Classification Of Disease Severity Research Articles

Systemic sclerosis associated interstitial lung disease: a conceptual framework for subclinical, clinical and progressive disease.

To establish a framework by which experts define disease subsets in systemic sclerosis associated interstitial lung disease (SSc-ILD). A conceptual framework for subclinical, clinical and progressive ILD was provided to 83 experts, asking them to use the framework and classify actual SSc-ILD patients. Each patient profile was designed to be classified by at least four experts in terms of severity and risk of progression at baseline; progression was based on 1-year follow-up data. A consensus was reached if ≥75% of experts agreed. Experts provided information on which items were important in determining classification. Forty-four experts (53%) completed the survey. Consensus was achieved on the dimensions of severity (75%, 60 of 80 profiles), risk of progression (71%, 57 of 80 profiles) and progressive ILD (60%, 24 of 40 profiles). For profiles achieving consensus, most were classified as clinical ILD (92%), low risk (54%) and stable (71%). Severity and disease progression overlapped in terms of framework items that were most influential in classifying patients (forced vital capacity, extent of lung involvement on high resolution chest CT [HRCT]); risk of progression was influenced primarily by disease duration. Using our proposed conceptual framework, international experts were able to achieve a consensus on classifying SSc-ILD patients along the dimensions of disease severity, risk of progression and progression over time. Experts rely on similar items when classifying disease severity and progression: a combination of spirometry and gas exchange and quantitative HRCT.

The human host response to monkeypox infection: a proteomic case series study.

The rapid rise of monkeypox (MPX) cases outside previously endemic areas prompts for a better understanding of the disease. We studied the plasma proteome of a group of MPX patients with a similar infection history and clinical manifestation typical for the current outbreak. We report that MPX in this case series is associated with a strong plasma proteomic response among nutritional and acute phase response proteins. Moreover, we report a correlation between plasma proteins and disease severity. Contrasting the MPX host response with that of COVID-19, we find a range of similarities, but also important differences. For instance, CFHR1 is induced in COVID-19, but suppressed in MPX, reflecting the different roles of the complement system in the two infectious diseases. Of note, the spatial overlap in response proteins suggested that a COVID-19 biomarker panel assay could be repurposed for MPX. Applying a targeted protein panel assay provided encouraging results and distinguished MPX cases from healthy controls. Hence, our results provide a first proteomic characterization of the MPX human host response and encourage further research on protein-panel assays in emerging infectious diseases.

Socioeconomic status is not associated with unfavorable outcomes in patients with acute limb ischemia.

Whether socioeconomic status (SES) is associated with health outcomes in patients with acute limb ischemia (ALI) is largely unknown. We aimed to determine whether SES is associated with worse presentations and outcomes for patients with ALI. We performed a retrospective medical record review of patients who presented with ALI between April 2016 and October 2020 at a single tertiary care center. SES was quantified using individual variables (median household income, level of education, and employment) and a composite endpoint, the neighborhood deprivation index (NDI). The NDI is a standardized and reproducible index that uses census tract data (higher number indicates lower SES status). The NDI summarizes 8 domains of socioeconomic deprivation. ALI severity was categorized using the Rutherford classification. The association between SES and the severity of ALI at presentation and between SES and other health outcomes were analyzed using bivariate analysis of variance, independent t test, and multivariate logistic regression. During the study period, 278 patients were treated for ALI, of whom 211 had complete SES data available. The mean age was 64 years, 55% were men, and 57% were White. The Rutherford classification of disease severity was grade 1, 2a, 2b, and 3 for 6%, 54%, 32%, and 8% of patients, respectively. Patients with a low SES status per the NDI were more likely to have a history of peripheral arterial disease and chronic kidney disease at presentation. The ALI etiology (thrombotic vs embolic) was not associated with SES. No significant differences were seen between SES and the severity of ALI at presentation (p = 0.96) or the treatment modality (p = 0.80). No associations between SES and 30-day or 1-year mortality were observed (mean NDI, 0.15 vs 0.26, p = 0.58, and 0.20 vs 0.26, p = 0.71, respectively) or between SES and 30-day or 1-year limb loss (mean NDI, 0.06 vs 0.30, p = 0.18, and 0.1 vs 0.32, p = 0.17, respectively). Lower SES (higher NDI) was associated with increased 30-day readmission (mean NDI, 0.49 vs 0.15, p = 0.021). However, this association was not significant on multivariate analysis (odds ratio 1.4, 95% CI 0.9-2.1, p = 0.06). SES was not associated with the severity of ALI at patient presentation. Although SES was associated with the presence of peripheral arterial disease and chronic kidney disease at presentation, SES was not a predictor of short-term or 1-year limb loss and mortality. Overall, ALI presentation and treatment outcomes were independent of SES.

