Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. According to the July 24, 2026 PLOS Global Public Health scoping review by Mhlanga et al., digital health (especially mHealth) has been used by non-physician health workers to support prevention, screening, treatment delivery, and supervision for non-communicable diseases (NCDs) in Africa (PLOS Global Public Health). This post explains the PLOS findings through the lens of AI-enabled qualitative research and shows practical steps program teams and researchers can take to turn sparse published evidence into actionable program design.
Key Takeaways
The July 24, 2026 PLOS Global Public Health scoping review found that “digital health, particularly mHealth, supports NPHWs in task-sharing for NCD prevention and management in Africa, ” while also noting constraints on scale-up (PLOS Global Public Health).
- The authors screened 4, 857 citations and included 15 studies from eight African countries as of the search cutoff on August 3, 2025, according to Mhlanga et al. (2026).
- mHealth was the single most common technology used in the included studies, appearing in 46.7% (7/15) of studies, according to Mhlanga et al. (2026).
- South Africa contributed the largest share of included studies, 26.7% (4/15), as reported in Mhlanga et al. (2026).
- The review reported both positive patient outcomes in some mental health treatment studies and neutral effects for several prevention outcomes, per Mhlanga et al. (2026).
- Chibanda et al. (as cited in Mhlanga et al., 2026) described using "up to six SMSs and phone calls" to support psychosocial interventions.
What Happened: the PLOS scoping review in brief
Answer: The scoping review mapped how digital health is used by non-physician health workers (NPHWs) for task-sharing in NCD care in Africa and identified gaps for scale-up.
According to Mhlanga et al. (2026) in PLOS Global Public Health, the authors followed a Joanna Briggs Institute scoping review method and searched PubMed, Scopus and Google Scholar between April 7, 2025 and August 3, 2025.
According to Mhlanga et al. (2026), the database search returned 4, 857 citations, after duplicates and screening 15 studies from eight countries met inclusion criteria, with the studies published between 2014 and August 2025.
According to Mhlanga et al. (2026), community health workers were the most common NPHW users (46.7%; 7/15) and mHealth (SMS, smartphone apps, decision-support tools) was the dominant technology across included studies.
Findings Snapshot
| Date / Search window | Metric | Value | Implication |
|---|---|---|---|
| Search completed Aug 3, 2025 | Citations identified | 4, 857 | Large initial yield, but small final evidence base (15 studies) for Africa |
| Published Jul 24, 2026 | Studies included | 15 studies from 8 countries | Geographically limited evidence; 26.7% (4/15) from South Africa |
| Study designs (2014–Aug 2025) | Primary technology | mHealth in 46.7% (7/15) of studies | Smartphone apps and SMS dominate; limited use of sensors or AI |
| Effectiveness (reported in 4 studies) | Patient outcomes | 2 positive for mental health, 2 neutral for prevention | Treatment delivery shows promise; prevention results mixed |
| Implementation barriers (reported across studies) | Common constraints | Low digital literacy, poor internet, inadequate electricity | Scale-up depends on training, infrastructure and governance |
Implications for researchers and program leads
Answer: Researchers and program leads should treat the PLOS findings as a mapping of promise plus critical context requirements, not as turnkey evidence for scale.
According to Mhlanga et al. (2026) in PLOS Global Public Health, mHealth was used for four main functions (prevention, screening, treatment delivery and supervision) so program design should explicitly specify which function is primary.
According to Mhlanga et al. (2026), where effectiveness was evaluated (4 studies), mental health task-sharing using mHealth showed positive patient symptom changes in 2 studies, while prevention trials (e.g., Lifestyle Africa) reported neutral biomarker changes, implying different evidence strengths by use case.
According to Mhlanga et al. (2026), common implementation barriers included low digital literacy, intermittent electricity and poor connectivity, therefore researchers should embed feasibility, training and infrastructure assessment into early-stage pilots.
How Evidano Helps: operationalizing qualitative evidence for mHealth task-sharing
Problem: Scattered qualitative findings slow program design
Answer: Dispersed study reports and qualitative quotes make it slow to synthesize what frontline workers actually do and need, according to Mhlanga et al. (2026).
According to Mhlanga et al. (2026), many studies report context-specific barriers such as low digital literacy and connectivity, so rapid cross-study synthesis is essential to design context-appropriate mHealth tools.
Solution: Thematic and cross-segment synthesis with Evidano
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Evidano can ingest published articles, field interview transcripts, and program reports to extract themes like "digital literacy" or "charging barriers" and quantify how often those themes appear across contexts.
Evidano features such as automated thematic coding, frequency and cross-segment analysis, and AI chat over documents speed up triangulation of findings from multiple small studies like those in the PLOS review; see features.
For primary data collection, Evidano’s transcription capabilities reduce time-to-insight for audio recorded training sessions or CHW interviews; see speech-to-text.
Practical use case
Answer: Use Evidano to combine the PLOS scoping review texts, local CHW interview transcripts, and app usage logs to produce an evidence-informed requirements brief.
Researchers can upload the 15 included study PDFs, tag passages that mention training length (e.g., two to nine days reported in Mhlanga et al., 2026), and produce a synthesis that shows which training formats map to which outcomes in similar settings.
FAQ: mHealth task-sharing Africa
What evidence supports mHealth for task-sharing in Africa?
Answer: The primary evidence base mapped by Mhlanga et al. (2026) comprises 15 studies from eight African countries aggregated in a PLOS scoping review (PLOS Global Public Health).
According to Mhlanga et al. (2026), the included studies show mHealth is frequently used for screening, treatment delivery and supervision, but only four studies reported patient outcomes, with mixed results by use case.
Which non-physician health workers use mHealth most?
Answer: Community health workers (CHWs) were the most commonly reported users, at 46.7% (7/15) of the included studies, according to Mhlanga et al. (2026).
According to Mhlanga et al. (2026), other users included lay counsellors, nurses, pharmacists and psychiatric technicians, reflecting diverse task-sharing cadres.
What implementation barriers should programs expect?
Answer: Expect low digital literacy, poor internet connectivity, and unreliable electricity to be core constraints, as reported across the included studies in Mhlanga et al. (2026).
According to Mhlanga et al. (2026), these barriers were repeatedly cited and are likely to shape which mHealth functions are feasible in a given setting.
How can AI-enabled qualitative research improve mHealth program design?
Answer: AI-enabled qualitative tools accelerate synthesis of small, context-specific studies so designers can prioritize features linked to real-world constraints, according to the analytic approach illustrated by the PLOS review.
According to Mhlanga et al. (2026), context matters: combining thematic coding across trial reports and CHW interviews helps reveal whether decision-support, SMS reminders, or video training best match user capacity and infrastructure.
Conclusion & Next Steps
The PLOS Global Public Health scoping review (published July 24, 2026) shows that mHealth is the dominant digital health approach used to support task-sharing for NCDs in Africa, but the evidence base is small (15 studies) and implementation barriers persist (Mhlanga et al., 2026).
Program teams and researchers should combine the review’s findings with local qualitative data to design feasible tools that match CHW skills and infrastructure conditions, as recommended by Mhlanga et al. (2026).
If you need to synthesize published studies, transcripts, and open-ended survey responses into prioritized, context-specific requirements, Evidano can accelerate that work and produce reproducible thematic and cross-segment analyses; Try Evidano for free.