Health Informatics

Permanent URI for this collection

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

Browse

Now showing 1 - 20 of 239

Assessment of Information Security Culture in Public Hospitals in Southern Nations Nationalities and Peoples Region: The Case of Hawassa Referral Hospital
(Addis Ababa University, 2010-06-01) Temesgen Gebrasilase; Lemma Lessa
Background: - Traditionally, most of the researchers and experts in the field of information security believed a technological solution to address majority of information security issues. However, contemporary studies have shown that non-technical solutions including the human behavior and processes are as important as technical solutions in safeguarding organization information assets. Objective: - To assess the information security culture of Hawassa Referral Hospital in order to improve the existing information security culture of the hospital. Methods: - A cross-sectional survey was conducted in Hawassa Referral Hospital from March-April 2010. A total of 314 study subjects were participated for questionnaire and in-depth interview. The data was collected by using a non-structured pre-tested questionnaire, in-depth interview and document analysis. The quantitative data was analyzed by using SPSS version 15.0 and the qualitative data was analyzed manually. Results: - It was found that, 66.9% of the study participants have no knowledge about information security. About 63% of the respondents reported that management does not assist to the implementation and incorporation of information security in the hospital. The result of the study also showed the absence of well written and documented information security policy in the hospital. Conclusion and recommendations: - The study showed that majority of the respondents in the hospital has no knowledge about information security. The study also revealed that there is a lack of commitment from top management for the incorporation and implementation of information security in the hospital. Hence, it is recommended that there is a need to provide extra-education and training on information security issues
Exploring the Potential of Web-Based Drug Information System Implementation Among Pharmacies and Drug Stores in Addis Ababa
(Addis Ababa University, 2010-06-01) Elias AIemayehu; Alemayehu Mekonnen (PhD)
Background: Web-based drug information system will provide a multifaceted benefit in terms of providing up-to-date, Impartial and scientific drug information (to health professionals as well as allow health professionals where patients can find drugs on their prescription. The study of the potential implementation of such a system in Addis Ababa will provide insights into the status and availability of the premises onto which such a system can be implemented. Objective: The objective of the study was to identify the prospects of implementing a web-based drug information system in Ethiopia, considering the country's unique pharmaceutical sector. The study used IT infrastructure availability, knowledge and attitude of respondents, as well as level of government commitment as outcome variables. Methodology: A cross-sectional survey of 265 pharmacies and drug stores in Addis Ababa was conducted to gather information about their IT infrastructure and the knowledge and attitude of their chief pharmacists and druggists towards the prospective implementation of web-based drug information system. Key informant interviews with designated government officials were also conducted. The responses to the survey questions were analyzed using SPSS software v16.0 whereas thematic classification was used to analyze and interpret the interviews. Important Findings: The survey revealed that 11 7 (44.2%, N=265) Drug Retail Outlets (DROs) have at least one computer in their store. Thirty-three (12.5%) DROs have Internet connection. An additional, 58 (21.9%) and 51 (19.2%) DROs indicated that they have planned to acquire computers and internet connection to their store respectively. In terms of knowledge and attitude. 66% of the respondents had satisfactory knowledge while 73% had a favorable attitude about using web-based DIS in Ethiopia. The study also identified the need for training and continuous education to upgrade the knowledge and skills of health professionals. Conclusion: The majority of respondents have the required knowledge and attitude to use a web-based drug information system. However, more training and continuous education should be provided to health professionals in the field alongside promoting up-to-date drug information use to more drug retail outlets. There is an enabling environment for the commencement of implementing a web-based drug information system in Ethiopia
Assessment of the New Health Management Information System Implementation in Public Health Facilities and Institutions in Addis Ababa.
