Abstract: This paper reports a structured literature review of the
application of Health Information Technology in developing
countries, defined as the World Bank categories Low-income
countries, Lower-middle-income, and Upper-middle-income
countries. The aim was to identify and classify the various
applications of health information technology to assess its current
state in developing countries and explore potential areas of research.
We offer specific analysis and application of HIT in Libya as one of
the developing countries. A structured literature review was
conducted using the following online databases: IEEE, Science
Direct, PubMed, and Google Scholar. Publication dates were set for
2000-2013. For the PubMed search, publications in English, French,
and Arabic were specified. Using a content analysis approach, 159
papers were analyzed and a total number of 26 factors were identified
that affect the adoption of health information technology. Of the 2681
retrieved articles, 159 met the inclusion criteria which were carefully
analyzed and classified. The implementation of health information
technology across developing countries is varied. Whilst it was
initially expected financial constraints would have severely limited
health information technology implementation, some developing
countries like India have nevertheless dominated the literature and
taken the lead in conducting scientific research. Comparing the
number of studies to the number of countries in each category, we
found that Low-income countries and Lower-middle-income had
more studies carried out than Upper-middle-income countries.
However, whilst IT has been used in various sectors of the economy,
the healthcare sector in developing countries is still failing to benefit
fully from the potential advantages that IT can offer.
Abstract: It is well known that Logistic Regression is the gold
standard method for predicting clinical outcome, especially
predicting risk of mortality. In this paper, the Decision Tree method
has been proposed to solve specific problems that commonly use
Logistic Regression as a solution. The Biochemistry and
Haematology Outcome Model (BHOM) dataset obtained from
Portsmouth NHS Hospital from 1 January to 31 December 2001 was
divided into four subsets. One subset of training data was used to
generate a model, and the model obtained was then applied to three
testing datasets. The performance of each model from both methods
was then compared using calibration (the χ2 test or chi-test) and
discrimination (area under ROC curve or c-index). The experiment
presented that both methods have reasonable results in the case of the
c-index. However, in some cases the calibration value (χ2) obtained
quite a high result. After conducting experiments and investigating
the advantages and disadvantages of each method, we can conclude
that Decision Trees can be seen as a worthy alternative to Logistic
Regression in the area of Data Mining.