A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics.

During the diagnostic process, clinicians leverage multimodal information, such as the chief complaint, medical images and laboratory test results. Deep-learning models for aiding diagnosis have yet to meet this requirement of leveraging multimodal information. Here we report a transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model leverages embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and uses bidirectional blocks with intramodal and intermodal attention to learn holistic representations of radiographs, the unstructured chief complaint and clinical history, and structured clinical information such as laboratory test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary disease (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Unified multimodal transformer-based models may help streamline the triaging of patients and facilitate the clinical decision-making process.

Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease.

Objective: To assess the performance of a novel deep learning (DL)-based artificial intelligence (AI) system in classifying computed tomography (CT) scans of pneumonia patients into different groups, as well as to present an effective clinically relevant machine learning (ML) system based on medical image identification and clinical feature interpretation to assist radiologists in triage and diagnosis. Methods: The 3,463 CT images of pneumonia used in this multi-center retrospective study were divided into four categories: bacterial pneumonia (n = 507), fungal pneumonia (n = 126), common viral pneumonia (n = 777), and COVID-19 (n = 2,053). We used DL methods based on images to distinguish pulmonary infections. A machine learning (ML) model for risk interpretation was developed using key imaging (learned from the DL methods) and clinical features. The algorithms were evaluated using the areas under the receiver operating characteristic curves (AUCs). Results: The median AUC of DL models for differentiating pulmonary infection was 99.5% (COVID-19), 98.6% (viral pneumonia), 98.4% (bacterial pneumonia), 99.1% (fungal pneumonia), respectively. By combining chest CT results and clinical symptoms, the ML model performed well, with an AUC of 99.7% for SARS-CoV-2, 99.4% for common virus, 98.9% for bacteria, and 99.6% for fungus. Regarding clinical features interpreting, the model revealed distinctive CT characteristics associated with specific pneumonia: in COVID-19, ground-glass opacity (GGO) [92.5%; odds ratio (OR), 1.76; 95% confidence interval (CI): 1.71-1.86]; larger lesions in the right upper lung (75.0%; OR, 1.12; 95% CI: 1.03-1.25) with viral pneumonia; older age (57.0 years ± 14.2, OR, 1.84; 95% CI: 1.73-1.99) with bacterial pneumonia; and consolidation (95.8%, OR, 1.29; 95% CI: 1.05-1.40) with fungal pneumonia. Conclusion: For classifying common types of pneumonia and assessing the influential factors for triage, our AI system has shown promising results. Our ultimate goal is to assist clinicians in making quick and accurate diagnoses, resulting in the potential for early therapeutic intervention.

Paracetamol Is Associated with a Lower Risk of COVID-19 Infection and Decreased ACE2 Protein Expression: A Retrospective Analysis

Ibuprofen is a common over-the-counter drug taken for pain relief. However, recent studies have raised concerns about its potential toxic effect with coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). It has been proposed that ibuprofen may increase levels of angiotensin-converting enzyme 2 (ACE2), the human receptor for SARS-CoV-2 infection. Therefore, paracetamol is suggested as an alternative to ibuprofen for treating COVID-19 symptoms. Nevertheless, the relationship between intake of paracetamol or ibuprofen and either susceptibility to infection by SARS-CoV-2 or modulation of cellular ACE2 levels remains unclear. In this study, we combined data from human medical records and cells in culture to explore the role of the intake of these drugs in COVID-19. Although ibuprofen did not influence COVID-19 infectivity or ACE2 levels, paracetamol intake was associated with a lower occurrence of COVID-19 in our cohort. We also found that paracetamol led to decreased ACE2 protein levels in cultured cells. Our work identifies a putative protective effect of paracetamol against SARS-CoV-2 infection. Future work should explore the molecular mechanisms underlying the relationship between paracetamol and COVID-19.

Distribution Atlas of COVID-19 Pneumonia on Computed Tomography: A Deep Learning Based Description.