(Addis Ababa University, 2010-06-01) Tilahun Alemu; Mesfin Addisse
Background :health management information system (HMIS) supports inf strategic decision making through the production of quality data and information for that helps mangers and health workers plan and manage the health service system HI one of the major core activities given due attention even though the ongoing bioprocess re-engineering in HMIS program has resulted several measures to be taken Objective: To assess the new HMIS implementation status in Addis Ababa Methods :A cross section descriptive study was conducted purposive sampling used structured questionnaire in-depth interview and observation were made be march and april 2010 both HMN and PRISM frames were used to evaluate then Result : there were 220 respondents and among them 80% were clinician health the majority of respondents (94.5%) did not participate in the designing efforts of HMIS and one hundred fifty one (68.6%) respondents are currently involving in the activities there is no incentive (93.6%) two hundred and eleven (95.9%) responder HMIS for reporting purpose implementation lacks ownership (19.4%) coordinates leadership(85%) strategy and policy (63,3) motivation (92.7%) shared responsibility among sack holders (57,7%) and not considered as the extension of the previous HIS(92%) Conclusion : large numbers of respondents currently participate in the manual based HMS implementation suffered form ownership follow-up communication and leadership Recommendation : HMIS should be a core activity famished with appropriate human material and financial resources improved data processing and management should be accompanied by skilled and trained health workers with appropriate ICT use management shall support facilitate and motivate information use culture HMIS implementation in Addis Ababa should have ownership follow up coordination and communication among stack holders
Drug Logistics Management Information System at Public Health Facilities in Addis Ababa
(Addis Ababa University, 2010-07) Segid Molla; Assefa Seme (PhD)
In most developing countries the research showed that the public health facilities do not have sufficient health commodities prescribed by the physician. Hence the patients required to buy medicines in the private pharmacies with high prices and others who couldn't afford to buy forego the treatment. There are various reasons for unavailability of drugs in a given country. The study aims to assess how the drug management information system function in the public health facilities administered by Addis Ababa City Administration Health Bureau. The assessment was done between February and April, 2010 in the health facilities of Addis Ababa City Administration . The performance of the logistics system was measured using quantitative and qualitative research instruments at the Addis Ababa City Administration Health Bureau, Sub City Health departments all the 5 hospitals and 10 health centers administered by Addis Ababa City Administration Health Bureau. The management and distribution of essential drugs was also studied. The various stakeholders for the programs were identified and interviewed using a semi structured interview guide. The result of the finding shows that there is no integrated LMIS for all essential drugs. The current LMIS serves only two vertical programs that are ARV drugs and Contraceptives. The essential logistics data is not collected for all essential drugs. There is no logistics management unit responsible for all health products. 86.67 % of the health facilities studied does not have a daily transaction records. Stock cards are not used in 73.33 % of the health facilities. Supervision of the health facilities is not adequately covered. All the store heads are not trained in basic store keeping procedures. The current LMIS design is not fully address all essential drugs, instead it is designed for two vertical programs which are influenced by the donors and have been built around the concerns of donors. The current LMIS practice focuses only on the above stated drugs by neglecting the importance of addressing the basic and critical public health concerns. This study therefore, is intended to assess LMIS application and forward appropriate recommendations particularly emphasizing on the development of logistics management information system for all health commodities with stake holders participation.
Design a Web-Based Maternal Death Surveillance and Response System for Addis Ababa City Administration Health Bureau Ethiopia
(Addis Ababa University, 2017-06) Selamawit Gosaye; Getachew Jemaneh; Wandmu Ayele
Maternal death is the death of a woman while pregnant or within 42 days of terminal ion of pregnancy, irrespective of the duration and sire of the pregnancy. Each maternal death has a story to tell and can provide indications on practical ways of addressing its causes and determinants. Most of these deaths could have been prevented with quality care. Accurate information on how many women died, where they died and why they died is essential, however currently the information is not containing all the necessary data. The Maternal Death Surveillance and Response done with clear standards provide information that can be used in the development of programs and interventions to improve maternal health. The existing paper based MDSR (Maternal Death Surveillance and Response) system has a problem of delaying of data and information flow from each level, lack of data quality, storage and retrieval of data as needed is difficult. Information Communication Technologies (ICTs) can play in improving information and accountability. The aim of the designed project is to automate the current paper based MDSR system in order to access adequate and timely information on the website from local to national level for Addis Ababa City Administration Health Bauer (health extension worker, Woreda Health Administration, health facilities, Sub-City, Addis Ababa Health Bauer and FMoH). The designed project was conducted in Addis Ababa and conceptually designing of the web• based Maternal Death Surveillance System for Addis Ababa City Administration Health Bureau. The project used Unified Process methodology with object oriented approach. 1n order to collect requirements, used a data collection tools (i.e. interview and relevant document review). Analysis and design of the proposed system was performed by using the unified modeling language tools and Microsoft Visio 2013 software. The system prototype is also developed in order 10 understand the design system. System usability test was done to assess effectiveness, efficiency and satisfaction of the users on the developed prototype. The newly design web-based Maternal Death Surveillance System can improve business process of the existing system i.e. death recording , death notification, combine data ,record action plan about modifiable factors contributing to deaths and use the information to prevent similar deaths in the future. 1t solve the challenges of obtaining accurate data, timely report, incompleteness of data, retrieving and storing data based on the need of stakeholders.
