A Phase II randomised controlled trial of oral prednisolone in early diffuse cutaneous systemic sclerosis (PRedSS).

OBJECTIVES: Although the painful and disabling features of early diffuse cutaneous systemic sclerosis (dcSSc) have an inflammatory basis and could respond to corticosteroids, corticosteroids are a risk factor for scleroderma renal crisis. Whether or not they should be prescribed is therefore highly contentious. Our aim was to examine safety and efficacy of moderate dose prednisolone in early dcSSc. METHODS: PRedSS set out as a Phase II, multicentre, double-blind randomised controlled trial, converted to open-label during the Covid-19 pandemic. Patients were randomised to receive either prednisolone (∼0.3 mg/kg) or matching placebo (or no treatment during open-label) for 6 months. Co-primary endpoints were the Health Assessment Questionnaire Disability Index (HAQ-DI) and modified Rodnan skin core (mRSS) at 3 months. Over 20 secondary endpoints included patient reported outcome measures reflecting pain, itch, fatigue, anxiety and depression, and helplessness. Target recruitment was 72 patients. RESULTS: Thirty-five patients were randomised (17 prednisolone, 18 placebo/control). The adjusted mean difference between treatment groups at 3 months in HAQ-DI score was -0.10 (97.5% CI -0.29-0.10), p= 0.254, and in mRSS -3.90 (97.5% CI -8.83-1.03), p= 0.070, both favouring prednisolone but not significantly. Patients in the prednisolone group experienced significantly less pain (p= 0.027), anxiety (p= 0.018) and helplessness (p= 0.040) than control patients at 3 months. There were no renal crises, but sample size was small. CONCLUSION: PRedSS was terminated early primarily due to the Covid-19 pandemic, and so was underpowered. Therefore, interpretation must be cautious and results considered inconclusive, indicating the need for a further randomised trial. TRIAL REGISTRATION: ClinicalTrials.gov, https://clinicaltrials.gov, NCT03708718.

Speech as a Biomarker for COVID-19 Detection Using Machine Learning.

The use of speech as a biomedical signal for diagnosing COVID-19 is investigated using statistical analysis of speech spectral features and classification algorithms based on machine learning. It is established that spectral features of speech, obtained by computing the short-time Fourier Transform (STFT), get altered in a statistical sense as a result of physiological changes. These spectral features are then used as input features to machine learning-based classification algorithms to classify them as coming from a COVID-19 positive individual or not. Speech samples from healthy as well as "asymptomatic" COVID-19 positive individuals have been used in this study. It is shown that the RMS error of statistical distribution fitting is higher in the case of speech samples of COVID-19 positive speech samples as compared to the speech samples of healthy individuals. Five state-of-the-art machine learning classification algorithms have also been analyzed, and the performance evaluation metrics of these algorithms are also presented. The tuning of machine learning model parameters is done so as to minimize the misclassification of COVID-19 positive individuals as being COVID-19 negative since the cost associated with this misclassification is higher than the opposite misclassification. The best performance in terms of the "recall" metric is observed for the Decision Forest algorithm which gives a recall value of 0.7892.