Health Informatics

Permanent URI for this collection

http://etd.aau.edu.et/handle/123456789/204

Browse

Browsing Health Informatics by Author "Addisse Adamu (PhD)"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Analyzing the Outbreak Surveillance and Response System in Ethiopia using Data Mining Techniques
    (Addis Ababa University, 2012-11) Mohammed Yimer; Abebe, Ermias (PhD); Addisse Adamu (PhD)
    The aim of this research work was to show the applicability of data mining techniques for the development of descriptive and predictive model to disease outbreak surveillance datasets in Ethiopia. To do that the three data mining applications such as classification, clustering and association rules mining were undertaken to explore the important applications to the datasets of the PHEM sectors from different perspectives. A total of 18600 records were collected and assessed from the data store of the surveillance system from the year 2004-2012G.C. After the preprocessing phase of knowledge discovery in databases of data mining application a total of 8796 records were prepared for data mining algorithms. From the total records filtered and prepared for model preparation 4703 were from the IDSR system dataset and the remaining 4093 records were taken from that of the PHEM dataset from the year 2004- 2008G.C. and 2009-2012G.C. respectively. The researcher analyzed two classification algorithms for the prediction of Epidemic typhus disease cases with decision tree J48 classifiers and Naïve Bayes classifiers. Finally the more performing algorithm has been taken for model development. From the results of the experiments done decision tree algorithm had a better performance to classify the disease cases in place and time setting. The accuracy rate of correctly classifying the Epidemic Typhus disease cases by the use of decision tree J48 algorithm was 87.44% whereas with Naïve Bayes classifier was 83.70%. The sensitivity and specificity test was also done for the two classifiers. The researcher also attempted to analyze the application of association rule mining to find some sort of correlation or patters among disease cases of the surveillance data. The attributes were selected only from the disease cases for the occurrence and nonoccurrence, which were collected in time and place bases. Here, Apriori association rule mining algorithm was run to find interesting patterns among the occurrence and co-occurrence of disease cases which were correlated together. The researcher used 20% for the minimum support and 90% for minimum confidence threshold before the application of the mining algorithm. The researcher took the combined (integrated) datasets for cluster analysis with the total numbers of 8796 records with 9 attributes. Simple K-Means clustering algorithm was used for the combined datasets since; the algorithm showed the grouping of disease cases with respect to time and place. In general data mining techniques were important and applicable in the classification, clustering and association rules model development for emerging and reemerging disease cases. But the datahas to have good quality with the inclusion of important attributes of variables for better prediction and description model development The results of the research, apart from its education purpose, were also used for the planning, preparedness, decision making, and disease control and prevention activities to the domain experts.
  • No Thumbnail Available
    Item
    Assessment of Health Management Information System in Harari Regional State
    (Addis Ababa University, 2010-06) Mahtsentu Mebrahtu; Addisse Adamu (PhD); Tamiru Melesse (PhD)
    Background: an organization succeeds by bringing together and managing resources in a productive way. Health information has been variously described as the “foundation” for better health, as the “glue” holding the health system together, and as the “oil” keeping the health system running. There is a big concern for the improvement of the health care services delivery system, which is widely seen to be attributed to the shortcomings of health management information system in the developing countries; where World Health Organization calls for reform. Objective of the research: To asses the current status of health management information system implementation in Harari Regional Health Bureau and suggest possible solutions for improvement. Methodology: The numbers of health facilities participated in the study were 2 hospitals and 5 health centers. A cross – sectional study was used to generate data from these health facilities in Harari Regional Health Bureau. Self administered structured questionnaire and in-depth interview with administrative units and service providers were conducted for quantitative and qualitative data collection respectively. Physical observation was also made by the investigator to supplement the qualitative findings. Result: The sex distribution of participants working in the study units showed that 121 (44.8%) were males while 149 (55.2%) were females. Out of 270 respondents 179 (66.3%) answered that there was no regular training given about the new health management