Challenges Associated With Physicians Acceptance and Usage of Electronic Medical Records (EMR) in Public Hospitals of Addis Ababa
(Addis Ababa University, 2013-09) Yosef G/Egziabher; Rahel Bekele (PhD)
Background: - Electronic Medical Record systems represent a departure from traditional paper records keeping in that they include all records of patient treatment stored in computerized format. When coupled with networked systems and the internet. the EMR platform offers increased versatility in terms of transferability of information, greater communication among doctors, and improvements in quality of care, just to name a few advantages. Objective : - The general objective of this study is to assess challenges associated with physicians' acceptance and usage of EMR in public hospitals of Addis Ababa. Methods: - A cross-sectional study design with quantitative method was conducted among 11 Hospitals under Addis Ababa Health bureau. Addis Ababa University and Federal Ministry of health from May to June 2013G.C. A total of275 physicians were selected using simple random sampling technique. The data were collected using self administer structured questionnaire. The data were entered and cleaned using Epinfo version 3.5. 1 and analyzed using SPSS version 15. Frequency and percentages were used to describe the study population. Result : - The study revealed that among the total respondents 46.5% learned how to use computers by their own. Only 2.5% of the study participants reported they feel discomfort while using computer. About 53.1% respondents have knowledge of Electronic Medical Records (EM R). About 43.4% responded that they didn' t get enough support from hosp ital administration and only 7.9% participants respond they did get full support. More than ha lf percent of participants acknowledged that time required entering data to the system, reluctant to replace a paper based medical records in order to integrate with EMR, lack of technical training and support. EMR increase in physicians work load and Poor typing ability as major factors affecting acceptance of EMR. Conclusion and Recommendation: - Generally this finding demonstrates that high proportion of physicians was supporting implementation of EMR: however. some factors such as lack of technical training and support. EMR increase work load and time required entering data to the system affect acceptance of it. So stockholders should device adequate training and support to them to solve the problem
Evaluation of Health Management Information System (HMIS) Disease Classification in Capturing Morbidity Data: The Case of Tikur Anbessa Specialized Hospital
(Addis Ababa University, 2010-09) Emawayish Birhanemeskel; Sebesebe Hailemariam
The HMS which draws its data from routine health service and administrative records provide an ideal source for indicators that are reviewed frequently to monitor and refine program implementation. However, the ability of HMIS shortlist in capturing morbidity data specifically has been debated. This study aims to evaluate the HMIS disease classification in capturing morbidity data. A cross sectional study was employed using both quantitative methods in Tikur Anbessa Specialized Hospital (TASH). Purpose sampling technique was used to select 15 key informants for in-depth interviews and morbidity data from abstract disease registers, registered in time period between 01/07/2001 to 30/6/2002 EC. A total of 10848 records were selected from medical and surgical departments to measure the efficiency of HMIS shortlist as compared with ICD-10 special tabulation shortlist for morbidity data as a gold standard. The frequency distributions of disease lists of the HMIS and ICD-10 shortlists were compared and analyzed. The sensitivity and specificity of the HMIS disease lists was assessed and focus was made on four selected ICD-10 chapters. The sensitivity varied among the selected chapters. The highest sensitivity was for chapter I.99.4%. The sensitivity for chapter II. chapter IX . chapter XIV was 45.2%. 54.6% 27.2% respectively. The average sensitivity was 46.3%. The specificity ranges from 86.1% to 100% for the selected ICD-10 chapters, and the average specificity was 96%. In general. This study demonstrated that the HMIS disease classification shortlist is inefficient and incomplete in capturing the overall morbidity data TASH. How ever ,the HMIS shortlist is effective and efficient in capturing morbidity data on infectious and parasitic diseases. The overall findings of this study imply the applications of ICD-10 shortlist with appropriate modifications for morbidity data collection, reporting and analysis in TASH.
Design and Development of Drug Scheduling System for Amanuel Mental Specialized Hospital
(Addis Ababa University, 2017-01-27) Boko, Taditi; Teferi, Derejje (PhD); Deyessa, Nigussie (PhD)
Introduction The application of Information Technology such as computerized physician order entry, automated dispensing cabinets, bedside bar-coded medication administration, and electronic medication reconciliation are important in avoiding medication errors and enhance quality of care. Electronic medication management includes common hospital process such as prescription of medication, dispensing medication orders, and administration of medications. Electronic medication management can reduce medication errors and can also improve efficiency in the medication management process, such as reducing the time required to locate paper medication charts. Objective The objective of this project is to design and implement Drug scheduling system for Amanuel mental specialized hospital Methodology The methodology used to develop the system is Object oriented analysis and design methodology. Requirement was collected using tools such as interview, observation and document review. Analysis and design of the proposed system was conducted using tools like the data process model, uses case diagram, and class diagram Discussion and Result prescription of antipsychotic medication for psychiatric inpatients is not performed with consistent dosage and duration. As the Medical Doctor who prescribes drug for patients told me, knowing the right dosage of medication is difficult. Estimating the range of dosage depends on the current status of the patient and patient’s response to the medication. For example patient can take 5mg morning and 10 mg evening at 12 hours interval. Using the new system to schedule drug for long duration and inconsistent dosage is difficult. Because of these, when there is change in medication, dosage and duration the system can help the user to edit and update this information. Conclusion Administering medication safely is the most crucial part of patient care. Nurse plays a vital role in administering medication. This activity is performed multiple times in a day for an individual patient. It is a complex process therefore accurate documentation of the medication administration is very important.
