Browsing by Author "Kyoyagala, Stella"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A Neonatal Sepsis Prediction Algorithm Using Electronic Medical Record (EMR) Data from Mbarara Regional Referral Hospital (MRRH)
    (Research square, 2022) Ezeobi, Dennis Peace; Wasswa, William; Musimenta, Angella; Kyoyagala, Stella
    Neonatal sepsis is a significant cause of neonatal death and has been a major challenge worldwide. The difficulty in early diagnosis of neonatal sepsis leads to delay in treatment. The early diagnosis of neonatal sepsis has been predicted to improve neonatal outcomes. The use of machine learning techniques with the relevant screening parameters provides new ways of understanding neonatal sepsis and having possible solutions to tackle the challenges it presents. This work proposes an algorithm for predicting neonatal sepsis using electronic medical record (EMR) data from Mbarara Regional Referral Hospital (MRRH) that can improve the early recognition and treatment of sepsis in neonates.Methods A retrospective analysis was performed on datasets composed of de-identified electronic medical records collected between 2015 to 2019. The dataset contains records of 482 neonates hospitalized in Mbarara Regional Referral Hospital, Uganda. The proposed algorithm implements Support Vector Machine (SVM), Logistic regression (LR), K-nearest neighbor (KNN), Naïve Bayes (NB), and Decision tree (DT) algorithms, which were trained, tested, and compared based on the acquired data. The performance of the proposed algorithm was evaluated by comparing it with the physician's diagnosis. The experiment used a Stratified K-fold cross-validation technique to evaluate the performance of the models. Statistical significance of the experimental results was carried out using the Wilcoxon Signed-Rank Test. ResultsThe results of this study show that the proposed algorithm (with the lowest Sensitivity of 95%, lowest Specificity of 95%) outperformed the physician diagnosis (Sensitivity = 89%, Specificity = 11%). SVM model with radial basis function, polynomial kernels, and DT model (with the highest AUROC values of 98%) performed better than the other models in predicting neonatal sepsis as their results were statistically significant.ConclusionsThe study provides evidence that the combination of maternal risk factors, neonatal clinical signs, and laboratory tests effectively diagnose neonatal sepsis. Based on the study result, the proposed algorithm can help identify neonatal sepsis cases as it exceeded clinicians' sensitivity and specificity. A prospective study is warranted to test the algorithm's clinical utility, which could provide a decision support aid to clinicians.
  • Thumbnail Image
    Item
    Newborn care knowledge and practices among care givers of newborns and young infants attending a regional referral hospital in Southwestern Uganda
    (Public Library of Science, 2024-05-07) Nampijja, Dorah; Kyoyagala, Stella; Najjingo, Elizabeth; Najjuma, Josephine N; Byamukama, Onesmus; Kyasimire, Lydia; Kabakyenga, Jerome; Kumbakumba, Elias
    A child born in developing countries has a 10 times higher mortality risk compared to one born in developed countries. Uganda still struggles with a high neonatal mortality rate at 27/1000 live births. Majority of these death occur in the community when children are under the sole care of their parents and guardian. Lack of knowledge in new born care, inappropriate new born care practices are some of the contributors to neonatal mortality in Uganda. Little is known about parent/caregivers’ knowledge, practices and what influences these practices while caring for the newborns. We systematically studied and documented newborn care knowledge, practices and associated factors among parents and care givers. To assess new born care knowledge, practices and associated factors among parents and care givers attending MRRH. We carried out a quantitative cross section methods study among caregivers of children from birth to six weeks of life attending a regional referral hospital in south western Uganda. Using pretested structured questionnaires, data was collected about care givers’ new born care knowledge, practices and the associated factors. Data analysis was done using Stata version 17.0. We interviewed 370 caregivers, majority of whom were the biological mothers at 86%. Mean age was 26 years, 14% were unemployed and 74% had monthly earning below the poverty line. Mothers had a high antenatal care attendance of 97.6% and 96.2% of the deliveries were at a health facility Care givers had variant knowledge of essential newborn care with associated incorrect practices. Majority (84.6%) of the respondents reported obliviousness to putting anything in the babies’ eyes at birth, however, breastmilk, water and saliva were reportedly put in the babies’ eyes at birth by some caregivers. Hand washing was not practiced at all in 16.2% of the caregivers before handling the newborn. About 7.4% of the new borns received a bath within 24 hours of delivery and 19% reported use of herbs. Caregivers practiced adequate thermal care 87%. Cord care practices were inappropriate in 36.5%. Only 21% of the respondents reported initiation of breast feeding within 1 hour of birth, Prelacteal feeds were given by 37.6% of the care givers, water being the commonest prelacteal feed followed by cow’s milk at 40.4 and 18.4% respectively. Majority of the respondents had below average knowledge about danger signs in the newborn where 63% and mean score for knowledge about danger signs was 44%. Caretaker’s age and relationship with the newborn were found to have a statistically significant associated to knowledge of danger signs in the newborn baby. There are variable incorrect practices in the essential new born care and low knowledge and awareness of danger signs among caregivers of newborn babies. There is high health center deliveries and antenatal care attendance among the respondents could be used as an opportunity to increase caregiver awareness about the inappropriate practices in essential newborn care and the danger signs in a newborn.