Background Combination therapy with hydroxychloroquine and darunavir/ritonavir or lopinavir/ritonavir has been suggested as an approach to improve the outcome of patients with moderate/severe COVID-19 infection. Objectives To examine the safety of combination therapy with hydroxychloroquine and darunavir/ritonavir or lopinavir/ritonavir. Methods This was an observational cohort study of patients hospitalized for COVID-19 pneumonia treated with hydroxychloroquine and darunavir/ritonavir or lopinavir/ritonavir. Clinical evaluations, electrocardiograms and the pharmacokinetics of hydroxychloroquine, darunavir and lopinavir were examined according to clinical practice and guidelines. Results Twenty-one patients received hydroxychloroquine with lopinavir/ritonavir (median age 68 years; 10 males) and 25 received hydroxychloroquine with darunavir/ritonavir (median age 71 years; 15 males). During treatment, eight patients (17.4%) developed ECG abnormalities. Ten patients discontinued treatment, including seven for ECG abnormalities a median of 5 (range 2–6) days after starting treatment. All ECG abnormalities reversed 1–2 days after interrupting treatment. Four patients died within 14 days. ECG abnormalities were significantly associated with age over 70 years, coexisting conditions (such as hypertension, chronic cardiovascular disease and kidney failure) and initial potential drug interactions, but not with the hydroxychloroquine concentration. Conclusions Of the patients with COVID-19 who received hydroxychloroquine with lopinavir or darunavir, 17% had ECG abnormalities, mainly related to age or in those with a history of cardiovascular disease.

No abstract

The objective of this work was to benchmark different deep learning architectures for noise detection against cardiac arrhythmia episodes recorded by pacemakers and implantable cardioverter-defibrillators (PM/ICDs) and transmitted for remote monitoring. Up to now, most signal processing from ICD data has been based on classical hand-crafted algorithms, not AI or DL-based ones.The database consist of PM/ICD data from 805 patients representing a total of 10471 recordings from three different channels: the right ventricular (RV), the right atria (RA), and the shock channel.Four deep learning approaches were trained and optimized to classify PM/ICDs' records as actual ventricular signal vs noise episodes. We evaluated the performance of the different models using the F 2 score.Results show that the use of 2D representations of 1D signals led to better performances than the direct use of 1D signals, suggesting that the detection of noise takes advantage of a spectral decomposition of the signal, which remains to be confirmed in other contexts.This study proposes deep learning approaches for the analysis of remote monitoring recordings from PM/ICDs. The detection of noise allows efficient management of this large daily flow of data.

No abstract

No abstract