ABSTRACT
Features in data samples usually need a unified dimension by a standardization process before clustering. However, there still exists a non-standardized metric in which the distance between samples is greater than 1 after features are standardized. It is difficult to find the optimal search path if the data sample metrics are not standardized. To address this problem, we develop a dynamic-metric accelerated method for fuzzy clustering by introducing a metric matrix, whose diagonal elements consist of infinite norms of the metric matrix into the Fuzzy C-Means (FCM) clustering algorithm and its derived algorithms. More specifically, we focus on constructing a dynamic metric matrix that is used to unify the metric between data samples and updating cluster centers to optimize the search path of the cluster center. In addition, we propose a new evaluation index named the Coefficient of Variation Metric (CVM) to evaluate metric effectiveness. The dynamic metric accelerated method, whose complexity remains unchanged, can effectively accelerate the iteration speed of fuzzy clustering. The comparisons between the algorithm using the dynamic metric accelerated method and the corresponding algorithm on UCI, business district and COVID-19 CT image datasets show the superiority of the dynamic metric accelerated method in accelerating effect and clustering performance.
ABSTRACT
Objective: To analyze the effects of angiotensin converting enzyme inhibitor/angiotensin receptor blocker (ACEI/ARB) on coronavirus disease 2019 (COVID-19) patients with hypertension, and to provide an evidence for selecting antihypertensive drugs in those patients. Methods: Clinical data were retrospectively analyzed in 58 COVID-19 patients with hypertension admitted to Shanghai Public Health Clinical Center from January 20 to February 22, 2020, including epidemiological history, clinical manifestations, laboratory findings, chest CT and outcome. Patients were divided into ACEI/ARB group and non-ACEI/ARB group. Results: Twenty-six patients were in ACEI/ARB group and the other 32 patients in non-ACEI/ARB group, with median age 64.0 (49.5, 72.0) years and 64.0 (57.0, 68.8) years respectively. The median time to onset was 5(3, 8) days in ACEI/ARB group and 4 (3, 7) days in non-ACEI/ARB group, the proportion of patients with severe or critical illness was 19.2% and 15.6% respectively. The main clinical symptoms in two groups were fever (80.8% vs. 84.4%) and cough (23.1% vs. 31.3%). The following parameters were comparable including lymphocyte counts, C-reactive protein, lactate dehydrogenase, D-dimer, bilateral involvement in chest CT (76.9% vs. 71.9%), worsening of COVID-19 (15.4% vs. 9.4%), favorable outcome (92.3% vs. 96.9%) between ACEI/ARB group and non-ACEI/ARB group respectively (all P>0.05). However, compared with non-ACEI/ARB group, serum creatinine [80.49 (68.72, 95.30) µmol/L vs. 71.29 (50.98, 76.98) µmol/L, P=0.007] was higher significantly in ACEI/ARB group. Conclusions: ACEI/ARB drugs have no significant effects on baseline clinical parameters (serum creatine and myoglobin excluded) , outcome, and prognosis of COVID-19 patients with hypertension. Antihypertensive drugs are not suggested to adjust in those patients, but the potential impairment of renal function as elevation of serum creatinine should be paid attention in patients administrating ACEI/ARB drugs.