scholarly journals Automated pancreatic cyst screening using natural language processing: a new tool in the early detection of pancreatic cancer

HPB ◽  
2015 ◽  
Vol 17 (5) ◽  
pp. 447-453 ◽  
Author(s):  
Alexandra M. Roch ◽  
Saeed Mehrabi ◽  
Anand Krishnan ◽  
Heidi E. Schmidt ◽  
Joseph Kesterson ◽  
...  
Keyword(s):  
Pancreatic Cancer ◽  
Natural Language Processing ◽  
Early Detection ◽  
Natural Language ◽  
Language Processing ◽  
Pancreatic Cyst

Sa307 NATURAL LANGUAGE PROCESSING IMPROVES THE IDENTIFICATION OF IPMN CYSTS AMONG PATIENTS WITH PANCREATIC CYST DIAGNOSTIC CODES

2021 ◽  
Vol 160 (6) ◽  
pp. S-479
Author(s):  
Natalia Khalaf ◽  
Hannah R. Abrams ◽  
Eke Chiemeziem ◽  
Ann Xu ◽  
Hardeep Singh ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Pancreatic Cyst ◽  
Diagnostic Codes

scholarly journals Prediction of suicidal ideation in young people from the analysis of texts in social networks written in Mexican spanish: a review of the state of the art

2020 ◽  
pp. 29-33
Author(s):  
Gabriel AGUILERA-GONZÁLEZ ◽  
Christian PADILLA-NAVARRO ◽  
Carlos ZARATE-TREJO ◽  
Georges KHALAF
Keyword(s):  
Social Networks ◽  
Natural Language Processing ◽  
Early Detection ◽  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
The State ◽  
World Health ◽  
Mexican Spanish ◽  
The World

Suicide prevention is one of the great issues of the current era. Institutions such as the World Health Organization, have continued to search for all possible alternatives for early detection and timely prevention. Suicide rates have grown more and more in the world, and Mexico, although it is not the country with the most suicides, is one of the countries with the highest growth in recent years. At present, the use of social networks has generated great changes in the way we communicate. Expressing yourself through a social network begins to be more common than expressing ourselves to human beings. Several studies, which will be presented later, show that it is possible to determine from the content of social networks: cases of depression, risk of suicide, and other mental problems. The use of technological tools, such as Natural Language Processing, has served as an effective ally for the early detection of risks, such as abuse, bullying or even detecting emotional problems. The present research seeks to carry out an in-depth analysis in the state of the art of the application of Natural Language Processing as an ally for the detection of suicide risk from the analysis of texts for Mexican Spanish in Social Networks.

scholarly journals COVID19: A Natural Language Processing and Ontology Oriented Temporal Case-Based Framework for Early Detection and Diagnosis of Novel Coronavirus

2020 ◽  
Author(s):  
Olaide Nathaniel Oyelade ◽  
Absalom E. Ezugwu
Keyword(s):  
Natural Language Processing ◽  
Early Detection ◽  
Natural Language ◽  
Language Processing ◽  
World Health ◽  
Case Based Reasoning ◽  
The World ◽  
Detection And Diagnosis ◽  
Early Detection And Diagnosis ◽  
Case Based

Coronavirus, also known as COVID-19, has been declared a pandemic by the World Health Organization (WHO). At the time of conducting this study, it had recorded over 1.6million cases while more than 105,000 have died due to it, with these figures rising on a daily basis across the globe. The burden of this highly contagious respiratory disease is that it presents itself in both symptomatic and asymptomatic patterns in those already infected, thereby leading to an exponential rise in the number of contractions of the disease and fatalities. It is therefore crucial to expedite the process of early detection and diagnosis of the disease across the world. The case-based reasoning (CBR) model is an effective paradigm that allows for the utilization of cases’ specific knowledge previously experienced, concrete problem situations or specific patient cases for solving new cases. This study therefore aims to leverage the very rich database of cases of COVID-19 to interpret and solve new cases even at their early stage to the advanced stage. The approach adopted in this study employs a natural language processing (NLP) technique to parse records of cases and thereafter formalize each case which is represented as a mini-ontology file. The formalized case is therefore parsed into a CBR model to allow for classification of the case into positive or negative to COVID-19. Meanwhile, feature extraction for each case is done by classifying tokens extracted by the NLP approach into special, temporal and thematic classes before encoding them using an ontology modeling method. The CBR model therefore leverages on the formalized features to compute the similarity of the new case with extracted similar cases from the archive of the CBR model. The proposed framework was populated with 68 cases obtained from the Italian Society of Medical and Interventional Radiology (SIRM) repository. Results obtained revealed that the proposed approach leverages on locations (spatial) and time (temporal) of contagion to successfully detect cases even in their early stages of two days onward before the incubation period of fourteen days. The proposed framework achieved an accuracy of 97.10%, sensitivity of 0.98 and specificity of .066. The study found that the proposed model can assist physicians to easily diagnose and isolate cases, thereby minimizing the rate of contagion and reducing false diagnosis as observed in some parts of the globe.

A Review and evaluation of Machine Translation methods for Lumasaaba

2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Research Area ◽  
Data Driven ◽  
East African ◽  
Data Set ◽  
African Languages ◽  
Translation Methods

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.

Sign in / Sign up

Export Citation Format

Share Document