Site Loader
Rock Street, San Francisco

1.0 Introduction

 

 Background

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

 

Text
Mining refers to the discovery of knowledge from textual data. Textual data
contains abundant qualitative information that is difficult to use in
statistical modeling. (Ghosh, Roy, & Bandyopadhyay, 2012). Text mining enables the
conversion of text into numeric formats that can be easily used for analysis. According to (Ghosh et al., 2012), most information (over 80%) is currently stored as text
thus a  need for text mining techniques.

 

In
fields of healthcare, physicians express patient medical records, opinions and
findings in terms of words that contain useful information that can be utilized
to improve the quality of healthcare (Raja, Mitchell, Day, & Hardin, 2008).  The healthcare environment is generally
perceived as being ‘information rich’ yet ‘knowledge poor’. (Rani & Govrdhan, n.d). 
AS1 According to (Belle et al., 2015), Most of healthcare data / clinical information contained
in patient medical records is presented in narrative and unstructured formats
making it difficult for analysis, as a result, healthcare data is often times
not available for analysis. There is a lack of effective analysis tools to
discover hidden relationships and trends in this data (Rani & Govrdhan, 2010). As a result, this information is not easily accessed by humans  to improve healthcare, teaching or research
purposes.

 

According
to (Aggarwal, 2012), textual data requires advanced
algorithmic text mining tools and techniques that can be utilized to discover
hidden relationships and learn interesting patterns from this data in a dynamic
and scalable way. The question is whether healthcare systems in low resource
settings can utilize text mining algorithms to make use of the vast amount of
health care data generated to improve  healthcare.

 

Amidst
the huge amounts of healthcare data collected is the data about HIV/ AIDS.
HIV/AIDS is  still a major global health concern
especially in sub Saharan Africa. According to the Centers for Disease Control
and Prevention (CDC) report (2016), In 2016, 36.7 million people worldwide were
estimated to be living with the  disease
while 1.8 million people become newly infected with HIV. (https://aidsinfo.nih.gov/understanding-hiv-aids/hiv-aids-awareness-days/173/world-aids-day). According to The Joint UN programme
on HIV/AIDS (UNAIDS) report 2016 ,  1.1
million people died from AIDS –related illnesses worldwide .In Uganda,
according to report by Ministry of health, 
31,000 people died from HIV related deaths in 2014, AIDS-related deaths
were 67,000 in 2010 and over 75,000 in the late 1980s and early 1990s.  (https://reliefweb.int/report/uganda/hiv-prevalence-general-population)

 

A study by (John,
2015)AS2 
shows that different people from  HIV/AIDS population are usually  seeking out 
for information in support of self-care, treatment and prevention of the
disease. However, little work has been done to closely examine the information gaps
and information-seeking behaviors of these people especially  in low resource countries like in Sub Saharan
Africa. There have been previous studies to examine information needs and
behaviors , however, most of these have been done in more developed countries
mainly using manual methods of content analysis. Having a better understanding
of the information needs and information-seeking behaviors of individuals in
regards to HIV/AIDS  will provide
guidelines which if utilized will facilitate information interventions that
will bridge the current knowledge gaps for a better health care system in
Uganda. .

The Medical Concierge
Group (TMCG), in Uganda (the test bed for this study) runs a 24/7 free medical
call center. The organization has so far recruited over 1,000 participants on
an mobile health study. This includes both HIV positive and negative
participants. The study is currently running in over 85 districts in the
country. Once recruites,  Participants
are given a toll free telephone number which they can use to contact  qualified medical personnel regarding any
health issues especially those related to HIV/AIDS at any time of the day. Details
of the consultations done and questions asked  are recorded by  medical personnel in database system called
Asterisks. This data, however is recorded in an unstructured text format. The
medical call center contains a vast amount of data that has never been utilizeddue
to the unstructured format of the questions asked. This information could be
representative of the HIV/AIDS information needs in Uganda.  Unfortunately Little is known about what
these participants tend to ask or inquire about in regards to their health.

This study aims at designing a
supervised machine learning text mining method that will  perform an HIV/AIDS question analysis to generate
information on the  HIV information needs
and information seeking behaviors of people on an HIV mobile health
intervention at TMCG (Uganda)

1.1 Research Problem

According to (Belle et al., 2015), Most of the healthcare data / clinical information
contained in patient medical records such as medical history, consultation
notes and findings is presented in narrative and unstructured formats  which make it very difficult for analysis. As
a result, healthcare data is rarely utilized in supporting clinical decisions,
teaching, research purposes or to improve health care. Furthermore, there is a
lack of effective analysis tools to discover hidden relationships and trends in
this data for proper utilization. This study aims at employing text mining
methods to explore patterns and trends in the information seeking needs and
behaviors for HIV/AIDS populations in low resource settings such as Uganda.

 

HIV/AIDS populations have varying needs ((Moradi, Mohraz, & Gouya,
2014)
Most prominent of which is the information need. According to (John, 2015) ,
a thorough understanding of user information needs and behaviour is fundamental
to successful information services. These seek information regarding prevention, treatment and self care of HIV/AIDS in relation
to healthcare services provided . These information needs also vary based
on several social demographic factors such as age, sex and economic status. for
example those who have just found out about their positive HIV status have
different needs such as how to access ARV’s while the youth might desire to learn
about HIV prevention. Women might also have varying needs compared to men. A
thorough understanding of these information needs is very imperative if right
information interventions such as Instant Voice Responses (IVR) for providing
Self Help information is to be implemented. In Uganda, little has been done to
explore and understand these various information needs.

 

This study aims at
designing a  text mining algorithm that
will be used to analyze Health care data. This will be archived through
designing a supervised machine learning Algorithm that will be used to classify
/ categorize HIV/AIDS information needs. The study will help in analyzing
HIV/AIDS related questions from individuals on a mobile health care center
system to identify information needs. Understanding these information needs will
provide guidelines the will aid the designing of better information
interventions in the country to improve the health care system.

 AS1I
think make these literature review Italic so that the reader know that these ar
references and not part of the sentence

 AS2John
who add something else that is abit unique.

Post Author: admin

x

Hi!
I'm Dora!

Would you like to get a custom essay? How about receiving a customized one?

Check it out