Objectives: To construct a distribution atlas of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) and further explore the difference in distribution by location and disease severity through a retrospective study of 484 cases in Jiangsu, China. Methods: All patients diagnosed with COVID-19 from January 10 to February 18 in Jiangsu Province, China, were enrolled in our study. The patients were further divided into asymptomatic/mild, moderate, and severe/critically ill groups. A deep learning algorithm was applied to the anatomic pulmonary segmentation and pneumonia lesion extraction. The frequency of opacity on CT was calculated, and a color-coded distribution atlas was built. A further comparison was made between the upper and lower lungs, between bilateral lungs, and between various severity groups. Additional lesion-based radiomics analysis was performed to ascertain the features associated with the disease severity. Results: A total of 484 laboratory-confirmed patients with 945 repeated CT scans were included. Pulmonary opacity was mainly distributed in the subpleural and peripheral areas. The distances from the opacity to the nearest parietal/visceral pleura were shortest in the asymptomatic/mild group. More diffused lesions were found in the severe/critically ill group. The frequency of opacity increased with increased severity and peaked at about 3-4 or 7-8 o'clock direction in the upper lungs, as opposed to the 5 or 6 o'clock direction in the lower lungs. Lesions with greater energy, more circle-like, and greater surface area were more likely found in severe/critically ill cases than the others. Conclusion: This study constructed a detailed distribution atlas of COVID-19 pneumonia and compared specific patterns in different parts of the lungs at various severities. The radiomics features most associated with the severity were also found. These results may be valuable in determining the COVID-19 sub-phenotype. Supplementary Information: The online version contains supplementary material available at 10.1007/s43657-021-00011-4.

AI-based analysis of CT images for rapid triage of COVID-19 patients.

The COVID-19 pandemic overwhelms the medical resources in the stressed intensive care unit (ICU) capacity and the shortage of mechanical ventilation (MV). We performed CT-based analysis combined with electronic health records and clinical laboratory results on Cohort 1 (n = 1662 from 17 hospitals) with prognostic estimation for the rapid stratification of PCR confirmed COVID-19 patients. These models, validated on Cohort 2 (n = 700) and Cohort 3 (n = 662) constructed from nine external hospitals, achieved satisfying performance for predicting ICU, MV, and death of COVID-19 patients (AUROC 0.916, 0.919, and 0.853), even on events happened two days later after admission (AUROC 0.919, 0.943, and 0.856). Both clinical and image features showed complementary roles in prediction and provided accurate estimates to the time of progression (p < 0.001). Our findings are valuable for optimizing the use of medical resources in the COVID-19 pandemic. The models are available here: https://github.com/terryli710/COVID_19_Rapid_Triage_Risk_Predictor .

Alzheimer's and Parkinson's Diseases Predict Different COVID-19 Outcomes: A UK Biobank Study.

In December 2019, a coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), began infecting humans, causing a novel disease, coronavirus disease 19 (COVID-19). This was first described in the Wuhan province of the People's Republic of China. SARS-CoV-2 has spread throughout the world, causing a global pandemic. To date, thousands of cases of COVID-19 have been reported in the United Kingdom, and over 45,000 patients have died. Some progress has been achieved in managing this disease, but the biological determinants of health, in addition to age, that affect SARS-CoV-2 infectivity and mortality are under scrutiny. Recent studies show that several medical conditions, including diabetes and hypertension, increase the risk of COVID-19 and death. The increased vulnerability of elderly individuals and those with comorbidities, together with the prevalence of neurodegenerative diseases with advanced age, led us to investigate the links between neurodegeneration and COVID-19. We analysed the primary health records of 13,338 UK individuals tested for COVID-19 between March and July 2020. We show that a pre-existing diagnosis of Alzheimer's disease predicts the highest risk of COVID-19 and mortality among elderly individuals. In contrast, Parkinson's disease patients were found to have a higher risk of SARS-CoV-2 infection but not mortality from COVID-19. We conclude that there are disease-specific differences in COVID-19 susceptibility among patients affected by neurodegenerative disorders.

Lower Circulating Interferon-Gamma Is a Risk Factor for Lung Fibrosis in COVID-19 Patients.

