Experiences of community health workers on adopting mHealth in rural Malawi: A qualitative study.

Background: The use of mobile health technology (mHealth) by community health workers (CHWs) can strengthen community-based service delivery and improve access to and quality of healthcare. Objective: This qualitative study sought to explore experiences and identify factors influencing the use of an integrated smartphone-based mHealth called YendaNafe by CHWs in rural Malawi. Methods: Using pre-tested interview guides, between August and October 2022, we conducted eight focus group discussions with CHWs (n = 69), four in-depth interviews with CHW supervisors, and eight key informant interviews in Neno District, Malawi. We audio-recorded and transcribed the interviews verbatim and organized them for analysis in Dedoose V9.0.62. We used an inductive analysis technique to analyze the data. We further applied the six domains of the socio-technical system (STS) framework to map factors influencing the use of YendaNafe. Results: User experiences and facilitators and barriers were the two main themes that emerged. mHealth was reported to improve the task efficiency, competence, trust, and perceived professionalism of CHWs. CHWs less frequently referred to cultural factors influencing app uptake. However, for other social systems, they identified relationships and trust with stakeholders, availability of training and programmatic support, and performance monitoring and feedback as influencing the use of YendaNafe. From the STS technical domain, the availability and adequacy of hardware such as phones, mobile connectivity, and usability influenced the use of YendaNafe. Conclusions: Despite the initial discomfort, CHWs found mHealth helpful in supporting their service delivery tasks. Identifying and addressing social and technical factors during mHealth implementation may help improve end users' attitudes and uptake.

Analysing 3429 digital supervisory interactions between Community Health Workers in Uganda and Kenya: the development, testing and validation of an open access predictive machine learning web app.

BACKGROUND: Despite the growth in mobile technologies (mHealth) to support Community Health Worker (CHW) supervision, the nature of mHealth-facilitated supervision remains underexplored. One strategy to support supervision at scale could be artificial intelligence (AI) modalities, including machine learning. We developed an open access, machine learning web application (CHWsupervisor) to predictively code instant messages exchanged between CHWs based on supervisory interaction codes. We document the development and validation of the web app and report its predictive accuracy. METHODS: CHWsupervisor was developed using 2187 instant messages exchanged between CHWs and their supervisors in Uganda. The app was then validated on 1242 instant messages from a separate digital CHW supervisory network in Kenya. All messages from the training and validation data sets were manually coded by two independent human coders. The predictive performance of CHWsupervisor was determined by comparing the primary supervisory codes assigned by the web app, against those assigned by the human coders and calculating observed percentage agreement and Cohen's kappa coefficients. RESULTS: Human inter-coder reliability for the primary supervisory category of messages across the training and validation datasets was 'substantial' to 'almost perfect', as suggested by observed percentage agreements of 88-95% and Cohen's kappa values of 0.7-0.91. In comparison to the human coders, the predictive accuracy of the CHWsupervisor web app was 'moderate', suggested by observed percentage agreements of 73-78% and Cohen's kappa values of 0.51-0.56. CONCLUSIONS: Augmenting human coding is challenging because of the complexity of supervisory exchanges, which often require nuanced interpretation. A realistic understanding of the potential of machine learning approaches should be kept in mind by practitioners, as although they hold promise, supportive supervision still requires a level of human expertise. Scaling-up digital CHW supervision may therefore prove challenging. TRIAL REGISTRATION: This was not a clinical trial and was therefore not registered as such.

Enhancing the Supervision of Community Health Workers With WhatsApp Mobile Messaging: Qualitative Findings From 2 Low-Resource Settings in Kenya.

An estimated half of all mobile phone users in Kenya use WhatsApp, an instant messaging platform that provides users an affordable way to send and receive text messages, photos, and other media at the one-to-one, one-to-many, many-to-one, or many-to-many levels. A mobile learning intervention aimed at strengthening supervisory support for community health workers (CHWs) in Kibera and Makueni, Kenya, created a WhatsApp group for CHWs and their supervisors to support supervision, professional development, and team building. We analyzed 6 months of WhatsApp chat logs (from August 19, 2014, to March 1, 2015) and conducted interviews with CHWs and their supervisors to understand how they used this instant messaging tool. During the study period, 1,830 posts were made by 41participants. Photos were a key component of the communication among CHWs and their supervisors: 430 (23.4%) of all posts contained photos or other media. Of the remaining 1,400 text-based posts, 87.6% (n = 1,227) related to at least 1 of 3 defined supervision objectives: (1) quality assurance, (2) communication and information, or (3) supportive environment. This supervision took place in the context of posts about the roll out of the new mobile learning intervention and the delivery of routine health care services, as well as team-building efforts and community development. Our preliminary investigation demonstrates that with minimal training, CHWs and their supervisors tailored the multi-way communication features of this mobile instant messaging technology to enact virtual one-to-one, group, and peer-to-peer forms of supervision and support, and they switched channels of communication depending on the supervisory objectives. We encourage additional research on how health workers incorporate mobile technologies into their practices to develop and implement effective supervisory systems that will safeguard patient privacy, strengthen the formal health system, and create innovative forms of community-based, digitally supported professional development for CHWs.

What do community health workers have to say about their work, and how can this inform improved programme design? A case study with CHWs within Kenya.

BACKGROUND: Community health workers (CHWs) are used increasingly in the world to address shortages of health workers and the lack of a pervasive national health system. However, while their role is often described at a policy level, it is not clear how these ideals are instantiated in practice, how best to support this work, or how the work is interpreted by local actors. CHWs are often spoken about or spoken for, but there is little evidence of CHWs' own characterisation of their practice, which raises questions for global health advocates regarding power and participation in CHW programmes. This paper addresses this issue. DESIGN: A case study approach was undertaken in a series of four steps. Firstly, groups of CHWs from two communities met and reported what their daily work consisted of. Secondly, individual CHWs were interviewed so that they could provide fuller, more detailed accounts of their work and experiences; in addition, community health extension workers and community health committee members were interviewed, to provide alternative perspectives. Thirdly, notes and observations were taken in community meetings and monthly meetings. The data were then analysed thematically, creating an account of how CHWs describe their own work, and the tensions and challenges that they face. RESULTS: The thematic analysis of the interview data explored the structure of CHW's work, in terms of the frequency and range of visits, activities undertaken during visits (monitoring, referral, etc.) and the wider context of their work (links to the community and health service, limited training, coordination and mutual support through action and discussion days, etc.), and provided an opportunity for CHWs to explain their motivations, concerns and how they understood their role. The importance of these findings as a contribution to the field is evidenced by the depth and detail of their descriptive power. One important aspect of this is that CHWs' accounts of both successes and challenges involved material elements: leaky tins and dishracks evidenced successful health interventions, whilst bicycles, empty first aid kits and recruiting stretcher bearers evidenced the difficulties of resourcing and geography they are required to overcome. CONCLUSION: The way that these CHWs described their work was as healthcare generalists, working to serve their community and to integrate it with the official health system. Their work involves referrals, monitoring, reporting and educational interactions. Whilst they face problems with resources and training, their accounts show that they respond to this in creative ways, working within established systems of community power and formal authority to achieve their goals, rather than falling into a 'deficit' position that requires remedial external intervention. Their work is widely appreciated, although some households do resist their interventions, and figures of authority sometimes question their manner and expertise. The material challenges that they face have both practical and community aspects, since coping with scarcity brings community members together. The implication of this is that programmes co-designed with CHWs will be easier to implement because of their relevance to their practices and experiences, whereas those that assume a deficit model or seek to use CHWs as an instrument to implement external priorities are likely to disrupt their work.