Leveraging AI and Machine Learning to Develop and Evaluate a Contextualized User-Friendly Cough Audio Classifier for Detecting Respiratory Diseases: Protocol for a Diagnostic Study in Rural Tanzania.

BACKGROUND: Respiratory diseases, including active tuberculosis (TB), asthma, and chronic obstructive pulmonary disease (COPD), constitute substantial global health challenges, necessitating timely and accurate diagnosis for effective treatment and management. OBJECTIVE: This research seeks to develop and evaluate a noninvasive user-friendly artificial intelligence (AI)-powered cough audio classifier for detecting these respiratory conditions in rural Tanzania. METHODS: This is a nonexperimental cross-sectional research with the primary objective of collection and analysis of cough sounds from patients with active TB, asthma, and COPD in outpatient clinics to generate and evaluate a noninvasive cough audio classifier. Specialized cough sound recording devices, designed to be nonintrusive and user-friendly, will facilitate the collection of diverse cough sound samples from patients attending outpatient clinics in 20 health care facilities in the Shinyanga region. The collected cough sound data will undergo rigorous analysis, using advanced AI signal processing and machine learning techniques. By comparing acoustic features and patterns associated with TB, asthma, and COPD, a robust algorithm capable of automated disease discrimination will be generated facilitating the development of a smartphone-based cough sound classifier. The classifier will be evaluated against the calculated reference standards including clinical assessments, sputum smear, GeneXpert, chest x-ray, culture and sensitivity, spirometry and peak expiratory flow, and sensitivity and predictive values. RESULTS: This research represents a vital step toward enhancing the diagnostic capabilities available in outpatient clinics, with the potential to revolutionize the field of respiratory disease diagnosis. Findings from the 4 phases of the study will be presented as descriptions supported by relevant images, tables, and figures. The anticipated outcome of this research is the creation of a reliable, noninvasive diagnostic cough classifier that empowers health care professionals and patients themselves to identify and differentiate these respiratory diseases based on cough sound patterns. CONCLUSIONS: Cough sound classifiers use advanced technology for early detection and management of respiratory conditions, offering a less invasive and more efficient alternative to traditional diagnostics. This technology promises to ease public health burdens, improve patient outcomes, and enhance health care access in under-resourced areas, potentially transforming respiratory disease management globally. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/54388.

Improving nursing education curriculum as a tool for strengthening the nurse-client relationships in maternal and child healthcare: Insights from a human-centered design study in rural Tanzania.

Background: There are growing evidence of poor nurse-client relationships in maternal and child health (MCH). The nursing curriculum forms an important entry point for strengthening such relationships, consequently improving client satisfaction with nurses' competencies, confidence in the formal healthcare system, healthcare-seeking practices, continuity with care, and MCH outcomes. Objective: MCH nurses and clients were invited to design an intervention package (prototype) to improve nurse-client relationships using a human-centered design (HCD) approach. Methods: A multi-step HCD approach was employed to first examine the contributors of poor nurse-client relationships using nine focus group discussions with nurses and clients and 12 key informant interviews with MCH administrators. Then, three meetings were held with 10 nurses, 10 clients, and 10 administrators to co-develop an intervention package to address the identified contributors. The solutions were validated by collecting qualitative information through six focus groups with nurses and MCH clients who were not involved in the initial HCD stages. Finally, refinement and adaptation meetings were held with 15 nurses, 15 clients, and 10 administrators. The data were managed with NVivo 12 software and analyzed thematically. Results: Nursing curriculum challenges contributing to poor nurse-client relationships in MCH care included inadequate content on nurse-client relationships specifically topics of customer care, communication skills, and patient-centered care; an inadequate practice on communication skills within nursing schools; and the absence of specific trainers on interpersonal relationships. Consequently, improving the nursing curriculum was one of the interventions proposed during the co-design and rated by participants as highly acceptable during validation and refinement meetings. Suggested improvements to the curriculum included increasing hours and credits on communication skills and patient-centered care, including customer care courses in the curriculum and creating a friendly learning environment for clinical practice on strengthening interpersonal relationships. Conclusion: Improving the nursing curriculum was considered by nurses and clients as one of the acceptable interventions to strengthen nurse-client relations in MCH care in rural Tanzania. Nursing education policy and curriculum developers need to ensure the curriculum facilitates the development of much-needed interpersonal skills among nursing graduates for them to have positive therapeutic interactions with their clients.

Provider experiences with the large-scale 'Helping Babies Breathe' training programme in Tanzania.

OBJECTIVES: Worldwide, there has been renewed emphasis on reducing neonatal mortality in low-resource countries. The Helping Babies Breathe (HBB) programme has been shown to reduce newborn deaths. The aim of this study is to present provider-level perceptions and experiences of the HBB programme implemented at-scale in Tanzania and identify key lessons learned for scalability in similar and other settings. METHODS: Focus group discussions with HBB-trained providers were conducted using a prospective longitudinal study design between October 2013 and May 2015. A semi-structured discussion guide was used to facilitate the focus groups which were held 4-6 weeks and 4-6 months post-HBB training. Data were managed using NVivo software and analysed thematically. RESULTS: A total of 222 focus group discussions were conducted in 252 trained facilities and involved 599 providers across 15 regions of Tanzania. Birth attendants reported that the training programme helped increase knowledge, skills and confidence, and that the provided equipment simplified resuscitation. Supportive supervision and regular follow-up visits were considered critical for skills retention. On the other hand, the brief 1-day training in Tanzania, small financal incentives, intra-facility rotations of trained attendants, staff shortages, limited rescucitation spaces and mastery of the bag-and-mask were considered challenges to the HBB programme in Tanzania. DISCUSSION: The HBB programme was largely very well received during its first at-scale implementation in Tanzania. Addressing the main challenges cited by participants, particularly the training duration, may increase provider satisfaction with the HBB training programme.