information system but 55 (20.4%) of them reported that there was regular training given to the staff’s. The remaining 36 (13.3%) didn’t know whether training was given to the staff or not. Regarding utilization of information generated from the facility at the unit/department level, 60 (22.2%) of them reported that they were using the information, whereas 202 (74.4%) of them were not utilized the information at all. Other 8 (3%) of them didn’t know whether the information was utilized or not. Conclusion: from this study it can be concluded that the utilization level of health management information system in health facilities under the study was far below the standard expectations. It is recommended from this study that assignment of adequate staff, given on job training, and given periodic feedback to improve the HMIS of the studied facilities. Key words: HMIS, HIS, data quality, utilization of health information system
  • No Thumbnail Available
    Item
    Designing A Predictive Model For Heart Disease Detection Using Data Mining Techniques
    (Addis Ababa University, 2011-07) Damtew Abel; Meshesha Million (PhD); Addisse Adamu (PhD)
    Background: Most countries face high and increasing rates of heart disease or Cardiovascular Disease. Even though, modern medicine is generating huge amount of data every day, little has been done to use this available data to solve the challenges that face a successful interpretation of echocardiography examination results. Objective: To design a predictive model for heart disease detection using data mining techniques from Transthoracic Echocardiography Report dataset that is capable of enhancing the reliability of heart disease diagnosis using echocardiography. Methodology: Knowledge Discovery in Database (KDD) methodology consisting of nine iterative and interactive steps was adopted to extract significant patterns from a dataset containing 7,339 echocardiography examination reports of patients. The data used for this study was collected by International Cardiovascular Hospital from October, 2008 to March, 2011. Results: The findings of this study revealed all the models built from J48 Decision Tree classifier, Naïve Bayes classifier and Neural Network have high classification accuracy and are generally comparable in predicting heart disease cases. However, comparison that is based on True Positive Rate suggests that the J48 model performs slightly better in predicting heart disease with classification accuracy of 95.56%. Conclusion: This study showed that data mining techniques can be used efficiently to model and predict heart disease cases. The outcome of this study can be used as an assistant tool by cardiologists to help them to make more consistent diagnosis of heart disease. Keywords: KDD, Data Mining, Decision Tree, Neural Network, Bayesian classifier, Heart Disease
  • No Thumbnail Available
    Item
    Improving Data Quality and Information Use In Maternal and Child Health Departments of Health Centers: The Case of Desire City Administration, South Wollo, Amhara Region
    (Addis Ababa University, 2017-05) Hailu Shewaye; Jemaneh Getachew (PhD); Addisse Adamu (PhD)
    Background:-. Effective Health Management Information System (HMIS) is essential for setting priority for community based problems, for allocation of budget and human resource and usage of health data that assist decision makers and stakeholders manage and plan resources at every level of health service. In Africa, including Ethiopia there are many problems in data management in the health sector in relation to missing of data in reports this leads to a picture which could not represent the country health information. Objective: - To assess and improve HMIS data quality and information use in maternal and child health departments of health centers in Dessie City Administration. Methodology: Pre and post interventional cross sectional descriptive study design was employed using both quantitative and qualitative approaches. The project was carried out in the MCH departments all eight fully functional health centers found in Dessie City Administration. World Health Organization (WHO) data quality assessment (DQA) tool was adopted which included data management, reporting system assessment and data verification. Semi-structured interview guide was also used to identify factors influencing data quality and information use. The assessment involved interview of responsible person, source document review and on-site observation. The study was based on eight key MNCH indicators and considered the second quarter data starting from October to December 2016. Based on the pre-assessment finding, the following interventions were carried out: on-job training; strengthening performance monitoring team, mentoring, fulfilling data collection tools/forms, and data audit. RESULT: - The result of the project showed that proportion of HMIS data accuracy has been increased from about 83 % before to 97 % after intervention which was compared with the Ethiopian National HSDP IV target which was 90%. Similarly, availability of all indicators source documents increases from 87% to 100%. Of the available indicator