Book Chapters
Permanent URI for this collection${dspace.ui.url}/handle/20.500.12479/2944
Browse
Recent Submissions
Item AI-Driven Imaging and Diagnostics in Smart Healthcare Systems(Springer Nature, 2025-10-31) Ogundokun, Roseline; Owolawi, Pius; Mkoba, Elizabeth; Olugbemi, Adesanjo; Ogbuju, EmekaArtificial intelligence (AI) has embedded itself into the core of smart healthcare systems, transforming the face of medical diagnosis, especially AI-driven imaging and diagnostic tools. These developments have met the exponentially increasing demand for accuracy, efficiency, and interpretability in healthcare solutions. However, challenges remain regarding optimal performance across diverse datasets and the transparency of AI-driven decision-making. Conventional classification models do not handle the challenge of an imbalanced dataset and generally fail to maintain a balance between precision and recall. Moreover, non-interpretable AI models result in complex deployments in critical applications where decision-making should be transparent. This research article investigates the performance of the SHAP-AI-XNet model, a novel AI-driven imaging and diagnosis tool for smart healthcare systems. This also discussed the evaluation of this model using accuracy, precision, and recall parameters to find their interpretability and suitability to high-stake medical contexts. Overall, 13,244 samples are in the dataset. These are either positive or negative. Below is the description of the performance of a few models that used a confusion matrix and ROC curve; the PR curve also describes it. The results were interpreted using various visual tools, calculating accuracy, precision, recall, and F1-score. The SHAP-AI-XNet model yielded 100% accuracy, precision, recall, and an F1 score of 100%. The ROC curve analysis yielded a perfect AUC of 1.00, indicating a perfect separation between the classes. A similar shape of the PR curve also attested to a high precision value at all recall values, showcasing that the model was reliable and strong. The results stated that the SHAP-AI-XNet model performed very well with a limited number of misclassifications and was highly interpretable. It is an efficient AI-based tool for imaging and diagnostics in smart healthcare systems, ensuring accuracy and reliability for medical decisions. Future work should confirm the scalability and generalizability of the model with more and larger diverse datasets. Besides, enhancing multi-class classification and real-time deployment could strengthen its application in smart healthcare environments.Item Integration of AI-Based for Seamless Operations in Smart Healthcare Systems(Springer Nature, 2025-10-31) Falola, Peace; Awotunde, Joseph; Adeniyi, Abidemi; Mkoba, ElizabethBy improving diagnosis, treatment, and patient management, the fusion of artificial intelligence (AI) into intelligent healthcare systems has completely transformed the way healthcare is delivered. Natural language processing (NLP), deep learning (DL), and machine learning (ML) are examples of AI-driven solutions that improve healthcare decision-making, promote smooth interoperability, and allow for individualized treatment regimens. Applications of AI in electronic health records (EHRs), robotics-assisted surgery, and diagnostic imaging have greatly enhanced patient outcomes and healthcare efficiency. Notwithstanding these developments, issues including algorithmic bias, privacy concerns, and data security still exist. This chapter examines how AI is revolutionizing smart healthcare, highlighting significant technical developments, ongoing uses, and potential future developments.Item Evidence-Based Practices on Co-operative Societies Information Record Management(Springer Nature, 2024-06-30) Germinous, George; Dida, MussaCo-operatives have proved to be one of the driving forces in the socio-economic empowerment of its members. The Government of Tanzania has been implementing the Poverty Reduction Strategy by encouraging people to form co-operatives in order to improve their economic prospects. Establishing a primary co-operative society involves a process which passes through the district co-operative office, regional co-operative office, and the registrar of co-operatives’ office at the national level. These processes bring about the issue of documentation and record keeping. The processing of records is done manually by using pen and paper, or electronically using computers, smart phones, and cameras. The research work essentially used questionnaires, interviews, observations, and document reviews to gather data. The findings of this study show that 8 out of 13 respondents (61.5%) responded to physically visiting co-operative offices to acquire existing records about co-operative societies. This vividly explains the use of manual procedures for co-operative records management thus leading to unsolved challenges such as; data inaccuracy and inconsistency, bureaucracy during physical access, money and time consumption due to geographical challenges, lack of transparency, and improper presentation of co-operative information in request. This ongoing research work avails a web-mobile approach named Co-operative Records Management System (CRMS). CRMS offers a solution that will enable District Co-operative officers (DCOs) to record, process, and generate electronic reports on co-operative societies’ records thus mitigating challenges about, but not limited to; time wastage, inconsistency in recording financial records as well as reducing costs for data acquisition. Thus, this paper presents evidence-based practices on co-operative societies’ information record management, a case of the Kilimanjaro region with a designed proposed solution.Item A Loan Application Management System for Efficient Loan Processing: A Case of Muhimbili SACCOS LTD(Springer Nature, 2024-06-30) Murimi, Luciana; Siebert, Marius; Salira, Godwin; Mkoba, Elizabeth; Ally, MussaMajor parts of the population in emerging markets are still unbanked. The 2021 Global Findex Database shows that only 52% of Tanzanian adults own a formal financial account. Unbanked individuals cannot access capital to grow their businesses. In Tanzania, Savings and Credit Cooperative Organization Societies (SACCOS) have traditionally provided services and products such as loans and savings tailored to fit the needs of the financially excluded. By doing so, tremendous success has been achieved in attaining financial inclusion. However, inefficient manual business processes still pose a great challenge, hindering SACCOS performance and sustainability. Whereas digital solutions such as web and mobile applications have been widely adopted to improve business processes in various sectors, this adoption has been quite slow in the SACCOS sector. Lack of affordable entry-level solutions has resulted in most SACCOS relying on manual paper-based processes. There is therefore need, for the design and implementation of affordable, entry-level digital solutions. This study presents the implementation of a loan application management system: a case of Muhimbili SACCOS LTD. Qualitative methods of data collection were used in identifying system requirements. An Android tablet-based loan application management system was implemented, allowing loan officers to capture rich information required to determine members’ loan eligibility. Through the application, loan officers can retrieve stored loan applications and generate the required templates needed for further processing. For integration with the Core Banking System (CBS), a schema is generated that can be uploaded to the CBS for further loan processing. Thus, achieving an efficient loan application process.