Skin improvement is a surrogate for favourable changes in other organ systems in early diffuse cutaneous systemic sclerosis

Abstract Objectives Skin improvement in diffuse cutaneous SSc (dcSSc), measured with modified Rodnan skin score (mRSS), is frequently used as a primary outcome in clinical trials, but it is uncertain whether mRSS changes reflect changes in other organ systems. This aim of this study was to explore if skin changes in early dcSSc over 1 and 2 years are associated with changes in severity of other organ involvement. Methods Canadian Scleroderma Research Group database patients with dcSSc, disease duration of ≤5 years, no evidence of initial end-stage organ damage and/or significant comorbidity who had 1 year (n = 154) and 2 years (n = 128) of follow-up data were included. mRSS changes of 25% and/or ≥5 points were considered significant. Organ involvement was assessed by Medsger Disease Severity Score and Canadian Scleroderma Research Group definitions using bivariate, chi-square, ANOVA, adjusted regression and longitudinal mixed effect model analyses. Results Improvement in mRSS was found in 41% of patients at 1 year and in 50% at 2 years. Improved patients showed less forced vital capacity decline (P = 0.012) and less frequent new cardiac involvement (P = 0.02) over 1 year, as well as better lung (by both Disease Severity Score, P = 0.006, and Δforced vital capacity%, P = 0.026), peripheral vascular (P = 0.006) and joint/tendon (P = 0.002) involvement over 2 years. mRSS worsening was consistently linked to less favourable lung outcomes at both 1- and 2-year follow-up visits, and more severe gastrointestinal disease at 2 years. Conclusion Changes in lung function in early dcSSc closely parallel skin changes. mRSS improvement reflects better prognosis for visceral disease and may be a reliable outcome measure in clinical trials.

Download Full-text

Automated assessment of COVID-19 pulmonary disease severity on chest radiographs using convolutional Siamese neural networks

10.1101/2020.05.20.20108159 ◽

2020 ◽

Cited By ~ 3

Author(s):

Matthew D. Li ◽

Nishanth Thumbavanam Arun ◽

Mishka Gidwani ◽

Ken Chang ◽

Francis Deng ◽

...

Keyword(s):

Neural Network ◽

Pulmonary Disease ◽

Disease Severity ◽

Severity Score ◽

Chest Radiographs ◽

Receiver Operator Characteristic ◽

Disease Severity Score ◽

Test Sets ◽

External Test

ABSTRACTPurposeTo develop an automated measure of COVID-19 pulmonary disease severity on chest radiographs (CXRs), for longitudinal disease evaluation and clinical risk stratification.Materials and MethodsA convolutional Siamese neural network-based algorithm was trained to output a measure of pulmonary disease severity on anterior-posterior CXRs (pulmonary x-ray severity (PXS) score), using weakly-supervised pretraining on ~160,000 images from CheXpert and transfer learning on 314 CXRs from patients with COVID-19. The algorithm was evaluated on internal and external test sets from different hospitals, containing 154 and 113 CXRs respectively. The PXS score was correlated with a radiographic severity score independently assigned by two thoracic radiologists and one in-training radiologist. For 92 internal test set patients with follow-up CXRs, the change in PXS score was compared to radiologist assessments of change. The association between PXS score and subsequent intubation or death was assessed.ResultsThe PXS score correlated with the radiographic pulmonary disease severity score assigned to CXRs in the COVID-19 internal and external test sets (ρ=0.84 and ρ=0.78 respectively). The direction of change in PXS score in follow-up CXRs agreed with radiologist assessment (ρ=0.74). In patients not intubated on the admission CXR, the PXS score predicted subsequent intubation or death within three days of hospital admission (area under the receiver operator characteristic curve=0.80 (95%CI 0.75-0.85)).ConclusionA Siamese neural network-based severity score automatically measures COVID-19 pulmonary disease severity in chest radiographs, which can be scaled and rapidly deployed for clinical triage and workflow optimization.SUMMARYA convolutional Siamese neural network-based algorithm can calculate a continuous radiographic pulmonary disease severity score in COVID-19 patients, which can be used for longitudinal disease evaluation and clinical risk stratification.KEY RESULTSA Siamese neural network-based severity score correlates with radiologist-annotated pulmonary disease severity on chest radiographs from patients with COVID-19 (ρ=0.84 and ρ=0.78 in internal and external test sets respectively).The direction of change in the severity score in follow-up radiographs is concordant with radiologist assessment (ρ=0.74).The admission chest radiograph severity score can help predict subsequent intubation or death within three days of admission (receiver operator characteristic area under the curve=0.80).

Download Full-text

DNA Methylation at ATP11A cg11702988 Is a Biomarker of Lung Disease Severity in Cystic Fibrosis: A Longitudinal Study

Genes ◽

10.3390/genes12030441 ◽

2021 ◽

Vol 12 (3) ◽

pp. 441

Author(s):

Fanny Pineau ◽

Davide Caimmi ◽

Sylvie Taviaux ◽

Maurane Reveil ◽

Laura Brosseau ◽

...

Keyword(s):

Cystic Fibrosis ◽

Dna Methylation ◽

Clinical Trials ◽

Lung Disease ◽

Disease Severity ◽

Genome Wide ◽

A Genome ◽

Lung Disease Severity ◽

Epigenetic Biomarker

Cystic fibrosis (CF) is a chronic genetic disease that mainly affects the respiratory and gastrointestinal systems. No curative treatments are available, but the follow-up in specialized centers has greatly improved the patient life expectancy. Robust biomarkers are required to monitor the disease, guide treatments, stratify patients, and provide outcome measures in clinical trials. In the present study, we outline a strategy to select putative DNA methylation biomarkers of lung disease severity in cystic fibrosis patients. In the discovery step, we selected seven potential biomarkers using a genome-wide DNA methylation dataset that we generated in nasal epithelial samples from the MethylCF cohort. In the replication step, we assessed the same biomarkers using sputum cell samples from the MethylBiomark cohort. Of interest, DNA methylation at the cg11702988 site (ATP11A gene) positively correlated with lung function and BMI, and negatively correlated with lung disease severity, P. aeruginosa chronic infection, and the number of exacerbations. These results were replicated in prospective sputum samples collected at four time points within an 18-month period and longitudinally. To conclude, (i) we identified a DNA methylation biomarker that correlates with CF severity, (ii) we provided a method to easily assess this biomarker, and (iii) we carried out the first longitudinal analysis of DNA methylation in CF patients. This new epigenetic biomarker could be used to stratify CF patients in clinical trials.

Download Full-text