The District Health Information Systems 2 (DHIS2) has been implemented in many countries as a standard tool for managing health information for decision making. Despite the continued adoption of this system in developing countries, some challenges affecting its effective use still exist. Previous studies have indicated that the majority of these challenges are mainly infrastructural and system related. As ICT infrastructure continues to improve, the need to investigate challenges affecting DHIS2 usage beyond infrastructural and system factors is important. In this study, factors influencing DHIS2 usage in Sierra Leone were investigated using the Technology-Organization-Environment (TOE) framework. Mixed sequential explanatory design was adopted using data from 126 respondents in 10 districts followed by focus group discussions. The study found that top management support, perceived benefits, security and privacy, and compatibility were significant predictors of DHIS2 usage in Sierra Leone. Similarly, poor Internet connectivity, lack of security policies and guidelines, and shortage of qualified staff were identified as challenges affecting the effective use of DHIS2. Recommendations for helping the Ministry of Health and Sanitation in Sierra Leone and other donors to ensure that DHIS2 is effectively used are discussed.
Coccidiosis, Salmonella, and Newcastle are the common poultry diseases that curtail poultry production if they are not detected early. In Tanzania, these diseases are not detected early due to limited access to agricultural support services by poultry farmers. Deep learning techniques have the potential for early diagnosis of these poultry diseases. In this study, a deep Convolutional Neural Network (CNN) model was developed to diagnose poultry diseases by classifying healthy and unhealthy fecal images. Unhealthy fecal images may be symptomatic of Coccidiosis, Salmonella, and Newcastle diseases. We collected 1,255 laboratory-labeled fecal images and fecal samples used in Polymerase Chain Reaction diagnostics to annotate the laboratory-labeled fecal images. We took 6,812 poultry fecal photos using an Open Data Kit. Agricultural support experts annotated the farm-labeled fecal images. Then we used a baseline CNN model, VGG16, InceptionV3, MobileNetV2, and Xception models. We trained models using farm and laboratory-labeled fecal images and then fine-tuned them. The test set used farm-labeled images. The test accuracies results without fine-tuning were 83.06% for the baseline CNN, 85.85% for VGG16, 94.79% for InceptionV3, 87.46% for MobileNetV2, and 88.27% for Xception. Finetuning while freezing the batch normalization layer improved model accuracies, resulting in 95.01% for VGG16, 95.45% for InceptionV3, 98.02% for MobileNetV2, and 98.24% for Xception, with F1 scores for all classifiers above 75% in all four classes. Given the lighter weight of the trained MobileNetV2 and its better ability to generalize, we recommend deploying this model for the early detection of poultry diseases at the farm level.
The use of modern information and communication technology plays a significant role in healthcare services improvement. In the recent years, various mobile application systems have been deployed in the health sectors of different developing countries to facilitate remote data collection and transmission so as to improve its quality and availability. Consequently, understanding the factors contributing to mobile technology acceptance is imperative. The purpose of this study was to adopt a modified UTAUT theoretical model to understand the factors influence acceptance and use of mobile health applications by health workers at health facilities in Tanzania. Questionnaires were used to collect data from health facilities workers. Out of 150 health facilities workers, only 108 return, a 72% return rate whose data was statistically analyzed using SPSS tool. The findings show that effort expectancy and facilitating conditions significantly influence the users located in the urban area on behavioral intention to use mobile health applications. Furthermore, the study shows that the constructs such as social influence, training adequacy, and voluntariness of use do not have a significant influence on the use of mobile health applications.
Background: The Government of Tanzania through the Ministry of Finance and Planning implemented the Government Electronic Payment Gateway (GePG) system to improve the whole cycle of revenue management. As of June 2020, the system has been implemented in 660 institutions, 28 commercial banks, and 6 mobile money operators. Whilst the initial acceptance of this system is positive, relatively no study has evaluated its effectiveness in meeting the expected benefits. Elsewhere, similar systems showed initial acceptance at the beginning, followed by failures after some years of use. Therefore, it is important to evaluate the effectiveness of GePG system to find out how effectively public money is spent.Objective: The objective of this study was to evaluate the success of GePG system using users’ satisfaction as a success measure.Method: The study adapted the updated Delone and Mclean Information Systems success model whereby perceived usefulness and trust in system were added as new factors. The sequential explanatory design research design integrating quantitative and qualitative data within a single investigation was adopted. A total of 442 users from 271 institutions in 11 regions in Tanzania participated in the study.Results: Trust in system, information quality, and perceived usefulness had a significant positive impact on users’ satisfaction with GePG system, whilst service quality had a significant negative impact. In contrast, system quality did not have an effect.Conclusion: The study shows that trust in system and perceived usefulness are important factors in the updated Delone and Mclean IS success model in evaluating user satisfaction with revenue collection systems. The findings from the open-ended questions and implications of the findings are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.