Browsing by Author "Bbosa, Francis Fuller"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Assessing Users Involvement in Analysis and Design Tasks of Electronic Health Information Systems: Experiences, Challenges, and Suggestions to Optimise Involvement
    (Journal of Health Infomatics in Africa, 2019) Akello, Christine Kalumera; Bbosa, Francis Fuller; Nabukenya, Josephine
    Background: User requirements play a vital role in the development of usable EHIS. For developers to design better quality, relevant and safer EHIS that meet user needs, they are required to actively engage stakeholders especially in the analysis and design tasks of its development life cycle. This is because they provide context appropriate solutions based on their needs. However, in most cases developers ignore health stakeholders’ input especially during these tasks due to varying perspectives and expectations, complexity, high cost, and variability in time to complete the tasks. This has resulted into various challenges including difficulty in capturing and interpreting user requirements in an effective and efficient manner, poorly designed and unusable systems, unsatisfied user needs, and high maintenance costs. This study thus aimed at assessing users’ involvement in the analysis and design tasks when developing EHIS with a view to understand their experiences, challenges, and suggestions to optimise their involvement. Methods: We employed a cross-sectional survey to investigate and describe the level of user involvement and challenges faced in the analysis and design tasks of the EHIS development process. A total of 36 health practitioners from 13 Key health institutions located in Uganda were selected as respondents. Results: The study revealed that majority of the respondents was involved in EHIS development, with a few involved at analysis and design tasks. Increased costs associated with data collection, followed by lack of consensus in clarifying, articulating and defining user requirements were recorded as the biggest challenges faced by users at requirements gathering, analysis and system design tasks. Regards suggestions to optimising users’ involvement in EHIS development tasks, the study reported that users were very much interested in being involved at all tasks of EHIS development, and consultation of users was paramount in order to incorporate all their needs in EHIS. Conclusions: The results from the study demonstrate the value of user involvement at the analysis and design tasks of EHIS development cycle. User involvement offers benefits in form of reduction in costs, improved productivity due to users easily arriving at a common consensus and positive growth in user attitudes. The researchers intend to incorporate suggestions that emerged from this study to conduct long-term evaluations of existing EHIS and investigate how users’ involvement changes over time.
  • Thumbnail Image
    Item
    On the Goodness of Fit of Parametric and Non‑Parametric Data Mining Techniques: The Case of Malaria Incidence Thresholds in Uganda
    (Health and Technology, 2021) Bbosa, Francis Fuller; Nabukenya, Josephine; Nabende, Peter; Wesonga, Ronald
    To identify which data mining technique (parametric or non-parametric) best fits the predictions on imbalanced malaria incidence dataset. The researchers compared parametric techniques in form of naïve Bayes and logistic regression against non-parametric techniques in form of support vector machines and artificial neural networks and their goodness of fit and prediction was assessed using 10-fold and 5-fold cross-validation on an independent validation dataset set to determine which model best fits the predictions on imbalanced malaria incidence dataset. The 10-fold cross-validation outperformed the 5-fold cross-validation in all performance metrics with the naïve Bayes classifier attaining accuracy of 69% with a sensitivity of 90.9%, a specificity of 55.6%, a precision of 55.6% and F-measure score of 69.0%, the logistic regression achieved an accuracy of 65.5% with a sensitivity of 83.3%, a specificity of 52.9%, a precision of 55.6% and F-measure score of 66.7%, the support vector machines achieved an accuracy of 82.8% with a sensitivity of 88.2%, a specificity of 75.0%, a precision of 83.3%, and F-measure score of 85.7% whereas the artificial neural networks registered an accuracy of 89.7% with a sensitivity of 94.1%, a specificity of 83.3%, a precision of 88.9%, and F-measure score of 91.4%. Non-parametric data mining techniques in form of artificial neural networks and support vector machines outperformed the parametric data mining technique in form of naïve Bayes in making predictions emanating from imbalanced malaria incidence dataset on account of registering higher F-measure values of 91.4% and 85.7% respectively.
  • Thumbnail Image
    Item
    Reliability of Predictions Using Hybrid Models: The Case of Malaria Incidence Rates in Uganda
    (Journal of Health Informatics in Africa, 2020) Nabende, Peter; Bbosa, Francis Fuller; Wensonga, Ronald; Nabukenya, Josephine
    Background and purpose: Reliability of estimates emanating from predictive independent data mining techniques is a complex problem. This could be attributed to cross-cutting weaknesses of individual techniques such as collinearity due to high dimensionality of attributes in a dataset, biasedness due to under fitting and over fitting of data as well as noise accumulation due to outliers and thus affecting the reliability of predictions emanating from these models. This study thus aimed at developing a hybrid data mining technique for predicting reliable malaria incidence rate thresholds. Methods: The decision tree and naïve Bayes classifiers were used to build a hybrid prediction model. Results of the developed hybrid model were compared with independent data mining models using 10- fold cross-validation on a previously unlearned data set. Accuracy, F-measure and the area under the receiver operating characteristics curve (AUC) were the key performance metrics used to evaluate the generalizability of the hybrid model in comparison to the independent models. Results: Findings revealed that the hybrid classifier attained an accuracy of 79.3% and an F-measure score of 84.2%, the naïve Bayes classifier achieved accuracy and F-measure value of 69% while the decision tree classifier registered an accuracy of 72.4% and an F-measure score of 80%. Conclusions: The developed hybrid model outperformed both independent decision tree and naïve Bayes models. Hence merging several independent homogeneous predictive data mining techniques enhances the accuracy of the estimates leading to reliable estimates.