Designing an Integrated Vital Event Registration System in the Case of Federal Vital Event Registration Agency
(Addis Ababa University, 2016-06-01) Mekonnen, Abdi; Ayalew, Elizabeth (PhD); Mekonnen, Wubegzier (PhD)
Most people in Africa and Asia are born and die without leaving a trace in any legal record or official statistics. The inequalities in registration rates are large; developing countries account for 99% of the estimated 48 million unregistered births, with South Asia and sub-Saharan Africa together accounting for 79% of all unregistered births. Ethiopia is among the countries that have not installed national as well as regional civil registration and vital statistics systems. The overall objective of the proposed project is to design an integrated Vital Event Registration System (IVERS) for the Federal Vital Event Registration Agency so as to register, birth, marriage, divorce, notification, death and causes of death and certification at national level. This study employed Object Oriented methodology and qualitative cross sectional case study design methods. User requirement gathering were made through in depth interview and document analysis as major techniques to capture the core business process of the existing manual system. Accordingly, Unified Modeling Language was applied to specify, visualize, construct and document the architecture of a software system. The designed civil registration and vital statistics system registers all births marriage, divorce and deaths, issues birth and death certificates, notifies the authority birth and death from facilities/communities and compiles and disseminates vital statistics, including cause of death information. The proposed project will have significant impact on the healthcare system, policy makers, legal and administrative users as it is intended to systematically lay a foundation for the implementation of a Civil Registration and Vital statistics system that enables access to easy and much flexible vital event information.
Predicting Under Nutrition Status of Under-Five Children Using Data Mining Techniques: The Case of 2011 Ethiopian Demographic and Health Survey
(Addis Ababa University, 2013-06) Markos, Zenebe; Yifiru, Martha (PhD)
Background: under nutrition is one of the leading causes of morbidity and mortality in children under the age of five in most developing countries including Ethiopia. Objective: The general objective of this study was to design a model that predicts the nutritional status of under-five children using data mining techniques. Methodology: This study followed hybrid methodology of Knowledge Discovery Process to achieve the goal of building predictive model using data mining techniques and used secondary data from 2011 Ethiopia Demographic and Health Survey dataset. Hybrid process model was selected since it combines best features of Cross-Industry Standard Process for Data Mining and Knowledge Discovery in Database methodology to identify and describe several explicit feedback loops which are helpful in attaining the research objectives. WEKA 3.6.8 data mining tools and techniques such as J48 decision tree, Naïve Bayes and PART rule induction classifiers were utilized as means to address the research problem. Result: In this particular study, the predictive model developed using PART pruned rule induction found to be best performing having 92.6% of accurate results and 97.8% WROC area. Promising result has been achieved from the rules regarding nutritional status prediction. Conclusion: The results from this study were encouraging and confirmed that applying data mining techniques could indeed support a predictive model building task that predicts nutritional status of under-five children in Ethiopia. In the future, integrating large demographic and health survey dataset and clinical dataset, employing other classification algorithms, tools and techniques could yield better results. Keywords: Predictive modeling, Nutritional status, children, Data mining, EDHS dataset
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.