Soybean rust detection and disease severity classification by remote sensing

AbstractThe detection and monitoring of soybean rust (SBR) through remote sensing is promising because of the importance of the crop and the aspects of the disease. We evaluated the effects of different levels of SBR severity on soybean [Glycine max (L.) Merr.] leaflets reflectance aiming for the construction of a disease classification model. Leaflet reflectance was evaluated on two cultivars (susceptible and partially resistant) at four disease severity levels: healthy, low, moderate, and high. Leaflets were collected in the field and taken to the laboratory for spectral evaluation through the spectrophotometer UV 2700 coupled with Integrating Sphere Attachment ISR‐603, in the range of 270–1000 nm. The feasibility of using a collection of vegetation indices (VIs) and data dimensionality reduction through multiple factor analysis (MFA) was evaluated, and a classification model was constructed. Ten algorithms were assessed based on precision, sensibility, and accuracy parameters, using 80% of the dataset as training data and 20% as testing dataset. The visible range and red edge region contributed more significantly to the disease prediction and classification model. The MFA performed satisfactorily in the dimensionality reduction and unveiled the effect of specific wavelengths on the classification of each class. Most of the VIs studied had high correlation performance across the severity classes. Classification accuracy and precision were >70% for all models. Linear support vector machine with the collection of VIs achieved the best results. This study provides a practical path for developing a detection model to be integrated into SBR management programs.

Microbiota Dysbiosis in Parkinson Disease-In Search of a Biomarker.

Numerous studies have highlighted the role of the gastrointestinal system in Parkinson disease pathogenesis. It is likely triggered by proinflammatory markers produced by specific gut bacteria. This review’s aim is to identify gut bacterial biomarkers of Parkinson disease. A comprehensive search for original research papers on gut microbiota composition in Parkinson disease was conducted using the PubMed, Embase, and Scopus databases. Research papers on intestinal permeability, nasal and oral microbiomes, and interventional studies were excluded. The yielded results were categorized into four groups: Parkinson disease vs. healthy controls; disease severity; non-motor symptoms; and clinical phenotypes. This review was conducted in accordance with the PRISMA 2020 statement. A total of 51 studies met the eligibility criteria. In the Parkinson disease vs. healthy controls group, 22 bacteria were deemed potentially important. In the disease severity category, two bacteria were distinguished. In the non-motor symptoms and clinical phenotypes categories, no distinct pathogen was identified. The studies in this review report bacteria of varying taxonomic levels, which prevents the authors from reaching a clear conclusion. Future research should follow a unified methodology in order to identify potential biomarkers for Parkinson disease.

Combining Deep Phenotyping of Serum Proteomics and Clinical Data via Machine Learning for COVID-19 Biomarker Discovery.

The persistence of long-term coronavirus-induced disease 2019 (COVID-19) sequelae demands better insights into its natural history. Therefore, it is crucial to discover the biomarkers of disease outcome to improve clinical practice. In this study, 160 COVID-19 patients were enrolled, of whom 80 had a “non-severe” and 80 had a “severe” outcome. Sera were analyzed by proximity extension assay (PEA) to assess 274 unique proteins associated with inflammation, cardiometabolic, and neurologic diseases. The main clinical and hematochemical data associated with disease outcome were grouped with serological data to form a dataset for the supervised machine learning techniques. We identified nine proteins (i.e., CD200R1, MCP1, MCP3, IL6, LTBP2, MATN3, TRANCE, α2-MRAP, and KIT) that contributed to the correct classification of COVID-19 disease severity when combined with relative neutrophil and lymphocyte counts. By analyzing PEA, clinical and hematochemical data with statistical methods that were able to handle many variables in the presence of a relatively small sample size, we identified nine potential serum biomarkers of a “severe” outcome. Most of these were confirmed by literature data. Importantly, we found three biomarkers associated with central nervous system pathologies and protective factors, which were downregulated in the most severe cases.

