Muni Repository (MR)
This repository contains open access publications of Muni University Library.
Objectives:
- To digitally collect, preserve and provide electronic access to scholarly works and research output of Muni University.
- Increase the visibility and impact of our research, making it easy for researchers, students, policymakers and journalists to reference, replicate, and re-use the work.
- Issue permanent, unique and trustworthy identifiers when creating URLs to access the resource without concern that the location of the resource may change.
How to publish in Muni Repository
- Contact the library through email: libsupport@muni.ac.ug
Communities in MR
Select a community to browse its collections.
Recent Submissions
An explainable AI framework for neonatal mortality risk prediction in Kenya: Enhancing clinical decisions with machine learning
(Science Publishing Group, 2025-09-30) Lumumba, Victor Wandera; Muriithi, Dennis Kariuki; Njoroge, Elizabeth Wambui; Langat, Amos Kipkorir; Mwebesa, Edson; Wanyama, Maureen Ambasa
Neonatal mortality remains a critical public health challenge in Kenya, with a rate of 21 per 1,000 live births—well above the SDG 3.2 target. While machine learning (ML) offers potential for risk prediction, most models lack transparency and clinical interpretability, limiting their adoption in low-resource settings. This study presents an explainable AI (XAI) framework for predicting neonatal mortality using Kenya Demographic and Health Survey (KDHS) data (N = 2,000), with a focus on model accuracy, fairness, and clinical relevance. Six ML models—Logistic Regression (LR), KNN, SVM, Naïve Bayes, Random Forest, and XG-Boost—were trained and evaluated using in-sample, out-of-sample, and balanced datasets, with performance assessed via AUC, F1-score, sensitivity, specificity, and Cohen’s Kappa. To address class imbalance and enhance generalizability, synthetic oversampling and rigorous cross-validation were applied. Post-balancing, LR achieved optimal performance (AUC = 1.0, κ = 0.98, F1 = 0.987), with SVM (AUC = 0.995) and XG-Boost (AUC = 0.982) also showing higher performance. SHAP and model breakdown analyses identified Apgar scores (at 1st and 5th minutes), birth weight, maternal health, and prenatal visit frequency as key predictors. Fairness assessments across socioeconomic subgroups indicated minimal bias (DIR > 0.8). The integration of XAI enhances transparency, supports clinician trust, and enables equitable decision-making. This framework bridges the gap between predictive accuracy and clinical usability, offering a scalable tool for early intervention. Policy recommendations include embedding this XAI-enhanced model into antenatal care systems to support evidence-based decisions and accelerate progress toward neonatal survival goals in resource-limited settings.
Value of hs‑cTnT, sST2, and Lp‑PLA2 in the classification of acute coronary syndrome
(Spandidos Publications, 2025-08-22) Peng, Hongxin; Lubanga, Nasifu; Sun, Cong; He, Bangshun; Mei, Yan‑Ping; Wang, Yishan
The present study aimed to assess the value of high‑sensitivity cardiac troponin T (hs‑cTnT), soluble suppression of tumorigenicity 2 protein (sST2) and lipoprotein‑associated phospholipase A2 (Lp‑PLA2) in the classification of acute coronary syndrome (ACS). A total of 236 patients diagnosed with ACS were enrolled in this retrospective study and were further divided into the non‑ST‑segment‑elevation (NSTE)‑ACS group (n=183) and ST‑segment elevation myocardial infarction (STEMI) group (n=53). The three biomarkers (hs‑cTnT, sST2 and Lp‑PLA2) were measured by electrochemiluminescence. The diagnostic performance of each biomarker in differentiating ACS subtypes was evaluated through receiver operating characteristic curve analysis. The DeLong test was applied to compare the discriminatory abilities of the different markers. The binary logistic regression model was employed to analyze the factors influencing ACS classification. The levels of hs‑cTnT and sST2 in males were significantly higher in the STEMI group than in the NSTE‑ACS group (P<0.05). hs‑cTnT [odds ratio (OR)=1.010, 95%CI: 1.007‑1.014] and sST2 (OR=1.022, 95%CI: 1.011‑1.033) were identified as good predictors for distinguishing STEMI from NSTE‑ACS, whereas Lp‑PLA2 (P=0.470) was not a suitable biomarker to discriminate between the two types of ACS. Additionally, the diagnostic efficacy of hs‑cTnT [area under curve (AUC=0.861)] and the combination of hs‑cTnT and sST2 (AUC=0.863) was higher than that of sST2 alone (AUC=0.833, P<0.05). In conclusion, these findings illustrated that hs‑cTnT and sST2 are promising biomarkers to classify patients with ACS. Compared with sST2 alone, hs‑cTnT and its combined detection demonstrate superior diagnostic efficiency in identifying ACS.