Assessment of Client-Health Care Provider Communication at Antenatal Care Clinics in Addis Ababa, Ethiopia
(Addis Ababa University, 2012-06) Tadesse, Worku; Shiferaw, Solomon (PhD); Lamnew, Worksheet (PhD)
Background Health care provider-client communication during Antenatal care is an effective strategy to improve maternal health care seeking behavior and satisfaction with health services. However, the presence of miscommunication, lack of communication, or unsatisfactory communication between health care providers and clients pose a significant challenge in the health care service utilization. Objective The aim of this study was to assess the client-health care provider communication including client satisfaction in public hospitals at antenatal care clinics, in Addis Ababa, Ethiopia. Method: A cross-sectional study design using both quantitative and qualitative methods was employed from October to June 2012. 425 consecutive clients of antenatal care took part in the study. Additionally, in-depth interview was conducted among 15 purposively selected antenatal clients, 17 conveniently selected health care providers using interview guides. Results: The mean (SD) age of antenatal clients was 27.6±4.7 years; majority having secondary (33.4%) and tertiary education (34.4%); and Only 161(37.9%) antenatal clients were satisfied by health care providers‟ quality of communication. Getting care by one provider at different visits (AOR=0.55;95%CI:0.32,0.96), longer duration of time for discussion(AOR=0.29;95%CI:0.11,0.77), clients‟ feeling of privacy(AOR=0.47;95%CI:0.22,0.99),health care providers‟ empathy (AOR=0.41; 95%CI:0.22,0.77) and information provision (AOR=0.09; 95% CI: 0.05, 0.17) were significantly associated with better client satisfaction. Time constraint due to heavy clients‟ load (88.0%), multiple clinical task (71.0%), and lack of dedicated space for communication (58.8%) were the most common barriers of optimal communication reported by health care providers. Conclusion and Recommendation: more than 3 out of 5 of antenatal clients were not satisfied by the providers‟ quality of communication. Insufficient discussion time, suboptimal health care providers‟ empathy and information provision, lack of feeling of privacy and lack of continuity of care by same health care providers were the main factors that contributed to the low antenatal client satisfaction on health care provider‟s quality of communication. Better demonstration of empathy, information provision, longer discussion time, continuity of care with one provider and providing sufficient feeling of privacy should be encouraged to improve antenatal clients‟ satisfaction on health care providers‟ quality of communication. Attempt should be made to free health care providers at ANC from multiple clinical tasks with more attention given to ensuring dedicated space to improve optimal provider-client communication.
Architectural Framework for Information Integration: Case of Organizations Working on Water, Hygiene and Sanitation in Ethiopia
(Addis Ababa University, 2013-05) Mulualem, Wondwossen; Enquselassie, Fikrie (PhD)
Water, Hygiene and Sanitation (WASH) is a subject of intersectoral interest that engages different governmental and non-governmental organizations. As it happens in the other areas of public health, existence of parallel WASH activities makes the sector prone to the problems of fragmentation, lack of consistency and other problems that plagued the sector. Such problems were felt at the national level by the Ethiopian government and, as the result, movement towards integrating all WASH activities in the nation was started by drafting a WASH implementation Framework (WIF) and Memorandum of Understanding which eventually was signed by four governmental organizations. The WIF aims at integrating all aspects of WASH activities, including the information system, under one umbrella and the interest of this research lies on exploring the possibility for creating a framework for an integrated WASH information system that can be shared by all stakeholders. The main objective of this research was to study the current status of WASH data creation, management and sharing practices among organizations working in the sector and propose an architectural framework that can be considered as a guide to setup an Integrated WASH information system. To this end, this research focused on the use of indicators as primary tools for data integration and attempted to study types of WASH activities performed and indicators used by target organizations, types of data they collect under each indicator, formats for data collection including the data attributes being used, standards being used for formulation of indicators and practice of sharing between organization working in the sector. Relevant data was collected mainly through semi-structured interviews and analysis of relevant documentations provided by the respondents. The result was eventually used to propose an architectural framework that can be considered as a starting point for practitioners working in the area. The framework was discussed with selected respondents for checking its validity and the overall reaction of the respondents was found to be positive. Keywords: Health Information Architecture, Health Information Architectural Framework, Water, Hygiene and Sanitation information System, Water, hygiene and Sanitation information Integration, Public Health Information System, Indicator-data Linkage. Indicator definition, Indicator standardization, standardized data definition