COVID-19 patients with altered steroid hormone levels are more likely to have higher disease severity.

PurposeThis study aims to evaluate the correlations between the severity of the disease and serum steroid levels by analyzing the serum steroid levels in COVID-19 patients with different levels of disease progression and the control group.MethodsMorning serum Aldosterone, 11-deoxycortisol, Androstenedione, 17-hydroxyprogesterone, Dihydrotestosterone (DHT), Dehydroepiandrosterone (DHEA), Corticosterone, Dehydroepiandrosterone sulfate (DHEAS), Estrone, Estradiol, Progesterone, 11-deoxycorticosterone, Cortisol, Corticosterone, Androsterone, Pregnenolone, 17-hydroxypregnenolone and 21-deoxycortisol levels were measured in 153 consecutive patients were grouped as mild, moderate, and severe based on the WHO COVID-19 disease severity classification and the control group. Steroid hormone levels were analyzed at once with a liquid chromatography-tandem mass spectrometric method (LC-MS/MS).ResultsIn our study, nearly all steroids were statistically significantly higher in the patients’ group than in the control group (p < 0.001). Also, DHEA was an independent indicator of the disease severity with COVID-19ConclusionsOur study reveals that the alteration in steroid hormone levels was correlated with disease severity. Also, steroid hormone levels should be followed up during COVID-19 disease management.

Quality of life in Malaysian children with inflammatory bowel disease: An understudied population.

Quality of life (QoL) in children with inflammatory bowel disease (IBD) is often impaired by underlying disease. We evaluated factors affecting health-related QoL (HRQoL) in Malaysian children with IBD. A cross-sectional study using IMPACT-III questionnaires evaluating HRQoL in children aged 8-17 years with duration of IBD of ≥6months was conducted. IMPACT-III, a validated instrument designed to measure HRQoL in children with IBD, was used. Higher IMPACT-III (maximum=100) score indicates better HRQoL. Impact of socio-demographic and clinical factors of IBD on the HRQoL was evaluated. Paediatric Crohn's disease (CD) and ulcerative colitis (UC) activity indices were used to classify disease severity. A total of 75 children (UC=44, CD=41; mean (SD) age at diagnosis 8.2 (3.5) years) were interviewed at mean age of 12.8 (2.7) years. Mean IMPACT-III score was significantly lower in children with more severe disease (mild: 71.8 (13.6) vs. moderate: 65.5 (10.9) vs. severe: 46.3 (14.5); P< 0.001), history of hospitalisation (yes: 64.0 (14.0) vs. none: 74.1 (12.2), P= 0.034) and a higher number of admissions (r= -0.352, P= 0.041) in preceding 6months. Diagnosis at a younger age (r= -0.31, P= 0.007) and a longer duration of disease (r=0.286, P= 0.013) was associated with higher score. A higher weight-for-age (r= 0.261, P= 0.023) or body mass index-for-age z-score (r= 0.235, P= 0.042) was correlated with a better body image domain score, respectively. In Malaysian children with IBD, HRQoL was adversely affected by a more severe disease. Better control of disease activity and maintaining long-term remission are important to improve the HRQoL in childhood IBD.

Predicting 6-minute walking test outcomes in patients with chronic obstructive pulmonary disease without physical performance measures

