Evidano is an AI-powered qualitative data analysis platform that accelerates transcription, translation, secure coding, and cross-segment theme comparison. Fast, research-ready take: a July 14, 2026 PLOS Neglected Tropical Diseases study of peri-urban Arusha and rural Monduli (data collected May-July 2024, n=57 across 5 FGDs and 13 interviews) found communities frame disease risk by seasonality rather than abstract climate models, and that risk messaging is fragmented and unevenly distributed. Read the original paper at PLOS Neglected Tropical Diseases. This post interprets published qualitative research for methodological insights only (non-diagnostic, research-focused). For hands-on execution, see Evidano.
Key Takeaways
Evidano is an AI-powered qualitative data analysis platform that accelerates transcription, translation, secure coding, and cross-segment theme comparison.
The PLOS NTD study (July 14, 2026; data May-July 2024; n=57) shows communities explain NTD patterns by dry versus rainy seasons, and current messaging is fragmented and uneven.
- A July 14, 2026 PLOS NTD study (data May-July 2024, n=57) found communities emphasize seasonal experience (dry vs rainy) over abstract 'climate change' when explaining disease patterns.
- Communities prefer trusted interpersonal networks, radio, and school outreach, but relying on children to relay messages creates equity and fidelity problems.
- Practitioners rely on national MDA and school-based education but face resource, training, and data disaggregation gaps; the study recommends strengthened surveillance, WaSH, trusted messengers, and practitioner training.
- Evidano workflows can reduce transcription overhead, preserve translation fidelity, and speed coding, synthesis, and cross-segment comparison for policy-ready outputs.
Study snapshot: numbers & timeline
| Item | Value | Source / Note |
|---|---|---|
| Publication date | July 14, 2026 | PLOS Negl Trop Dis |
| Data collection | May-July 2024 | In-person FGDs & interviews (Swahili/English) |
| Sample | n = 57 (5 FGDs, 13 interviews) | 44 community FGD participants + 13 practitioners |
| Primary locations | Arusha (peri-urban), Monduli (rural) | Agro-pastoral contexts; urban/rural comparison |
| Key thematic finding | Seasonality frames risk; mismatch between community needs and system messaging | Recommendations: strengthen surveillance, WaSH, trusted messengers |
What happened: methods & core findings
The study used an environmental scan, five focus groups, and 13 semi-structured interviews with doctors, nurses, veterinarians, health administrators, and community members to compare practitioner risk communication with community preferences.
The authors ran an environmental scan, five focus groups, and 13 semi-structured interviews with doctors, nurses, veterinarians and health administrators to compare practitioner risk communication with community preferences.
- Communities emphasize seasonal experience (dry vs rainy) over abstract 'climate change' when explaining disease patterns.
- Preferred channels: trusted interpersonal networks (village leaders, churches), radio, and school outreach, though relying on children to relay messages creates equity and fidelity problems.
- Practitioners rely on national MDA and school-based education but face resource, training, and data disaggregation gaps.
- Five tactical recommendations emerged: boost surveillance/data use, counter vaccine hesitancy, invest in practitioner training and WaSH, reduce the communicative burden on children, and integrate traditional knowledge and leaders.
So what for researchers and research teams
For qualitative researchers
For qualitative researchers, the study is a model of comparative, place-based qualitative work using a small-n, deep-context approach and iterative coding to saturation.
Key analytic tasks were translation checking, dual coding, and a mixed inductive/deductive codebook tied to WHO and national strategy documents.
If you run similar projects, prioritize verified translations (team double-checks) and transparent codebook workflows to preserve interpretive validity across languages and positionalities.
For UX/health teams and policy analysts
For UX, health teams, and policy analysts, the evidence points to tactical wins: align messaging to seasonal risk windows, use trusted community messengers, and create diagrammatic, low-literacy materials.
Design decision: prefer timely, targeted communications (for example, pre-rainy season schistosomiasis alerts) over generic, infrequent campaigns.
For surveillance & data teams
For surveillance and data teams, disaggregated, routine surveillance by place, livelihood, and age is essential to detect emergent NTD patterns as climates shift.
Pair qualitative community intelligence with downscaled climate projections to prioritize wards for WaSH and MDA.
