Kibuspace

Kibuspace is the institutional repository of Kibabii University, the repository preserves the University's research legacy and all aspects of knowledge generated by KIBU community for posterity

 

Communities in DSpace

Select a community to browse its collections.

Recent Submissions

No Thumbnail Available
Item
Feasibility, acceptance, and workflow integration of an AI- enabled clinical decision support system for non- communicable diseases in Kiambu County, Kenya: A mixed- methods implementation evaluation
(Open Research Africa, 2026-02-28) Kamau, David; Mbuguah, Samuel Mungai; Omondi, Protus; Kamau, Gideon; Mbugua, George; Ngugi, Rosslyn; Ngure, Jane; Ngaruiya, Njeri; Wamaitha, Nicole; Munene, Joan; Maina, Njogu; Gitaka, Jesse
Background Non-communicable diseases (NCDs), particularly hypertension and diabetes, impose a growing burden on health systems in low- and middle- income countries like Kenya. Artificial intelligence (AI)-driven Clinical Decision Support Systems (CDSS) may enhance diagnostic accuracy and adherence to clinical guidelines, yet their feasibility and acceptability among frontline clinicians in real-world settings underexplored. Methods We conducted a mixed-methods implementation study in 10 health facilities in Kiambu County, Kenya. The evaluation comprised three components. First, a retrospective review of 1,929 patient records established baseline NCD prevalence and care patterns. Second, we assessed the clinical acceptance of the NCDAI platform, an AI-CDSS using a Large Language Model with Retrieval-Augmented Generation, through 300 independent expert physician reviews of its recommendations. Third, we captured clinician perspectives via a cross-sectional Knowledge, Attitudes, and Practices (KAP) survey (n=29) and key-informant interviews (n=11). Results The baseline cohort demonstrated a substantial NCD burden: 72.8% had a history of hypertension and 43.1% had diabetes. Expert validation showed high acceptance of AI-generated recommendations, with 67.0% “Agreed,” 26.3% “Partially Agreed,” and only 6.7% “Disagreed,” yielding 93.3% overall (partial or full) agreement. Most disagreements arose in medication and treatment plan recommendations. Clinicians demonstrated strong digital readiness; 86% reported moderate or good IT proficiency, and 69% were already aware of AI in healthcare. Patient-related factors were the most commonly cited barriers to NCD care (33%). Qualitative findings identified operational challenges particularly duplicative data entry arising from parallel paper-based workflows as the main impediment to NCDAI adoption amid high patient volumes. Conclusions An AI-driven CDSS for NCD management is feasible and highly acceptable to expert physicians and frontline clinicians in Kenya. The key barrier is not reluctance toward AI but workflow friction. Effective scale-up will require investment in digital infrastructure to enable seamless integration and replacement of paper-based systems
No Thumbnail Available
Item
Modeling User Experience with Universities Websites Based on Webometric Ranking User Analysis
(International Journal of Computer Trends and Technology (IJCTT), 2020-04-27) Mukanda, Adeline; Mbuguah, Samuel Mungai; Wabwoba, Franklin; Aselemo, Peters Ikoha
The paper sets posits that Universities are ranked globally based on their web presence. The web crawler accesses the universities websites to collect data on presence, visibility, openness, and excellence. These data is then used to rank the Universities based on set criteria. The paper identifies design issues that may affect website ranking. The paper identifies as a gap lack of user analysis model for university website and recommends a study of the same.
No Thumbnail Available
Item
Framework for Evaluation of Effectiveness of Integrated Financial Management Information Systems Architecture Implemented in Public Hospitals in Kenya
(International Journal of Scientific Research in Science, Engineering and Technology, 2020-12-12) Afwande, Margaret; Mbuguah, Samuel Mungai; Kilwake, Juma
Integrated Financial Management Information System (IFMIS), is an enterprise resource planning application that captures all functional processes and relevant financial flows within Public expenditure management. IFMIS is being adopted by the Public hospitals to promote efficiency, effectiveness, accountability, transparency, security of data management and comprehensive reporting. However the Public hospitals are loosing a lot of money through scandals and this has compromised service delivery to the Public. Therefore, the purpose of this study was to investigate the effectiveness of IFMIS as used in Public procurement services in Public Hospitals in Kenya and come up with an enhanced secure technical architecture. The objectives of the study were: to asses the extent to which IFMIS has been implemented in Public procurement services in Public hospitals in Kenya, to evaluate the effectiveness of IFMIS in enforcing logical access and technical controls in Public procurement services in Public Hospitals in Kenya and to develop a framework that will evaluate the effectiveness of IFMIS architecture that is implemented in Public procurement services in Public hospitals in Kenya .The study used mixed method research design targeting users of IFMIS. Stratified sampling was used to select the target population of 132 in 4 hospitals in Kenya. The target population was from 5 homogeneous stratum comprising of 44 Procurement Assistants, 36 Finance Assistants, 12 Audit Assistants, 28 Medical Practioneers and 12 ICT Staff. Proportional allocation method was used to calculate the sample size which was 99 respondents. The data was collected through questionnaires and direct observation. Content validity was done to ascertain the validity of the research instruments. Reliability of the instruments was carried out using test- retest technique. Internal consistence of data was computed using Cronbach Alpha Computation. Analysis of Quantitative and qualitative data was through descriptive and inferential statistics methods and content analysis respectively. The study developed a framework of enhanced technical architecture of IFMIS that would streamline procurement services in Public hospitals and improve provision of quality health care.
No Thumbnail Available
Item
Webometrics User Ranking Analysis Model Development and Validation
(International Journal of Computer and Organization Trends, 2022-04-26) Mukanda, Adeline; Mbuguah, Samwel Mungai; Wabwoba, Franklin
The webometrics user ranking analysis model was developed and validated. The need for the model arose as directorates of ICT in Kenyan Universities were assigned the challenge of improving their university's webo ranking. Webo ranking is the preferred method of the universities to showcase their niche and what they do to the global community. There are no published models for webometrics ranking. This leads to each university taking different approaches. In this paper, a model has been developed and validated.
No Thumbnail Available
Item
Leveraging P2P Architecture and Semantic Web for Enhanced Resource Discovery
(International Journal of Scientific Research in Science, Engineering and Technology, 2024-05-18) Kirui, Leonard K.; Mbuguah, Samuel Mungai; Ronoh, Richard K.
Web 4.0, also known as the next generation, intelligent internet, possesses the potential to become a widely and universally used communication medium for various types of information. However, its decentralized architecture lacks strong semantic support, resulting in an internet that is disorganized. The current system lacks the capacity to facilitate users' effective information discovery, extraction, and integration from multiple sources. Additionally, it fails to give consumers efficient tools for manipulating and turning acquired data into knowledge that is useful. Peer-to-peer (P2P) overlay technologies have recently come to light as a way to improve resource discovery on the internet. In dynamic and large- scale situations, these technologies provide a scalable framework for allocating, sharing, and gaining access to resources. The purpose of this research is to discuss on semantically enabled web architecture that makes use of P2P overlay technology. This architecture aims to facilitate structured and precise access to internet resources and promote knowledge sharing among community members who share similar interests. The paper examines the core elements of the semantic web architecture, which encompass the services and protocols responsible for resource advertising, discovery, and management, methods and material. It then delve into the hybrid peer-to-peer (P2P) overlay structure, specifically focusing on indexing and resource location, and explores the mechanisms necessary to facilitate scalable routing within a distributed environment.