Background and ObjectiveChronic obstructive pulmonary disease (COPD) requires a multifactorial assessment, evaluating the airflow limitation and symptoms of the patients. The 6-min walk test (6MWT) is commonly used to evaluate the functional exercise capacity in these patients. This study aims to propose a novel predictive model of the major 6MWT outcomes for COPD assessment, without physical performance measurements. MethodsCardiopulmonary and clinical parameters were obtained from fifty COPD patients. These parameters were used as inputs of a Bayesian network (BN), which integrated three multivariate models including the 6-min walking distance (6MWD), the maximum HR (HRmax) after the walking, and the HR decay 3 min after (HRR3). The use of BN allows the assessment of the patients’ status by predicting the 6MWT outcomes, but also inferring disease severity parameters based on actual patient's 6MWT outcomes. ResultsFirstly, the correlation obtained between the estimated and actual 6MWT measures was strong (R = 0.84, MAPE = 8.10% for HRmax) and moderate (R = 0.58, MAPE = 15.43% for 6MWD and R = 0.58, MAPE = 32.49% for HRR3), improving the classical methods to estimate 6MWD. Secondly, the classification of disease severity showed an accuracy of 78.3% using three severity groups, which increased up to 84.4% for two defined severity groups. ConclusionsWe propose a powerful two-way assessment tool for COPD patients, capable of predicting 6MWT outcomes without the need for an actual walking exercise. This model-based tool opens the way to implement a continuous monitoring system for COPD patients at home and to provide more personalized care.

Specialty Pharmacy Disease Screening and Routine Assessments for Patients with Rheumatoid Arthritis and Psoriasis

Background: Rheumatoid arthritis and psoriasis are inflammatory diseases which require frequent monitoring to optimize therapy. Specialty pharmacists are in the unique position to assist in the screening and monitoring of patients with complex, chronic diseases. Objectives: The study objective is to describe the impact of pharmacist screening services in two patient populations. In patients with rheumatoid arthritis, the goal is to describe outcome monitoring through disease severity, therapeutic switches, and adherence rates. In patients with psoriasis, the aim is to describe the utilization of a screening for psoriatic arthritis and the resulting number of potential referrals to medical providers. Methods: The retrospective study patient population consisted of rheumatoid arthritis (RA) patients who filled one or more prescriptions at a specialty pharmacy between 8/22/2017 and 9/26/2018, and psoriasis patients who filled between 6/1/2021 to 9/1/2021. A Routine Assessment of Patient Index Data 3 (RAPID3) score was collected during a refill coordination call every three months throughout the 13-month period for RA patients, and a Psoriasis Epidemiology Screening Tool (PEST) scores reported throughout the stated timeline.1,2 Data was imported from the pharmacy’s electronic medical record into an Excel spreadsheet with each row representing a unique patient. Following data validation, descriptive statistics including means, standard deviations, and percentages were calculated to characterize the sample. Statistical significance was determined at an alpha of 0.05. Results: Of the patients who had 4 assessments for RAPID3, the disease severity category significantly improved from assessment 1 to assessment 4 (p=0.021) when analyzed using a chi-square test. The RAPID3 assessment of patients with RA by pharmacists in a specialty setting identified responders (n=21, 25.6%) and stable patients (n=51, 63%), which reinforces current therapy, and non-responders (n=10, 12.2%), who may benefit from referral to their provider for reevaluation of their therapeutic plan. The PEST screening of patients with psoriasis by pharmacists in a specialty setting identified 11 of 32 patients (34%) who scored a 3 or higher and who may benefit from a referral to a rheumatologist for further assessment of psoriatic arthritis activity. Conclusion: Specialty pharmacists are an essential part of ongoing assessment and management of patients with chronic inflammatory conditions such as rheumatoid arthritis and psoriasis. Screening and monitoring of patients by pharmacists can identify the need for referral to a medical provider.

Association between Type 2 Diabetes and Classification of Periodontal Disease Severity in Japanese Men and Women: A Cross-Sectional Study.

Background: to evaluate the association between type 2 diabetes and periodontal disease severity using the rate of alveolar bone loss (ABL) and high-sensitivity C-reactive protein (hs-CRP) value as indices. Methods: In this cross-sectional study of 372 patients (mean age ± SD, 53.2 ± 11.8 years) from a Japanese hospital, we measured ABL and number of teeth on either panoramic radiographs or intraoral dental radiographs of all teeth. Periodontal disease severity was classified into nine groups by combining ABL and hs-CRP. Results: 48 subjects had type 2 diabetes; 324 did not. Univariate analysis showed that type 2 diabetes was significantly associated with age, sex, body mass index, number of teeth, ABL, hs-CRP, and periodontal disease severity. Multivariate analysis showed significant associations between type 2 diabetes and the groups with high severity of periodontal disease. In receiver operating characteristic (ROC) curve analysis, predicting the presence of diabetes, area under the ROC curve was 0.762 (95%CI = 0.688–0.835) for ABL, and 0.709 (95%CI = 0.635–0.784) for hs-CRP, which was significant. Conclusions: this study showed that diabetes can be associated with a periodontal disease severity classification using the combination of ABL and hs-CRP.