Cytokine storm resulting from SARS-CoV-2 infection is one of the leading causes of acute respiratory distress syndrome (ARDS) and lung fibrosis. We investigated the effect of inflammatory molecules to identify any marker that is related to lung fibrosis in coronavirus disease 2019 (COVID-19). Seventy-six COVID-19 patients who were admitted to Youan Hospital between January 21 and March 20, 2020 and recovered were recruited for this study. Pulmonary fibrosis, represented as fibrotic volume on chest CT images, was computed by an artificial intelligence (AI)-assisted program. Plasma samples were collected from the participants shortly after admission, to measure the basal inflammatory molecules levels. At discharge, fibrosis was present in 46 (60.5%) patients whose plasma interferon-γ (IFN-γ) levels were twofold lower than those without fibrosis (p > 0.05). The multivariate-adjusted logistic regression analysis demonstrated the inverse association risk of having lung fibrosis and basal circulating IFN-γ levels with an estimate of 0.43 (p = 0.02). Per the 1-SD increase of basal IFN-γ level in circulation, the fibrosis volume decreased by 0.070% (p = 0.04) at the discharge of participants. The basal circulating IFN-γ levels were comparable with c-reactive protein in the discrimination of the occurrence of lung fibrosis among COVID-19 patients at discharge, unlike circulating IL-6 levels. In conclusion, these data indicate that decreased circulating IFN-γ is a risk factor of lung fibrosis in COVID-19.

Links between air pollution and COVID-19 in England.

In December 2019, a novel disease, coronavirus disease 19 (COVID-19), emerged in Wuhan, People's Republic of China. COVID-19 is caused by a novel coronavirus (SARS-CoV-2) presumed to have jumped species from another mammal to humans. This virus has caused a rapidly spreading global pandemic. To date, over 300,000 cases of COVID-19 have been reported in England and over 40,000 patients have died. While progress has been achieved in managing this disease, the factors in addition to age that affect the severity and mortality of COVID-19 have not been clearly identified. Recent studies of COVID-19 in several countries identified links between air pollution and death rates. Here, we explored potential links between major fossil fuel-related air pollutants and SARS-CoV-2 mortality in England. We compared current SARS-CoV-2 cases and deaths from public databases to both regional and subregional air pollution data monitored at multiple sites across England. After controlling for population density, age and median income, we show positive relationships between air pollutant concentrations, particularly nitrogen oxides, and COVID-19 mortality and infectivity. Using detailed UK Biobank data, we further show that PM2.5 was a major contributor to COVID-19 cases in England, as an increase of 1 m3 in the long-term average of PM2.5 was associated with a 12% increase in COVID-19 cases. The relationship between air pollution and COVID-19 withstands variations in the temporal scale of assessments (single-year vs 5-year average) and remains significant after adjusting for socioeconomic, demographic and health-related variables. We conclude that a small increase in air pollution leads to a large increase in the COVID-19 infectivity and mortality rate in England. This study provides a framework to guide both health and emissions policies in countries affected by this pandemic.

Tailoring steroids in the treatment of COVID-19 pneumonia assisted by CT scans: three case reports.

In this article, we analyze and report cases of three patients who were admitted to Renmin Hospital, Wuhan University, China, for treating COVID-19 pneumonia in February 2020 and were unresponsive to initial treatment of steroids. They were then received titrated steroids treatment based on the assessment of computed tomography (CT) images augmented and analyzed with the artificial intelligence (AI) tool and output. Three patients were finally recovered and discharged. The result indicated that sufficient steroids may be effective in treating the COVID-19 patients after frequent evaluation and timely adjustment according to the disease severity assessed based on the quantitative analysis of the images of serial CT scans.

A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images.

OBJECTIVES: To utilize a deep learning model for automatic detection of abnormalities in chest CT images from COVID-19 patients and compare its quantitative determination performance with radiological residents. METHODS: A deep learning algorithm consisted of lesion detection, segmentation, and location was trained and validated in 14,435 participants with chest CT images and definite pathogen diagnosis. The algorithm was tested in a non-overlapping dataset of 96 confirmed COVID-19 patients in three hospitals across China during the outbreak. Quantitative detection performance of the model was compared with three radiological residents with two experienced radiologists' reading reports as reference standard by assessing the accuracy, sensitivity, specificity, and F1 score. RESULTS: Of 96 patients, 88 had pneumonia lesions on CT images and 8 had no abnormities on CT images. For per-patient basis, the algorithm showed superior sensitivity of 1.00 (95% confidence interval (CI) 0.95, 1.00) and F1 score of 0.97 in detecting lesions from CT images of COVID-19 pneumonia patients. While for per-lung lobe basis, the algorithm achieved a sensitivity of 0.96 (95% CI 0.94, 0.98) and a slightly inferior F1 score of 0.86. The median volume of lesions calculated by algorithm was 40.10 cm3. An average running speed of 20.3 s ± 5.8 per case demonstrated the algorithm was much faster than the residents in assessing CT images (all p < 0.017). The deep learning algorithm can also assist radiologists make quicker diagnosis (all p < 0.0001) with superior diagnostic performance. CONCLUSIONS: The algorithm showed excellent performance in detecting COVID-19 pneumonia on chest CT images compared with resident radiologists. KEY POINTS: • The higher sensitivity of deep learning model in detecting COVID-19 pneumonia were found compared with radiological residents on a per-lobe and per-patient basis. • The deep learning model improves diagnosis efficiency by shortening processing time. • The deep learning model can automatically calculate the volume of the lesions and whole lung.

