Evidano home
Commentary on News

From Field Interviews to Insight: AI Thematic Analysis

Evidano8 min read

Healthcare researchers often need to combine survey results, diagnostic measurements, and interview transcripts before they can explain what is happening in a community. The challenge is especially serious in remote settings, where a small number of interviews may reveal barriers that routine surveillance does not capture. The 2026 PLOS study on malaria in Indigenous communities in the Peruvian Amazon offers a useful example of how qualitative evidence can explain quantitative findings. This article shows how AI thematic analysis healthcare teams can use responsibly to organize transcripts, compare stakeholder perspectives, and connect themes to epidemiological results. The source study used manual thematic analysis, not artificial intelligence, so the discussion below distinguishes the researchers’ findings from the potential role of AI-enabled qualitative research.

Key Takeaways

According to the PLOS Neglected Tropical Diseases study published on November 19, 2026, malaria remained a substantial burden in four remote Indigenous communities in Peru during the COVID-19 pandemic, while interviews showed that disruptions to diagnosis, treatment, surveillance, and follow-up shaped access to care.

AI thematic analysis healthcare teams can use should accelerate coding and comparison without replacing contextual interpretation, community engagement, or clinical and ethics review.

  • The 2026 mixed-methods study included 514 participants and found PCR-confirmed malaria prevalence of 17.6% in 2021 and 26.09% in 2022, although the authors cautioned that the figures were not directly comparable because recruitment strategies and participating communities differed.
  • The 2026 study included 14 semi-structured interviews with community members, community health workers, and health personnel, identifying three major themes and eight subthemes about malaria care during COVID-19.
  • Participants in the 2026 study reported medication shortages, reduced surveillance, delayed diagnosis and treatment, and reliance on herbal medicine when formal care was difficult to access.
  • The 2026 study integrated quantitative and qualitative evidence through the Pillar Integration Process, showing how interview themes can explain patterns that prevalence data alone cannot describe.
  • AI-enabled qualitative research can help healthcare teams process transcripts, compare stakeholder groups, and identify recurring barriers, but the 2026 study’s limitations show why human review remains essential.

What the Peru Malaria Study Found

The Peru malaria study found that pandemic-related health service disruptions may have intensified existing barriers to malaria control in remote Indigenous communities.

According to the 2026 study, researchers conducted a convergent parallel mixed-methods study in 2021 and 2022 across Alianza Progreso, Caterpiza, Chapiza, and Nueva Esperanza in the Río Santiago district of Amazonas, Peru. The quantitative component used microscopy and PCR-based malaria testing, while the qualitative component used semi-structured interviews with inhabitants, community health workers, and local health personnel.

The 2026 study reported PCR-based malaria prevalence of 17.65% among participants surveyed in 2021 and 26.09% among participants surveyed in 2022. The authors explicitly stated that these estimates should not be interpreted as evidence of a temporal increase because the communities and recruitment methods differed between study years.

The 2026 study found particularly high observed Plasmodium falciparum prevalence in Alianza Progreso, at 24.19% in 2021 and 16.16% in 2022. The authors also reported that chills were associated with PCR-confirmed malaria, while the relationship between self-reported previous malaria and current infection varied by study year.

The qualitative findings added operational detail to the epidemiological results. One participant told the researchers, "There was a community health promoter that was doing rapid tests for malaria; he used to go to the health post with the information, and there they used to tell him that there was no treatment". Another participant said, "Most people in the jungle are cured with herbal medicine".

The 2026 study reported that interviews were conducted in Spanish, transcribed verbatim, translated into English, and analyzed thematically using the six-step framework associated with Braun and Clarke. Three researchers reviewed and refined codes, themes, and subthemes through iterative discussion.

Findings Snapshot: Dates, Measures, and Meaning

Date or study periodMeasureValueWhy it matters for qualitative research
2021PCR-confirmed malaria prevalence17.65%The quantitative result establishes disease burden that interview themes can help explain.
2022PCR-confirmed malaria prevalence26.09%The result cannot be treated as a year-over-year increase because the 2026 authors identified community and recruitment differences.
2021 and 2022Study participants514A large survey sample was paired with a smaller qualitative sample to connect population-level measurement with lived experience.
February 2022Semi-structured interviews14 interviews lasting 10 to 30 minutesThe interviews exposed care disruptions, fear, mobility, and treatment-seeking behavior that laboratory results could not show.
2026 publicationQualitative structure3 major themes and 8 subthemesA defined thematic structure makes findings easier to audit, compare, and communicate.

What AI Thematic Analysis Healthcare Teams Can Learn

Why should healthcare researchers combine quantitative and qualitative data?

