based on experiences gained from the curated data. Advances in AI methods have created an unprecedented opportunity for building agile surveillance systems using the deluge of real-time data generated within a short span of time. During the COVID-19 pandemic, many reports have discussed the utility of AI approaches in prioritization, delivery, surveillance, and supply chain of drugs, vaccines, and non-pharmaceutical interventions. This review will discuss the clinical utility of AI-based models and will also discuss limitations and challenges faced by AI systems, such as model generalizability, explainability, and trust as pillars for real-life deployment in healthcare.

Artificial Intelligence in Surveillance, Diagnosis, Drug Discovery and Vaccine Development against COVID-19

As of August 6th, 2021, the World Health Organization has notified 200.8 million laboratory-confirmed infections and 4.26 million deaths from COVID-19, making it the worst pandemic since the 1918 flu. The main challenges in mitigating COVID-19 are effective vaccination, treatment, and agile containment strategies. In this review, we focus on the potential of Artificial Intelligence (AI) in COVID-19 surveillance, diagnosis, outcome prediction, drug discovery and vaccine development. With the help of big data, AI tries to mimic the cognitive capabilities of a human brain, such as problem-solving and learning abilities. Machine Learning (ML), a subset of AI, holds special promise for solving problems based on experiences gained from the curated data. Advances in AI methods have created an unprecedented opportunity for building agile surveillance systems using the deluge of real-time data generated within a short span of time. During the COVID-19 pandemic, many reports have discussed the utility of AI approaches in prioritization, delivery, surveillance, and supply chain of drugs, vaccines, and non-pharmaceutical interventions. This review will discuss the clinical utility of AI-based models and will also discuss limitations and challenges faced by AI systems, such as model generalizability, explainability, and trust as pillars for real-life deployment in healthcare.

The Rise of SARS-CoV-2 Variants and the Role of Convalescent Plasma Therapy for Management of Infections

Novel therapies for the treatment of COVID-19 are continuing to emerge as the SARS-Cov-2 pandemic progresses. PCR remains the standard benchmark for initial diagnosis of COVID-19 infection, while advances in immunological profiling are guiding clinical treatment. The SARS-Cov-2 virus has undergone multiple mutations since its emergence in 2019, resulting in changes in virulence that have impacted on disease severity globally. The emergence of more virulent variants of SARS-Cov-2 remains challenging for effective disease control during this pandemic. Major variants identified to date include B.1.1.7, B.1.351; P.1; B.1.617.2; B.1.427; P.2; P.3; B.1.525; and C.37. Globally, large unvaccinated populations increase the risk of more and more variants arising. With successive waves of COVID-19 emerging, strategies that mitigate against community transmission need to be implemented, including increased vaccination coverage. For treatment, convalescent plasma therapy, successfully deployed during recent Ebola outbreaks and for H1N1 influenza, can increase survival rates and improve host responses to viral challenge. Convalescent plasma is rich with cytokines (IL-1β, IL-2, IL-6, IL-17, and IL-8), CCL2, and TNFα, neutralizing antibodies, and clotting factors essential for the management of SARS-CoV-2 infection. Clinical trials can inform and guide treatment policy, leading to mainstream adoption of convalescent therapy. This review examines the limited number of clinical trials published, to date that have deployed this therapy and explores clinical trials in progress for the treatment of COVID-19.

Longitudinal trajectories of pneumonia lesions and lymphocyte counts associated with disease severity among convalescent COVID-19 patients: a group-based multi-trajectory analysis

Background

To explore the long-term trajectories considering pneumonia volumes and lymphocyte counts with individual data in COVID-19.

Methods

A cohort of 257 convalescent COVID-19 patients (131 male and 126 females) were included. Group-based multi-trajectory modelling was applied to identify different trajectories in terms of pneumonia lesion percentage and lymphocyte counts covering the time from onset to post-discharge follow-ups. We studied the basic characteristics and disease severity associated with the trajectories.

Results

We characterised four distinct trajectory subgroups. (1) Group 1 (13.9%), pneumonia increased until a peak lesion percentage of 1.9% (IQR 0.7–4.4) before absorption. The slightly decreased lymphocyte rapidly recovered to the top half of the normal range. (2) Group 2 (44.7%), the peak lesion percentage was 7.2% (IQR 3.2–12.7). The abnormal lymphocyte count restored to normal soon. (3) Group 3 (26.0%), the peak lesion percentage reached 14.2% (IQR 8.5–19.8). The lymphocytes continuously dropped to 0.75 × 10⁹/L after one day post-onset before slowly recovering. (4) Group 4 (15.4%), the peak lesion percentage reached 41.4% (IQR 34.8–47.9), much higher than other groups. Lymphopenia was aggravated until the lymphocytes declined to 0.80 × 10⁹/L on the fourth day and slowly recovered later. Patients in the higher order groups were older and more likely to have hypertension and diabetes (all P values < 0.05), and have more severe disease.

Conclusions

Our findings provide new insights to understand the heterogeneous natural courses of COVID-19 patients and the associations of distinct trajectories with disease severity, which is essential to improve the early risk assessment, patient monitoring, and follow-up schedule.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12890-021-01592-6.

Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph

Triaging and prioritising patients for RT-PCR test had been essential in the management of COVID-19 in resource-scarce countries. In this study, we applied machine learning (ML) to the task of detection of SARS-CoV-2 infection using basic laboratory markers. We performed the statistical analysis and trained an ML model on a retrospective cohort of 5148 patients from 24 hospitals in Hong Kong to classify COVID-19 and other aetiology of pneumonia. We validated the model on three temporal validation sets from different waves of infection in Hong Kong. For predicting SARS-CoV-2 infection, the ML model achieved high AUCs and specificity but low sensitivity in all three validation sets (AUC: 89.9-95.8%; Sensitivity: 55.5-77.8%; Specificity: 91.5-98.3%). When used in adjunction with radiologist interpretations of chest radiographs, the sensitivity was over 90% while keeping moderate specificity. Our study showed that machine learning model based on readily available laboratory markers could achieve high accuracy in predicting SARS-CoV-2 infection.