Dynamic evolution of COVID-19 on chest computed tomography: experience from Jiangsu Province of China.

OBJECTIVES: To determine the patterns of chest computed tomography (CT) evolution according to disease severity in a large coronavirus disease 2019 (COVID-19) cohort in Jiangsu Province, China. METHODS: This retrospective cohort study was conducted from January 10, 2020, to February 18, 2020. All patients diagnosed with COVID-19 in Jiangsu Province were included, retrospectively. Quantitative CT measurements of pulmonary opacities including volume, density, and location were extracted by deep learning algorithm. Dynamic evolution of these measurements was investigated from symptom onset (day 1) to beyond day 15. Comparison was made between severity groups. RESULTS: A total of 484 patients (median age of 47 years, interquartile range 33-57) with 954 CT examinations were included, and each was assigned to one of the three groups: asymptomatic/mild (n = 63), moderate (n = 378), severe/critically ill (n = 43). Time series showed different evolution patterns of CT measurements in the groups. Following disease onset, posteroinferior subpleural area of the lung was the most common location for pulmonary opacities. Opacity volume continued to increase beyond 15 days in the severe/critically ill group, compared with peaking on days 13-15 in the moderate group. Asymptomatic/mild group had the lowest opacity volume which almost resolved after 15 days. The opacity density began to drop from day 10 to day 12 for moderately ill patients. CONCLUSIONS: Volume, density, and location of the pulmonary opacity and their evolution on CT varied with disease severity in COVID-19. These findings are valuable in understanding the nature of the disease and monitoring the patient's condition during the course of illness. KEY POINTS: • Volume, density, and location of the pulmonary opacity on CT change over time in COVID-19. • The evolution of CT appearance follows specific pattern, varying with disease severity.

Multicenter cohort study demonstrates more consolidation in upper lungs on initial CT increases the risk of adverse clinical outcome in COVID-19 patients.

Rationale: Chest computed tomography (CT) has been used for the coronavirus disease 2019 (COVID-19) monitoring. However, the imaging risk factors for poor clinical outcomes remain unclear. In this study, we aimed to assess the imaging characteristics and risk factors associated with adverse composite endpoints in patients with COVID-19 pneumonia. Methods: This retrospective cohort study enrolled patients with laboratory-confirmed COVID-19 from 24 designated hospitals in Jiangsu province, China, between 10 January and 18 February 2020. Clinical and initial CT findings at admission were extracted from medical records. Patients aged < 18 years or without available clinical or CT records were excluded. The composite endpoints were admission to ICU, acute respiratory failure occurrence, or shock during hospitalization. The volume, density, and location of lesions, including ground-glass opacity (GGO) and consolidation, were quantitatively analyzed in each patient. Multivariable logistic regression models were used to identify the risk factors among age and CT parameters associated with the composite endpoints. Results: In this study, 625 laboratory-confirmed COVID-19 patients were enrolled; among them, 179 patients without an initial CT at admission and 25 patients aged < 18 years old were excluded and 421 patients were included in analysis. The median age was 48.0 years and the male proportion was 53% (224/421). During the follow-up period, 64 (15%) patients had a composite endpoint. There was an association of older age (odds ratio [OR], 1.04; 95% confidence interval [CI]: 1.01-1.06; P = 0.003), larger consolidation lesions in the upper lung (Right: OR, 1.13; 95%CI: 1.03-1.25, P =0.01; Left: OR,1.15; 95%CI: 1.01-1.32; P = 0.04) with increased odds of adverse endpoints. Conclusion: There was an association of older age and larger consolidation in upper lungs on admission with higher odds of poor outcomes in patients with COVID-19.