Background: Despite the widely anticipated benefits of eHealth technologies in enhancing health care service delivery, the sustainable usage of eHealth in transitional countries remains low. There is limited evidence supporting the low sustainable adoption of eHealth in low- and middle-income countries. Objective: The aim of this study was to explore the facilitators and barriers to the sustainable use of eHealth solutions in low- and middle-income nations. Methods: A qualitative descriptive exploratory study was conducted in 4 African nations from September to December 2021. A semistructured interview guide was used to collect the data. Data were audio-recorded and transcribed from the local to the English language verbatim, and the audio data were transcribed. On the basis of the information gathered, we assigned codes to the data, searched for conceptual patterns, and created emerging themes. Data were analyzed thematically using OpenCode software. Results: A total of 49 key informant interviews (10 from Tunisia, 15 from Ethiopia, 13 from Ghana, and 11 from Malawi) were conducted. About 40.8% (20/49) of the study participants were between the ages of 26 and 35 years; 73.5% (36/49) of them were male participants; and 71.4% (35/49) of them had a master’s degree or higher in their educational background. Additionally, the study participants' work experience ranged from 2 to 35 years. Based on the data we gathered, we identified 5 themes: organizational, technology and technological infrastructure, human factors, economy or funding, and policy and regulations. Conclusions: This study explores potential facilitators and barriers to long-term eHealth solution implementation. Addressing barriers early in the implementation process can aid in the development of eHealth solutions that will better fulfill the demands of end users. Therefore, focusing on potential challenges would enhance the sustainability of eHealth solutions in low- and middle-income countries.

Introduction: Non-attendance and delay for vaccination schedules remains a big challenge to healthcare workers. Among the frequently mentioned reasons for missed vaccination in children is the lack of communication between child caretakers and health workers. This necessitates developing an appropriate and uninterrupted vaccine delivery strategy with more focus on demand side interventions like forgetfulness.Objectives: This paper aimed to develop and test an automated mobile text message reminder system in the local context.Methods: Before development of the system, interview and document reviews were used for requirement gathering. This system is developed using iterative development process through phases of requirement analysis, design, development, testing and refinement. Front end application was developed using Java technologies while back end applications were developed with Oracle database. Finally, pilot testing was done on 30 participants before actual implementation.Results: The automated system has been developed based on requirements. The text message reminder system has two components: 1. Web based application for client registration and automatic reminder scheduling; 2.SMS application for automatic SMS text messaging. In the final testing, all the messages (100%) were delivered to the piloted mothers. Message speeds for each individual client ranged on average from 5 second to 30 seconds.Conclusion: Text message reminder system has been developed for routine childhood immunization program in Ethiopian context. Text message interventions should be carefully developed, tested and refined before implementation to ensure they are written in the most appropriate way for their target population.

Background: Although Ethiopia has made remarkable progress in the uptake of the District Health Information System version 2 (DHIS2) for national aggregate data reporting, there has been no comprehensive assessment of the maturity level of the system. Objective: This study aims to assess the maturity level of DHIS2 implementation in Ethiopia and propose a road map that could guide the progress toward a higher level of maturity. We also aim to assess the current maturity status, implementation gaps, and future directions of DHIS2 implementation in Ethiopia. The assessment focused on digital health system governance, skilled human resources, information and communication technology (ICT) infrastructure, interoperability, and data quality and use. Methods: A collaborative assessment was conducted with the engagement of key stakeholders through consultative workshops using the Stages of Continuous Improvement tool to measure maturity levels in 5 core domains, 13 components, and 39 subcomponents. A 5-point scale (1=emerging, 2=repeatable, 3=defined, 4=managed, and 5=optimized) was used to measure the DHIS2 implementation maturity level. Results: The national DHIS2 implementation’s maturity level is currently at the defined stage (score=2.81) and planned to move to the manageable stage (score=4.09) by 2025. The domain-wise maturity score indicated that except for ICT infrastructure, which is at the repeatable stage (score=2.14), the remaining 4 domains are at the defined stage (score=3). The development of a standardized and basic DHIS2 process at the national level, the development of a 10-year strategic plan to guide the implementation of digital health systems including DHIS2, and the presence of the required competencies at the facility level to accomplish specific DHIS2-related tasks are the major strength of the Ministry of Health of Ethiopia so far. The lack of workforce competency guidelines to support the implementation of DHIS2; the unavailability of core competencies (knowledge, skills, and abilities) required to accomplish DHIS2 tasks at all levels of the health system; and ICT infrastructures such as communication network and internet connectivity at the district, zonal, and regional levels are the major hindrances to effective DHIS2 implementation in the country. Conclusions: On the basis of the Stages of Continuous Improvement maturity model toolkit, the implementation status of DHIS2 in Ethiopia is at the defined stage, with the ICT infrastructure domain being at the lowest stage as compared to the other 4 domains. By 2025, the maturity status is planned to move from the defined stage to the managed stage by improving the identified gaps. Various action points are suggested to address the identified gaps and reach the stated maturity level. The responsible body, necessary resources, and methods of verification required to reach the specified maturity level are also listed.

We propose a new approach for modelling the process of RNA folding as a graph transformation\ud guided by the global value of free energy. Since the folding process evolves towards a configuration\ud in which the free energy is minimal, the global behaviour resembles the one of a self-adaptive system.\ud Each RNA configuration is a graph and the evolution of configurations is constrained by precise rules\ud that can be described by a graph grammar

Topological data analysis has been recently used to extract meaningful information frombiomolecules. Here we introduce the application of persistent homology, a topological data analysis tool, for computing persistent features (loops) of the RNA folding space. The scaffold of the RNA folding space is a complex graph from which the global features are extracted by completing the graph to a simplicial complex via the notion of clique and Vietoris-Rips complexes. The resulting simplicial complexes are characterised in terms of topological invariants, such as the number of holes in any dimension, i.e. Betti numbers. Our approach discovers persistent structural features, which are the set of smallest components to which the RNA folding space can be reduced. Thanks to this discovery, which in terms of data mining can be considered as a space dimension reduction, it is possible to extract a new insight that is crucial for understanding the mechanism of the RNA folding towards the optimal secondary structure. This structure is composed by the components discovered during the reduction step of the RNA folding space and is characterized by minimum free energy.

This paper introduces a model that automates the diagnosis of a patient’s condition, reducing reliance on highly trained professionals, particularly in resource-constrained settings. To ensure data consistency, the dataset was preprocessed for uniformity in size, format, and color channels. Image quality was further enhanced using histogram equalization to improve the dynamic range. Lung regions were isolated using segmentation techniques, which also eliminated extraneous areas from the images. A modified segmentation-based cropping technique was employed to define an optimal cropping rectangle. Feature extraction was performed using persistent homology, deep learning, and hybrid methodologies. Persistent homology captured topological features across multiple scales, while the deep learning model leveraged convolutional transition equivariance, input-adaptive weighting, and the global receptive field provided by Vision Transformers. By integrating features from both methods, the classification model effectively predicted severity levels (mild, moderate, severe). The segmentation-based cropping method showed a modest improvement, achieving 80% accuracy, while stand-alone persistent homology features reached 66% accuracy. Notably, the hybrid model outperformed existing approaches, including SVM, ResNet50, and VGG16, achieving an accuracy of 82%.