source documents level of HMIS data completeness has been increased from about 86% before to 98 % after intervention. However, timeliness ranges from 83 % to 100%.Regarding data management and reporting system, these four areas were in turn weighted based on composite sub componentsand are scored between zero and three, with 2.5 - 3.0 indicating full system strength, 1.5 – 2.49 indicating partial strength and less than 1.5 indicating no use system in place. Accordingly after intervention data management and reporting system components complete system strength was documented. M&E structure, function and capabilities scored about from 2.4 to 2.9; use of standard data collection and reporting tools and guidelines scored from 2.2 to 2.8; data management process from 2.3 to 2.5 and information use 1.4 to 2.7at all service delivery points. Lack of continuous training, lack of supportive supervision, lack of HMIS material supply, low management support and lack of feedback were identified as the contributing factors for the minimum use of HMIS information in the department. CONCLUSION:-For improving HMIS data quality and information use practice in maternal and child health departments;. Simple, strategic and practical interventional activities were carried out throughout the project. The interventional activities of this project on HMIS data quality and information use practice more or less increased the data management and reporting system, the accuracy, completeness and timeliness of HMIS data reporting that paved the way for continuous information use in Health Centers. RECOMMENDATION:-The health centers management should flow the annual plan to the department and individual level and perform routine performance monitoring per the schedule according to the plan and the health centers employ similar intervention mechanism for the other departments.
  • No Thumbnail Available
    Item
    Utilization of Information and Communication Technologies (ICTs) for Accessing Health Information by Physicians in Addis Ababa Private Hospitals
    (Addis Ababa University, 2013-10) Kibru Sahle; Addisse Adamu (PhD); Kebede Gashaw (PhD)
    Background: Information and communication technologies (ICTs) are defined as digital and analogue technologies that facilitate the capturing, processing, storage and exchange of information via electronic communication. ICTs have the potential to improve information management, access to health services, quality of care, continuity of services, and cost containment. So that, the use of Information Communication Technologies (ICTs) within healthcare can makes significant changes in the daily operations of hospitals. Objective: These were to: identify the available ICTs tools and services to the physicians; identify the purposes of ICTs utilization by the physicians in private hospitals; determine the extent to which the existing information services meet information needs of the physicians; assess the factors to access and utilize of ICTs by the physicians; and explore the knowledge and attitudes of the physicians to utilize ICTs for their work. Methodology: A cross-sectional survey of 147 physicians in private hospitals in Addis Ababa was conducted to gather the availability and utilization of ICTs for accessing health information to their daily clinical activities. A self-administered questionnaire was used to collect data. Data were analyzed using SPSS version 16.0, and summery measures, descriptive statistics and logistic regression analysis were used for interpreting and presentation the data. Important Findings: The survey revealed that physicians 34.7% had own Smart phones, 87 have flush disk for their work , only forty-nine(33.8%) physicians survey reported that they have computer available in the hospitals accessed for their works, among those thirty-three (22.4%) physicians reported that they have internet connection in the hospitals. In terms of knowledge and attitudes 74% of physicians had satisfactory knowledge ICTs utilization and 71% of physicians’ also favorable attitudes towards ICTs for their daily activities. The study also predicted the relation between the outcome variable and the possible factors. Physicians’ activity, working experience, computer access and computer training are found to have significant effect on ICTs utilization. Similarly, physicians’ level of specialty, computer accessibility, working burden and taking forma computer training found to have significant effects among possible factors on physicians attitude towards ICTs utilization for daily operations. Conclusion: Information has been critical part of the medical professionals’ /physicians/ armament of tools to provide patient care. Utilizing ICTs can offer the physicians with enhanced access to: key data at all levels from international to local, electronic libraries of evidence, peer reviewed research and practice guidelines, and network of professionals in health and related disciplines. While information access is critical in delivery of quality health care services, there are many problems that are inherent in attempting to meet the information needs of physicians at private Hospitals.