Which model is superior in predicting ICU survival: artificial intelligence versus conventional approaches

BackgroundA disease severity classification system is widely used to predict the survival of patients admitted to the intensive care unit with different diagnoses. In the present study, conventional severity classification systems were compared with artificial intelligence predictive models (Artificial Neural Network and Decision Tree) in terms of the prediction of the survival rate of the patients admitted to the intensive care unit.MethodsThis retrospective cohort study was performed on the data of the patients admitted to the ICU of Ghaemshahr’s Razi Teaching Care Center from March 20th, 2017, to September 22nd, 2019. The required data for calculating conventional severity classification models (SOFA, SAPS II, APACHE II, and APACHE IV) were collected from the patients’ medical records. Subsequently, the score of each model was calculated. Artificial intelligence predictive models (Artificial Neural Network and Decision Tree) were developed in the next step. Lastly, the performance of each model in predicting the survival of the patients admitted to the intensive care unit was evaluated using the criteria of sensitivity, specificity, accuracy, F-measure, and area under the ROC curve. Also, each model was validated externally. The R program, version 4.1, was used to create the artificial intelligence models, and SPSS Statistics Software, version 21, was utilized to perform statistical analysis.ResultsThe area under the ROC curve of SOFA, SAPS II, APACHE II, APACHE IV, multilayer perceptron artificial neural network, and CART decision tree were 76.0, 77.1, 80.3, 78.5, 84.1, and 80.0, respectively.ConclusionThe results showed that although the APACHE II model had better results than other conventional models in predicting the survival rate of the patients admitted to the intensive care unit, the other conventional models provided acceptable results too. Moreover, the findings showed that the artificial neural network model had the best performance among all the studied models, indicating the discrimination power of this model in predicting patient survival compared to the other models.

SABA use as an indicator for asthma exacerbation risk: an observational cohort study (SABINA Canada).

BackgroundPatients with asthma use short-acting β-agonists (SABA) to relieve symptoms but SABA alone does not treat underlying inflammation. Thus, over-reliance on SABA may result in poor asthma control and negative health outcomes.ObjectiveTo describe use of SABA and characterise the relationship with severe exacerbations in the Canadian provinces of Nova Scotia (NS) and Alberta (AB).MethodsIn this longitudinal Canadian SABA In Asthma (SABINA) study, patients with an asthma diagnosis were identified between 2016 and 2020 within two provincial administrative datasets (Health Data Nova Scotia and Alberta Health Services). All patients were followed for ≥24 months, with the first 12 months used to measure baseline asthma severity. Medication use and the relationship of SABA overuse (three or more canisters per year) with severe asthma exacerbations were characterised descriptively and via regression analysis.ResultsA total of 115 478 patients were identified (NS: n=8034; AB: n=107 444). SABA overuse was substantial across both provinces (NS: 39.4%; AB: 28.0%) and across all baseline disease severity categories. Patients in NS with SABA overuse had a mean±sd annual rate of 0.46±1.11 exacerbations, compared to 0.30±1.36 for those using fewer than three canisters of SABA. Patients in AB had mean±sd exacerbation rates of 0.31±0.86 and 0.17±0.62, respectively. The adjusted risk of severe exacerbation was associated with SABA overuse (NS: incidence ratio rate 1.36, 95% CI 1.18–1.56; AB: incidence ratio rate 1.32, 95% CI 1.27–1.38).ConclusionThis study supports recent updates to Canadian Thoracic Society and Global Initiative for Asthma guidelines for asthma care. SABA overuse is associated with increased risk of severe exacerbations and can be used to identify patients at a higher risk for severe exacerbations.