Data Exchnage Interoprability Framework for Laboratory Information System (Lis) and Electronic Health Record (Ehr) of Two Hospitals in Addis Ababa
(Addis Ababa University, 2013-06) Shiferaw, Wondwosen; Enquselassie, Fikre (PhD)
Background: eHealth applications are key to facilitate the health care delivery by increasing access and quality. However, those applications are vary in design and structure. Interoperability between those applications is important that creates a bridge and facilitates the data exchange between two different eHealth applications. In Ethiopian hospitals, eHealth applications are characterized by small-scale in size with greater duplication of efforts. For instance, one of the gap has been the integration of applications such as Laboratory information system (LIS) and Electronic Health Record (EHR) due to limited interoperability in laboratory data exchange between these applications in the Hospitals. Objectives: The objective of this study is to assess the existing LIS and EHR for data exchange interoperability and identify challenges with the view to explore the possibility of proposing and developing data exchange interoperability framework. Methodology: In this study, an attempt is made to apply qualitative research method to explore the status of e-Health applications (LIS and EHR). Interviews were used tool for data collection. We have also collect the criteria from the literature on LIS and EHR application functionality testing. Finally, then constructive method helped for design data exchange interoperability framework on eHealth applications in the case of LIS and EHR. We used NVivo-10 software for coding the interview and analyze the data. Results: In this study, lacks of interoperability and coordination cause for fragmentation of systems and data redundancy on eHealth applications which are the main challenges in the Hospitals. In order to overcome the data exchange interoperability problems in the Hospitals, the researcher suggested data exchange interoperability framework between LIS and EHR. The framework is tested by the developers and decision makers. The proposed and designed framework is encouraging for future change. Conclusion: the study was designed to explore the current status of eHealth applications in the selected case. The investigator shown that there have been challenges in terms of data exchange interoperability, integration and coordination of the systems. The proposed data exchange interoperability framework is a possible solution to address the challenges
Assessment of the Feasbility of Using Text Messages Among Art Follow-Up Patients to Improve Drug Adherence in Selected Art Units in Addis Ababa City Administration. Addis Ababa
(Addis Ababa University, 2010-06) Hailu Tsega; Fantahun Mesganaw (Professor)
Back ground: PLWHA on ART follow –up individuals may or may not have mobile phones, ability to use text messages and willingness to receive text message reminders to take their drugs .But the extent of theses desires and how it varies by individual, social, health and demographic characteristics is not well understood. Objective: to assess the feasibility of using text messages among ART follow up patients to improve drug adherence in selected ART units in Addis Ababa city administration Method: The study was undertaken from March to April 2010, using quantitative cross-sectional study supplemented by qualitative in-depth interview on a sample of 461 PLWHA on ART follow up care for quantitative and 14 respondents for qualitative. Study subjects were selected using stratified random sampling method. A pre- tested structured questionnaire was used to collect data; Data were entered, cleaned, and analyzed using SPSS version 16 Result- One hundred twenty five (82.8%) male and ninety-three (79.5%) female over all 218 (81.3 %) of the total respondents PLWHA on ART follow-up in Addis Ababa were willing to receive (SMS) text message reminders. Of those who have willingness to receive text message reminders had disclosure of HIV status to their partner or family with (adjusted OR: 0.03, 95%CI :( 0.01-0.08) times more likely willing to receive SMS text message reminders than those who did not disclose their HIV status. In addition, respondents who attended elementary school (adjusted OR: 8.21, 95% CI: 1.59-42.33) times more likely to receive text message than those who do not attended school and those who secondary school (adjusted OR: 58.65, 95% CI: 12.18-280.12) times more likely to receive text messages than those who did not attended school. One hundred forty eight (68.2%) of PLWHA on ART follow-up individuals wanted to receive text message reminders of time to take their drugs Conclusion: High proportion of HIV positive individuals on ART follow-up wanted to receive text message reminders, of time to take their drugs. Their willingness to receive text message reminders of these people has implication to introduce or adoption (SMS) text message technology with designed special computer software program that automatically sends special message service (SMS) to improve drug adherence.
