Establishing a Carotid Artery Stenosis Disease Cohort for Comparative Effectiveness Research Using Natural Language Processing

Author(s):  
Robert W. Chang ◽  
Lue-Yen Tucker ◽  
Kara A. Rothenberg ◽  
Elizabeth M. Lancaster ◽  
Andrew L. Avins ◽  
...  
VASA ◽  
2017 ◽  
Vol 46 (4) ◽  
pp. 268-274
Author(s):  
Erhan Saraçoğlu ◽  
Ertan Vuruşkan ◽  
Yusuf Çekici ◽  
Salih Kiliç ◽  
Halil Ay ◽  
...  

Abstract. Background: After carotid artery stenting (CAS), neurological complications that cannot be explained with imaging methods may develop. In our study we aimed to show, using oxidative stress markers, isolated oxidative damage and resulting neurological findings following CAS in patients with asymptomatic carotid artery stenosis. Patients and methods: We included 131 neurologically asymptomatic patients requiring CAS. The neurological findings were evaluated using the modified Rankin Scale (mRS) prior to the procedure, one hour post-procedure, and two days after. Patients with elevated mRS scores but with or without typical hyperintense lesions observed on an MRI and with changes of oxidative stress marker levels at the time (Δtotal-thiol, Δtotal antioxidative status [TAS], and Δtotal oxidant status [TOS]) were evaluated. Results: In the neurological examination carried out one hour prior to the procedure, there were 92 patients with mRS = 0, 20 with mRS = 1, and 12 with mRS = 2. When Δtotal-thiol, ΔTAS, and ΔTOS values and the mRS were compared, it was observed that as the difference in oxidative parameters increased, clinical deterioration also increased proportionally (p = 0.001). Conclusions: We demonstrate a possible correlation between oxidative damage and neurological findings after CAS which could not be explained by routine imaging methods.


2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.


Diabetes ◽  
2019 ◽  
Vol 68 (Supplement 1) ◽  
pp. 1243-P
Author(s):  
JIANMIN WU ◽  
FRITHA J. MORRISON ◽  
ZHENXIANG ZHAO ◽  
XUANYAO HE ◽  
MARIA SHUBINA ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document