Development and validation of a multivariable mortality risk prediction model for COPD in primary care

Risk stratification of chronic obstructive pulmonary disease (COPD) patients is important to enable targeted management. Existing disease severity classification systems, such as GOLD staging, do not take co-morbidities into account despite their high prevalence in COPD patients. We sought to develop and validate a prognostic model to predict 10-year mortality in patients with diagnosed COPD. We constructed a longitudinal cohort of 37,485 COPD patients (149,196 person-years) from a UK-wide primary care database. The risk factors included in the model pertained to demographic and behavioural characteristics, co-morbidities, and COPD severity. The outcome of interest was all-cause mortality. We fitted an extended Cox-regression model to estimate hazard ratios (HR) with 95% confidence intervals (CI), used machine learning-based data modelling approaches including k-fold cross-validation to validate the prognostic model, and assessed model fitting and discrimination. The inter-quartile ranges of the three metrics on the validation set suggested good performance: 0.90–1.06 for model fit, 0.80–0.83 for Harrel’s c-index, and 0.40–0.46 for Royston and Saurebrei’s R_D^2 with a strong overlap of these metrics on the training dataset. According to the validated prognostic model, the two most important risk factors of mortality were heart failure (HR 1.92; 95% CI 1.87–1.96) and current smoking (HR 1.68; 95% CI 1.66–1.71). We have developed and validated a national, population-based prognostic model to predict 10-year mortality of patients diagnosed with COPD. This model could be used to detect high-risk patients and modify risk factors such as optimising heart failure management and offering effective smoking cessation interventions.

Two-Stage Convolutional Neural Networks for Diagnosing the Severity of Alternaria Leaf Blotch Disease of the Apple Tree

In many parts of the world, apple trees suffer from severe foliar damage each year due to infection of Alternaria blotch (Alternaria alternata f. sp. Mali), resulting in serious economic losses to growers. Traditional methods for disease detection and severity classification mostly rely on manual labor, which is slow, labor-intensive and highly subjective. There is an urgent need to develop an effective protocol to rapidly and accurately evaluate disease severity. In this study, DeeplabV3+, PSPNet and UNet were used to assess the severity of apple Alternaria leaf blotch. For identifications of leaves and disease areas, the dataset with a total of 5382 samples was randomly split into 74% (4004 samples) for model training, 9% (494 samples) for validation, 8% (444 samples) for testing and 8% (440 samples) for overall testing. Apple leaves were first segmented from complex backgrounds using the deep-learning algorithms with different backbones. Then, the recognition of disease areas was performed on the segmented leaves. The results showed that the PSPNet model with MobileNetV2 backbone exhibited the highest performance in leaf segmentation, with precision, recall and MIoU values of 99.15%, 99.26% and 98.42%, respectively. The UNet model with VGG backbone performed the best in disease-area prediction, with a precision of 95.84%, a recall of 95.54% and a MIoU value of 92.05%. The ratio of disease area to leaf area was calculated to assess the disease severity. The results showed that the average accuracy for severity classification was 96.41%. Moreover, both the correlation coefficient and the consistency correlation coefficient were 0.992, indicating a high agreement between the reference values and the value that the research predicted. This study proves the feasibility of rapid estimation of the severity of apple Alternaria leaf blotch, which will provide technical support for precise application of pesticides.

SARS-CoV-2 breakthrough infections among hospitalized patients in southeastern Michigan