Assessment of Knowledge Sharing Practices of Health Care Professionals in Hospitals Under Addis Ababa Health Bureau
(Addis Ababa University, 2011-06) Yalew Tirualem; Addisse Mesfin (PhD)
Background: - Knowledge is the most important strategic resource in organizations, and its management is critical to organizational success. Knowledge sharing is a social interaction culture, involving the exchange of employee knowledge, experiences, and skills through organization. However there is no previous study that assesses the knowledge sharing practice in AA. Therefore the purpose of this study is to assess the knowledge-sharing practices and identify factors that affect knowledge sharing practices among health professionals. Objective: -To investigate the level and factors associated with knowledge-sharing practice among health care professionals in public hospitals of Addis Ababa. Methods:-A cross-sectional study with both quantitative and qualitative methods was conducted among 5 hospitals under Addis Ababa Health Bureau from May to June 2011 G.C. Total of 318 respondents were selected using simple random sampling technique. The data were collected using self administered structured questionnaire and to supplement the quantitative study in-depth interviews were also conducted. The data were entered and cleaned using Epinfo version 3.5.1 and analyzed using SPSS version 16. Frequencies and percentages were used to describe the study population and Logistic regression with 95% confidence interval was used to assess the presence and degree of association between dependent and independent variables. Result: - The study revealed that 50.3% of the respondents were engaged in active knowledge sharing practice. More than half (57.2%) of the respondents were not satisfied with their job, and 69% of participants report the absence of motivational schema in their health institutes. Over all 72% of respondents are willing to share their knowledge. The factors that were independent predictors of knowledge sharing were job satisfaction, very high level of motivation, extrinsic motivation, use of communication channel and the presence of knowledge sharing opportunity. Those respondents who were satisfied with their job were more likely to share their knowledge than the others with the odds ratio, AOR[95%CI] 1.73[1.00-2.98], who had high level of motivation were more likely to share their knowledge than the others with the odds ratio, AOR[95%CI] 3.38[1.04-11.00], and those respondents who were extrinsically motivated were more likely to share their knowledge than the others with the odds ratio, AOR[95%CI] 1.75[1.02-2.99].The respondents who used communication channels were more likely to share their knowledge than the others with the odds ratio , AOR[95%CI] 3.05[1.71-5.45] and who had knowledge sharing opportunity were more likely to share their knowledge than the others with the odds ratio, AOR[95%CI] 2.89[1.70-4.90]. Conclusion and Recommendation: - From this study most of the respondents were aware of the importance of knowledge sharing but only half of respondents were engaged on active knowledge sharing practice, and the factors that were independent predictors of knowledge sharing were job satisfaction, high level of motivation, extrinsic motivation, use of communication channel, the presence of knowledge sharing opportunity. So stake holders (AAHB, the hospitals) should device a way for strengthen knowledge sharing practice through improving all the hinderers of knowledge sharing.
Assessment of the New Health Management Information System Implementation in Public Health Facilities and Institutions in Addis Ababa
(Addis Ababa University, 2010-06) Alemu Tilahun; Addisse Mesfin (PhD)
Background: Health Management Information System (HMIS) supports informed strategic decision making through the production of quality data and information for action that helps mangers and health workers plan and manage the health service system. HMIS is one of the major ’core’ activities given due attention even though the ongoing ‘businessprocess re-engineering’ in HMIS program has resulted several measures to be taken. Objective: To assess the new HMIS implementation status in Addis Ababa. Methods: A cross–sectional, descriptive study was conducted. Purposive sampling was used. Structured questionnaire, in-depth interview and observation were made between March and April 2010. Both HMN and PRISM frameworks were used to evaluate the results. Result: There were 220 respondents and among them, 80% were clinician health workers. The majority of respondents (94.5%) did not participate in the designing efforts of the new HMIS and one hundred fifty one (68.6%) respondents are currently involving in the HMIS activities. There is no incentive (93.6%).Two hundred and eleven (95.9%) respondents use HMIS for reporting purpose. Implementation lacks ownership (91.4%), coordination and leadership (85%), strategy and policy (63.3%), motivation (92.7%), shared responsibility among stack holders (57.7%) and not considered as the extension of the previous HIS(92.%). Conclusion: large numbers of respondents currently participate in the manual based HMIS activities through a well designed data collection and reporting formats. A short period on job-training, absence of incentive, motivation and lack of management support lead to poor information use culture that is limited mainly for a send-report purpose. HMIS Implementation suffered from ownership, follow-up, communication and leadership. Recommendation: HMIS should be a core activity furnished with appropriate human, material and financial resources. Improved data processing and management should be accompanied by Skilled and trained health workers with appropriate ICT use. Management shall support, facilitate and motivate information use culture. HMIS implementation in Addis Ababa should have ownership, follow up, coordination, cooperation and communication among stack holders. Key words: HMIS, HIS, Data Quality, Information Use, Implementation status.