Maize leaf greenness and yield differential response to the biostimulating effect of Bacillus simplex under irrigation
(University of Zagreb, 2025-05-21) Ocwa, Akasairi; Ssemugenze, Brian; Bojtor, Csaba; Illés, Árpád; Kuunya, Ronald; Okiria, Aisu Latif; Rátonyi, Tamás; Harsányi, Endre
The use of bioinoculants continues to gain research attention due to the need to ensure sustainable soil and crop productivity under climate change. Soil and Plant Analysis Development (SPAD) and Normalized Difference Vegetation Index (NDVI) are useful indicators of leaf greenness that have a positive nexus with yield. These parameters are proper indicators of treatment effects. Therefore, this study examined the biostimulating effect of Bacillus simplex seed inoculation on leaf greenness and yield of maize under irrigated conditions. A field experiment with treatments consisting of maize seeds inoculated with Bacillus simplex and a control under irrigation was conducted. The SPAD and NDVI data were collected at the 12-leaf stage (V12), tasselling stage (VT) and Kernel blister stage (R2), while yield component and yield data were collected at harvest time. Analysed data revealed that Bacillus simplex seed inoculation significantly improved NDVI by 16.42% only at the R2 growth stage. Yield and yield components were significantly optimised by Bacillus simplex seed inoculation. Cob length, cob weight, weight of seeds per cob, number of seeds per cob and weight of 1000 seeds improved by 18.45%, 24.99%, 24.62%, 18.62% and 6.34%, respectively. The overall grain yield was optimised by 26.97% (3.12 t/ha). Therefore, Bacillus simplex can be used as a seed bioinoculant with irrigation to enhance sustainable maize production under climate change.
Prevalence of malaria among individuals living with lymphedema in Kamwenge District, Western Uganda
(Springer Nature, 2025-10-02) Mwesigye, Vicent; Tebulwa, Joanita Berytah; Musinguzi, Benson; Muzafaru, Twinomujuni; Zamarano, Henry; Bagenda, Charles Nkubi; Mulogo, Edgar; Byarugaba, Frederick; Herbert, Itabangi
Lymphedema, also known as elephantiasis, is a long-term and often debilitating condition characterized by the progressive swelling of limbs due to poor lymphatic drainage. While lymphatic filariasis, a mosquito-borne disease, is a common infectious cause globally, non-infectious forms such as podoconiosis resulting from prolonged exposure to mineral-rich soils are also prevalent in many low-resource, endemic regions. In areas where both malaria and lymphedema occur, malaria may further affect individuals already suffering from chronic swelling. In Kamwenge District, Western Uganda, lymphedema is a recognized public health concern, yet the contributing factors remain poorly understood. This lack of clarity complicates effective diagnosis, treatment, and disease control. This study aimed to assess the presence of malaria among individuals living with lymphedema in this setting.
A cross-sectional study was conducted among 154 individuals with clinically confirmed lymphedema, recruited through purposive sampling from Rukunyu Hospital and surrounding communities. Data collection involved structured interviews, physical examinations, and venous blood sampling. Malaria infection was determined through microscopic examination of blood smears.
Of the 154 participants, 71.4% were female, with an average age of 54.7 years. Plasmodium falciparum was detected in 3.3% (n=5) of the individuals. The majority (96.8%) had bilateral lower limb lymphedema and resided in rural areas, primarily engaged in subsistence farming.
The presence of malaria among individuals with lymphedema highlights the need for integrated healthcare approaches in areas where multiple parasitic diseases are endemic. Although malaria was detected in a small portion of participants, its occurrence alongside lymphedema underscores the importance of continued disease surveillance, targeted interventions, and community education to support affected populations.
Navigating the enigmas of unregulated nomadic pastoralism on peasant farmer communities
(East African Nature and Science Organization (EANSO), 2025-09-15) Ocan, Johnson; Eton, Marus; Akello, Jacqueline; Arinaitwe, Julius Alexander
This study investigated the profound implications of the roaming pastoral practices of the Balaalo on peasant farming communities in Northern Uganda, particularly the disruptions resulting from their free-range nomadic lifestyles. Employing a qualitative research design, data were collected through questionnaires and subsequently analysed using MAXQDA’s auto-coding, sentiment, and text-based analytical tools. The target population comprised 600 individuals across affected communities, with 400 participants ultimately completing the study. The reduced participation was largely attributed to the contextual challenges of unregulated pastoralism: seasonal cattle movements and recurrent land conflicts caused widespread displacement, insecurity, and mobility, which hindered consistent engagement. Furthermore, subsistence farmers often prioritised urgent survival activities over research commitments, making the final sample both realistic and representative of community realities. Findings reveal that loosely regulated mobile pastoralism exerts a significant strain on agrarian livelihoods. The Balaalo’s patterns of land encroachment and the destruction of farmlands have intensified tensions across the Acoli, Lango, and Madi subregions, with a high potential for replication in other parts of Uganda if left unaddressed. The study underscores the structural consequences of nomadic incursions, including disruption of local farming systems, heightened food insecurity, and increasing vulnerability among subsistence households. These dynamics highlight the urgent need for effective policy interventions to balance pastoral mobility with agrarian land rights. The study acknowledges certain limitations. Because the analysis draws on case studies within four districts, the findings cannot fully capture the breadth of livelihood adjustments or the nuanced belief systems of all affected communities. Nonetheless, the research provides valuable insights into ongoing structural transformations in northern Uganda. This work makes three critical contributions: first, it demonstrates the long-term consequences of unregulated pastoral mobility on smallholder farming systems; second, it highlights the formation of alternative and adaptive livelihood strategies within contested rangelands; and third, it situates these processes within broader debates on poverty reduction and vulnerability mitigation in pastoral–agrarian interfaces. By foregrounding the lived realities of farmers confronting the pressures of roaming pastoralism, the study advances both scholarly and policy dialogues on land use, livelihood security, and sustainable coexistence in Uganda and beyond.