Background: As of January 2022, more than 57 million cases of COVID-19 have been reported in the United States. Three primary COVID-19 vaccines are widely available: Pfizer (BNT162b2), Moderna (mRNA-1273), and Johnson &amp; Johnson’s-Janssen (JNJ-78436735). The vaccines are effective but do not prevent all infections. We investigated trends in type of vaccine receipt, demographic characteristics, and disease outcomes in COVID-19 breakthrough infections among hospitalized patients. Methods: A breakthrough case is defined as the detection of SARS-CoV-2 ≥14 days after completion of all doses of an FDA-authorized COVID-19 vaccine. An electronic medical record report in EPIC EHR software identified 85 fully vaccinated patients with a documented positive SARS-CoV-2 result between February and September 2021 at 2 hospitals in southeastern Michigan. Demographic information and hospitalization characteristics, including length of stay and oxygen requirements, were collected from the report. Patients were classified into disease severity categories: nonsevere, severe, or critical. A case was considered severe if the patient’s oxygen saturation level (SpO2) was ≤94% on room air or if the patient required supplemental oxygen. Illness was considered critical if the patient developed respiratory failure, including mechanical ventilation or extracorporeal membrane oxygenation. All other cases were classified as nonsevere. Cycle threshold (Ct) values, the number of PCR cycles required to reach a threshold of SARS-CoV-2 genomic material, were collected from the hospital microbiology lab. Results: We identified 85 breakthrough infections (Fig. 1). The average patient age was 69.9±15.7 years, and 44 (51.8%) were female. Severe disease was most common (n = 73, 85.9%) followed by nonsevere disease (n = 7, 8.24%), and 9 patients (10.6%) in this cohort died. Most patients received either the Moderna (n = 35, 41.2%) or Pfizer (n = 38, 44.7%) vaccines. Pfizer vaccine receipt was most common among patients with severe illness (n = 33 of 73, 45.2%), and Moderna vaccine receipt was most common among patients with critical illness (n = 4 of 5, 80.0%). Average time from last vaccination to positive test was longest among Moderna vaccine recipients (181.9±43.1 days) and shortest among J&amp;J vaccine recipients (91.0±61.1 days). The average Ct value was 23.8±7.5 and ranged from 13.0 to 41.3. There were no appreciable differences in the average Ct value by vaccine manufacturer. Conclusions: Breakthrough infections among hospitalized patients were uncommon, but incidence increased with time after vaccine receipt in all vaccines. Further study is needed to examine differences and severity in breakthrough infections by vaccine type and in individuals who completed booster vaccines.Funding: NoneDisclosures: None

Joint Learning of Multi-Level Tasks for Diabetic Retinopathy Grading on Low-Resolution Fundus Images.

Diabetic retinopathy (DR) is a leading cause of permanent blindness among the working-age people. Automatic DR grading can help ophthalmologists make timely treatment for patients. However, the existing grading methods are usually trained with high resolution (HR) fundus images, such that the grading performance decreases a lot given low resolution (LR) images, which are common in clinic. In this paper, we mainly focus on DR grading with LR fundus images. According to our analysis on the DR task, we find that: 1) image super-resolution (ISR) can boost the performance of both DR grading and lesion segmentation; 2) the lesion segmentation regions of fundus images are highly consistent with pathological regions for DR grading. Based on our findings, we propose a convolutional neural network (CNN)-based method for joint learning of multi-level tasks for DR grading, called DeepMT-DR, which can simultaneously handle the low-level task of ISR, the mid-level task of lesion segmentation and the high-level task of disease severity classification on LR fundus images. Moreover, a novel task-aware loss is developed to encourage ISR to focus on the pathological regions for its subsequent tasks: lesion segmentation and DR grading. Extensive experimental results show that our DeepMT-DR method significantly outperforms other state-of-the-art methods for DR grading over three datasets. In addition, our method achieves comparable performance in two auxiliary tasks of ISR and lesion segmentation.

Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning

Radiological findings on chest X-ray (CXR) have shown to be essential for the proper management of COVID-19 patients as the maximum severity over the course of the disease is closely linked to the outcome. As such, evaluation of future severity from current CXR would be highly desirable. We trained a repurposed deep learning algorithm on the CheXnet open dataset (224,316 chest X-ray images of 65,240 unique patients) to extract features that mapped to radiological labels. We collected CXRs of COVID-19-positive patients from an open-source dataset (COVID-19 image data collection) and from a multi-institutional local ICU dataset. The data was grouped into pairs of sequential CXRs and were categorized into three categories: ‘Worse’, ‘Stable’, or ‘Improved’ on the basis of radiological evolution ascertained from images and reports. Classical machine-learning algorithms were trained on the deep learning extracted features to perform immediate severity evaluation and prediction of future radiological trajectory. Receiver operating characteristic analyses and Mann-Whitney tests were performed. Deep learning predictions between “Worse” and “Improved” outcome categories and for severity stratification were significantly different for three radiological signs and one diagnostic (‘Consolidation’, ‘Lung Lesion’, ‘Pleural effusion’ and ‘Pneumonia’; all P < 0.05). Features from the first CXR of each pair could correctly predict the outcome category between ‘Worse’ and ‘Improved’ cases with a 0.81 (0.74–0.83 95% CI) AUC in the open-access dataset and with a 0.66 (0.67–0.64 95% CI) AUC in the ICU dataset. Features extracted from the CXR could predict disease severity with a 52.3% accuracy in a 4-way classification. Severity evaluation trained on the COVID-19 image data collection had good out-of-distribution generalization when testing on the local dataset, with 81.6% of intubated ICU patients being classified as critically ill, and the predicted severity was correlated with the clinical outcome with a 0.639 AUC. CXR deep learning features show promise for classifying disease severity and trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.