Mining Echocardiography Data to Predict Heart Disease (Medphd)
(Addis Ababa University, 2012-06) Habte, Thomas; Meshesha, Million (PhD)
Background: These days, a major challenge of health care is reaching to correct diagnosis of specific disease condition. Poor clinical decision leads to catastrophic consequences which are unacceptable. Decision making process at the health care setting needs to be supported with more advanced technology including a computer based information system. Objective: This study aims at extracting hidden knowledge (patterns and relationships) associated with echocardiography datasets and designing a predictive model for heart disease detection using data mining techniques. Methods: A Hybrid Data Mining methodology is followed, which is a six-step knowledge discovery process. The data for this research obtained from International Cardiovascular Hospital in Addis Abeba, Ethiopia. This study investigates the use of different data mining techniques, Decision tree, neural network, and support vector machine for classification tasks. On Transthoracic Echocardiography report datasets, descriptive data summarization and visualization were taken to gain understanding of the data. Moreover, missing values, outliers data, data integration and transformation were managed at preprocess stage of hybrid process model. Results: The results show that all the models performed well, though J48 Decision tree algorithms outperforms support vector machine, Multilayer Perceptron Neural Network, registering 96.73%. The best attributes selected by J48 decision tree are Left Atrium Systole Diameter, LV ejection fraction, and Tricuspid velocity. As per discussion made with the cardiologist, one of the interesting rule, a patient with Left atrium systole diameter less than or equal to 40 millimeter and LV ejection fraction less than or equal to 51% blood pumped out of ventricles and Tricuspid velocity is greater than 2.5 centimeter per second results Left Ventricle dysfunction and Pulmonary hypertensive disorder. Conclusion: The result thus obtained in this study is promising to apply data mining for heart disease detection. To make usable the knowledge extracted in this study, an attempt has made to design a knowledge-based system that shows the potential to integration. It is a further research direction.Keywords: Echocardiography, Knowledge discovery process, Decision tree, neural network, Support vector machine
Application of Data Mining For Predicting Adult Mortality
(Addis Ababa University, 2012-06) Hailemariam, Tesfahun; Meshesha, Million (PhD)
Background: The fast-growing, tremendous amount of data, collected and stored in large and massive data repositories, has far exceeded human ability for comprehension without powerful tools. As a result, data collected in large data repositories become seldom visited. This in turn, calls the application of data mining technology. Every year, more than 7·7 million children die before their fifth birthday. However, over three times those of nearly 24 million adults die every year. Less attention has been given to adults which are the most productive phase of life for both economic and social ramification of families and countries. Objective: The general objective of this research is to construct adult mortality predictive model using data mining techniques so as to identify and improve adult health status using BRHP open cohort database. Methods: The hybrid model that was developed for academic research was followed. Dataset is preprocessed for missing values, outliers and data transformation. Decision tree and Naïve Bayes algorithms were employed to build the predictive model by using a sample dataset of 62,869 records of both alive and died adults through three experiments and six scenarios. Result: In this study as compared to Bayes, the performance of J48 pruned decision tree reveals that 97.2% of accurate results are possible for developing classification rules that can be used for prediction. If no education in family and the person is living in rural highland and lowland, the probability of experiencing adult death is 98.4% and 97.4% respectively with concomitant attributes in the rule generated. The likely chance of adult to survive in completed primary school, completed secondary school, and further education is (98.9%, 99%, 100%) respectively. Conclusion: The study suggests that education plays a considerable role as a root cause of adult death, followed by outmigration. Further comprehensive and extensive experimentation is needed to substantially describe the loss experiences of adult mortality in Ethiopia. Key words: BRHP data, Mortality, Adult, predictive model, J48 decision tree, Data Mining.
Application of Data Mining Techniques to Discover Cause of Under-five Children Admission to Pediatric Ward: The case of Nigist Eleni Mohammed Memorial Zonal Hospital
(Addis Ababa University, 2012-06) Dileba, Temesgen; Teferi, Dereje (Associate Professor)
Background: - Health care system is potential area to apply and take the advantage of data mining. Higher priority is given for the prevention and control of preventable disease at home or community level. However, for seriously ill children admissions should be facilitated in order to save the life of the child. Objectives: - The objective of this study is to apply data mining techniques on under five children dataset in developing a model that support the discovery of the causes for under-five children admission to pediatric ward. Methodology: - Cross industry standard process for data mining process model was applied. Major processes covered were business understanding, data understanding, data preprocessing, modeling and evaluation. Decision tree and artificial neural network algorithms were tested for classification tasks in Waikato Environment for Knowledge Analysis. Exploratory data analysis techniques, graphs and tabular formats for visualization and accuracy, true positive rate, false positive rate, receiver operating characteristic and the idea of experts were used for evaluation of the model. The dataset used was records in integrated registration log book in under-five outpatient department. Result: - The decision tree algorithm J48 has higher accuracy (94.77%), weighted true positive rate (94.7%), weighted false positive rate (5.3%), weighted receiver operating characteristics (0.99) and performs much faster than multilayer perceptron. According to interesting rules in J48 presenting complaint of not taking any food, fluid or breast feeding (98.32%), low weight for age without sunken eyes (92.31%) and very low weight for age but not in association with restless or irritable (98.33%) are among the cause of under-five children admission to pediatric ward without any consideration of health information management system admission disease classification. Conclusion: - In conclusion, encouraging results are obtained in classification tasks, data mining technique is applicable on pediatric dataset in developing a model that support the discovery of the causes of under-five children admission to pediatric ward. The outcome of this study serves primarily users in the domain area, decision makers and planners.

Browse

Recent Submissions