Do more, faster with Evidano (mapped to this use case)
Problem: Multilingual audio + limited transcription capacity
Evidano handles multilingual audio with automated transcription, custom dictionaries, speaker labels, and PII redaction to cut manual overhead and speed QA.
Evidano solution: automated transcription with custom dictionaries (Swahili/Maasai terms), speaker labels, and PII redaction, cuts manual overhead and speeds QA.
Problem: Translation & semantic drift
Evidano preserves translation fidelity with integrated translation workflows and side-by-side originals for transcript checking to maintain local terms and cultural meaning for coding.
Evidano solution: integrated translation workflow with transcript checking and side-by-side originals to preserve local terms and cultural meaning for coding.
Problem: Inconsistent coding and slow synthesis
Evidano imports codebooks, runs AI-assisted coding across transcripts, and generates thematic, frequency, and cross-segment analyses to speed synthesis.
Evidano solution: import your codebook, run AI-assisted coding across transcripts, then generate thematic, frequency, and cross-segment analyses (for example, Arusha vs Monduli). Co-occurrence networks and hierarchical code to subcode visualizations make patterns scannable for stakeholders.
Problem: Stakeholder reporting and trust building
Evidano exports stakeholder briefs, clickable quotes, and low-literacy visuals while providing secure data storage with end-to-end encryption and a policy that user data is never used to train third-party models.
Evidano solution: export stakeholder briefs, clickable quotes, and low-literacy visuals. Use secure data storage (end-to-end encryption) and Evidano’s policy: user data is never used to train third-party models.
Problem: Need for follow-up engagement
Evidano supports consented, autonomous follow-ups through AI avatar interviewers to capture seasonal changes in knowledge and attitudes at scale.
Evidano solution: AI avatar interviewers can run autonomous, ethical follow-ups (consented) to capture seasonal changes in knowledge and attitudes at scale.
Two-week pilot workflow to reproduce these insights
This two-week plan converts raw field audio into policy-ready recommendations using the study's methods as a template.
- Day 1-3: Upload audio and documents to Evidano; set custom dictionary for local terms (Maasai names, local disease terms).
- Day 3-5: Auto-transcribe and auto-translate; run transcript QA with bilingual team members; redact PII.
- Day 6-8: Import initial codebook (deductive codes: seasonality, channels, vaccine hesitancy, WaSH) and run AI-assisted coding across segments (Arusha vs Monduli).
- Day 9-10: Generate cross-segment frequency tables, co-occurrence maps, and sample quotes exports for stakeholder validation.
- Day 11-14: Package a 2-page policy brief and a 10-slide visual deck; schedule a village meeting and a practitioner workshop using the visuals to test message resonance.
Wrapping up: next moves
This PLOS study (July 14, 2026) is a practical reminder that communities think in seasons, not abstract climate models, and that risk communication must be timely, trusted, and adapted to literacy and technology constraints.
- Start small: pilot targeted, seasonal messaging informed by disaggregated surveillance and qualitative insights.
- Use tools that preserve semantics and security: transcription, translation, and codebook workflows with encrypted storage.
- Try Evidano for free to move from field audio to thematic and cross-segment analysis quickly and securely.
FAQ: NTD risk communication
How was the data collected and where did the study take place?
The study collected data through an environmental scan, five focus group discussions, and 13 semi-structured interviews in Arusha (peri-urban) and Monduli (rural) during May-July 2024.
The sample included 44 community FGD participants and 13 practitioners for a total n = 57.
What do communities say about disease risk?
Communities attribute disease patterns to seasonal experience, distinguishing dry versus rainy periods rather than invoking abstract climate change.
This seasonal framing shapes how communities perceive risk windows and appropriate preventive actions.
Which communication channels do communities prefer?
Communities prefer trusted interpersonal networks, radio, and school outreach as their primary communication channels.
The study notes that relying on children to relay messages creates equity and fidelity problems.
What practical recommendations came from the study?
The study recommends strengthening surveillance and data use, investing in WaSH and practitioner training, countering vaccine hesitancy, reducing the communication burden on children, and integrating traditional leaders.
These recommendations aim to align messaging with seasonal risk windows and trusted local messengers.