ABSTRACT
OBJECTIVE: To evaluate the impact of hypertension on the clinical outcome of COVID-19 patients aged 60 years old and older. METHODS: This single-center retrospective cohort study enrolled consecutive COVID-19 patients aged 60 years old and older, who were admitted to Liyuan Hospital from January 1, 2020 to April 25, 2020. All included patients were divided into two groups: hypertension and nonhypertension group. The baseline demographic characteristics, laboratory test results, chest computed tomography (CT) images and clinical outcomes were collected and analyzed. The prognostic value of hypertension was determined using binary logistic regression. RESULTS: Among the 232 patients included in the analysis, 105 (45.3%) patients had comorbid hypertension. Compared to the nonhypertension group, patients in the hypertension group had higher neutrophil-to-lymphocyte ratios, red cell distribution widths, lactate dehydrogenase, high-sensitivity C-reactive protein, D-dimer and severity of lung lesion, and lower lymphocyte counts (all P<0.05). Furthermore, the hypertension group had a higher proportion of intensive care unit admissions [24 (22.9%) vs. 14 (11.0%), P=0.02) and deaths [16 (15.2%) vs. 3 (2.4%), P<0.001] and a significantly lower probability of survival (P<0.001) than the nonhypertension group. Hypertension (OR: 4.540, 95% CI: 1.203-17.129, P=0.026) was independently correlated with all-cause in-hospital death in elderly patients with COVID-19. CONCLUSION: The elderly COVID-19 patients with hypertension tend to have worse conditions at baseline than those without hypertension. Hypertension may be an independent prognostic factor of poor clinical outcome in elderly COVID-19 patients.
Subject(s)
COVID-19 , Hypertension , Aged , COVID-19/complications , Hospital Mortality , Humans , Hypertension/complications , Hypertension/epidemiology , Middle Aged , Retrospective Studies , SARS-CoV-2ABSTRACT
Given the outbreak of COVID-19 pandemic and the shortage of medical resource, extensive deep learning models have been proposed for automatic COVID-19 diagnosis, based on 3D computed tomography (CT) scans. However, the existing models independently process the 3D lesion segmentation and disease classification, ignoring the inherent correlation between these two tasks. In this paper, we propose a joint deep learning model of 3D lesion segmentation and classification for diagnosing COVID-19, called DeepSC-COVID, as the first attempt in this direction. Specifically, we establish a large-scale CT database containing 1,805 3D CT scans with fine-grained lesion annotations, and reveal 4 findings about lesion difference between COVID-19 and community acquired pneumonia (CAP). Inspired by our findings, DeepSC-COVID is designed with 3 subnets: a cross-task feature subnet for feature extraction, a 3D lesion subnet for lesion segmentation, and a classification subnet for disease diagnosis. Besides, the task-aware loss is proposed for learning the task interaction across the 3D lesion and classification subnets. Different from all existing models for COVID-19 diagnosis, our model is interpretable with fine-grained 3D lesion distribution. Finally, extensive experimental results show that the joint learning framework in our model significantly improves the performance of 3D lesion segmentation and disease classification in both efficiency and efficacy.