Few results on cardiac catheterization have been published for patients with sickle cell disease (SCD) with pulmonary hypertension (PHTN). Their survival once this complication develops is unknown. We analyzed hemodynamic data in 34 adult patients with SCD at right-sided cardiac catheterization and determined the relationship of PHTN to patient survival. In 20 patients with PHTN the average systolic, diastolic, and mean pulmonary artery pressures were 54.3, 25.2, and 36.0 mm Hg, respectively. For 14 patients with SCD without PHTN these values were 30.3, 11.7, and 17.8 mm Hg, respectively. The mean pulmonary capillary wedge pressure in patients with PHTN was higher than that in patients without PHTN (16.0 versus 10.6 mm Hg; P ‫؍‬ .0091) even though echocardiography showed normal left ventricular systolic function. Cardiac output was high (8.6 L/min) for both groups of patients. The median postcatheterization follow-up was 23 months for patients with PHTN and 45 months for those without PHTN. Eleven patients (55%) with PHTN died compared to 3 (21%) patients without PHTN ( 2 ‫؍‬ 3.83; P ‫؍‬ .0503). The mean pulmonary artery pressure had a significant inverse relationship with survival (Cox proportional hazards modeling). Each increase of 10 mm Hg in mean pulmonary artery pressure was associated with a 1.7-fold increase in the rate (hazards ratio) of death (95% CI ‫؍‬ 1.1-2.7; P ‫؍‬ .028). The median survival for patients with PHTN was 25.6 months, whereas for patients without PHTN the survival was still over 70% at the end of the 119-month observation period (P ‫؍‬ .044, Breslow-Gehan logrank test). Our findings suggest that PHTN in patients with SCD shortened their sur-

Due to the substantial growth of internet users and its spontaneous access via electronic devices, the amount of electronic contents is growing enormously in recent years through instant messaging, social networking posts, blogs, online portals, and other digital platforms. Unfortunately, the misapplication of technologies has boosted with this rapid growth of online content which leads to the rise in suspicious activities. People misuse the web media to disseminate malicious activity, perform the illegal movement, abuse other people, and publicize suspicious contents on the web. The suspicious contents usually available in the form of text, audio or video, whereas text contents have been used in most of the cases to perform suspicious activities. Thus, one of the most challenging issues for NLP researchers is to develop a system that can identify suspicious text efficiently from the specific contents. In this paper, a Machine Learning (ML)-based classification model is proposed (hereafter called STD) to classify Bengali text into non-suspicious and suspicious categories based on its original contents. A set of ML classifiers with various features has been used on our developed corpus, consisting of 7000 Bengali text documents where 5600 documents used for training and 1400 documents used for testing. The performance of the proposed system is compared with the human baseline and existing ML techniques. The SGD classifier `tf-idf’ with the combination of unigram and bigram features are used to achieve the highest accuracy of 84.57%.

No abstract

No abstract

COVID-19 hits the world like a storm by arising pandemic situations for most of the countries around the world. The whole world is trying to overcome this pandemic situation. A better health care quality may help a country to tackle the pandemic. Making clusters of countries with similar types of health care quality provides an insight into the quality of health care in different countries. In the area of machine learning and data science, the K-means clustering algorithm is typically used to create clusters based on similarity. In this paper, we propose an efficient K-means clustering method that determines the initial centroids of the clusters efficiently. Based on this proposed method, we have determined health care quality clusters of countries utilizing the COVID-19 datasets. Experimental results show that our proposed method reduces the number of iterations and execution time to analyze COVID-19 while comparing with the traditional k-means clustering algorithm.