Severity and outcome of COVID-19 disease in patients with allergic rhinitis during the pandemic in Qatar - A preliminary report.

Background: Allergic rhinitis and asthma exacerbation are strongly linked to respiratory viral and bacterial infections. COVID-19 pandemic has raised concerns about the risk of infection and the severity of COVID-19 infection in patients with asthma and allergic rhinitis. However, increasing evidence suggests that atopic disease protects against severe COVID-19 illness owing to the underlying type 2 inflammatory process. Many studies have reported the impact of asthma on COVID-19 disease; however, data on allergic rhinitis are scarce. In this study, we aimed to investigate the severity and outcome of COVID-19 disease in adult patients with allergic rhinitis in Qatar during the first pandemic wave.Methods: We conducted a retrospective chart review of adult patients with a confirmed diagnosis of asthma and/or allergic rhinitis who had a positive COVID-19 RT-PCR between February 01, 2020, and December 01, 2020. Parameters evaluated included the WHO classification of COVID-19 disease severity as mild, moderate, severe, and critical; COVID-19 disease outcome; and mortality. Patients with allergic rhinitis were defined as those with typical allergic rhinitis symptoms and positive skin prick test or specific IgE to perennial or seasonal inhaled allergens. Only data about patients with allergic rhinitis has been presented in this report.Results: We screened 97 EMR Cerner records of patients who had the diagnosis code for allergic rhinitis. Nine patients met the inclusion criteria of allergic rhinitis diagnosis; the remaining either had no allergy testing or had negative allergy tests. Seven (77.7%) patients had mild COVID-19, whereas only one (11.1%) patient each had moderate and severe disease. The length of hospital stays for 6 patients ranged from 5–13 days, and the remaining 3 patients were quarantined at home. No reports of critical cases or death were identified. All the patients recovered from COVID-19 with a favorable outcome.Conclusion: This preliminary data showed that most patients with allergic rhinitis had mild COVID-19 disease. Furthermore, all of them recovered well, similar to the available data from previous studies. A limitation of this study is the small population size.

Systemic Treatments for Adult Patients with Moderate-to-Severe Psoriasis: Consensus Statements for the United Arab Emirates

Background: Psoriasis is a chronic, immune-mediated disease characterized by mild localized plaques to severe plaques involving any part of the skin; it has a pronounced effect on patients’ quality of life. In the United Arab Emirates (UAE), there are limited local guidelines for the management of patients with psoriasis in daily clinical practice. Objectives: The study aimed to develop consensus statements for the evaluation and management of moderate-to-severe psoriasis in the UAE. Methods: To develop consensus statements, the Emirates Dermatology Society set up advisory board meetings in which local key opinion leaders (KOLs), including dermatologists from the UAE, participated. A targeted literature review was conducted to review current international and regional guidelines on the management of psoriasis, based on which the statements were formulated. A final consensus on each statement was reached based on collective agreement among the KOLs. Results : Consensus statements were generated with the intention of supporting physicians in clinical decision-making with respect to the classification of disease severity, treatment options including biologic and non-biologic systemic therapies, transitioning and adjusting of systemic therapies, and monitoring and management of psoriasis in special populations. Conclusion: These consensus statements could provide useful, practical guidance on the diagnosis and management of patients with moderate-to-severe psoriasis and would cater to the needs of physicians in the UAE.