Healthcare researchers should combine quantitative and qualitative data when numerical measurements show the scale of a problem but interviews explain how and why the problem is experienced.

The 2026 Peru study used the Pillar Integration Process to compare malaria testing results with accounts from inhabitants, community health workers, and health personnel. The integrated analysis connected limited healthcare access and treatment interruptions with the observed malaria burden.

AI thematic analysis can support this workflow by organizing coded excerpts alongside survey segments or community groups. Researchers still need to determine whether a theme genuinely supports, contradicts, or merely coexists with a quantitative pattern.

How can AI help analyze healthcare interviews without flattening context?

AI can help analyze healthcare interviews by clustering related statements, suggesting candidate codes, summarizing themes, and comparing perspectives across participant groups.

The 2026 study shows why context must remain visible: residents of communities without health posts faced different access barriers from residents of communities with health posts, and participants described fear-driven migration to farm areas that reduced follow-up.

An AI workflow should preserve speaker identity, community, interview date, language, and source excerpt so researchers can inspect the evidence behind every generated theme.

What safeguards are important when using AI for Indigenous health research?

Indigenous health research using AI requires consent, privacy protection, culturally informed interpretation, and human review before findings are shared or used in policy decisions.

The 2026 study obtained individual informed consent and consulted community leaders before field activities, while also acknowledging that its 14-person interview sample did not proportionally represent the four communities and included no interviews in Caterpiza.

Researchers should treat AI-generated codes as analytical suggestions rather than facts, avoid diagnostic conclusions, and ensure that community perspectives are not reduced to decontextualized keyword counts.

How Evidano Helps With AI Qualitative Healthcare Research

Problem: Healthcare teams spend too long organizing transcripts and reports

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze healthcare interviews, open-ended survey responses, papers, reports, and other documents.

Evidano can organize uploaded interview transcripts and research documents for thematic analysis, helping teams move from raw text to candidate themes and supporting excerpts more efficiently. Researchers can review the original evidence before accepting an interpretation.

Problem: Different stakeholder groups describe the same health system differently

Solution: Evidano supports cross-segment analysis so researchers can compare community members, health workers, clinicians, locations, or study periods.

For a study like the 2026 Peru malaria research, cross-segment analysis could help compare reported barriers in communities with and without health posts, while keeping the comparison grounded in the underlying transcripts.

Problem: Researchers need to interrogate a large evidence set after initial coding

Solution: Evidano provides AI chat over uploaded documents and analyses, allowing researchers to ask focused questions about recurring barriers, exceptions, stakeholder differences, and supporting quotations.

Researchers can use Evidano’s AI chat capabilities to investigate a document set, then verify each answer against the source material and the study design.

Problem: Sensitive healthcare transcripts require careful handling

Solution: Evidano offers transcription with PII redaction and states that uploaded data is encrypted and never used to train third-party models.

Researchers should still obtain appropriate consent, follow institutional review requirements, and remove unnecessary identifiers before analysis. Details are available in Evidano’s data security information.

FAQ: AI Thematic Analysis Healthcare Research

What is AI thematic analysis in healthcare research?

AI thematic analysis in healthcare research is the use of artificial intelligence to help identify, organize, compare, and summarize recurring meanings in interviews, open-ended surveys, and documents.

The 2026 Peru malaria study used manual thematic analysis, so AI should be understood as a workflow aid rather than as part of that study’s reported methods. Human researchers remain responsible for interpretation and validation.

How many interviews did the Peru malaria study analyze?

The 2026 Peru malaria study analyzed 14 semi-structured interviews conducted in February 2022.

The interviews included nine community inhabitants, two community health workers, and three local Ministry of Health personnel, according to the study’s qualitative results.

Did malaria prevalence increase from 2021 to 2022 in the study?

The 2026 study did not establish that malaria prevalence increased from 2021 to 2022.

The study reported prevalence of 17.65% in 2021 and 26.09% in 2022, but the authors cautioned that different communities and recruitment strategies limited direct comparison.

What qualitative themes emerged from the COVID-19 malaria research?

The 2026 study identified themes involving pandemic effects on communities, disruptions to malaria care, and barriers to diagnosis and prevention.

Participants described reduced surveillance, treatment shortages, delayed care, fear of COVID-19, temporary migration, and reliance on herbal medicine.

Can AI replace researchers in qualitative healthcare analysis?

AI cannot replace researchers in qualitative healthcare analysis because interpretation depends on context, ethics, study design, language, and community knowledge.

The 2026 study relied on iterative review by three researchers and openly described limitations in its interview sample, demonstrating why human judgment and transparent methodological reporting remain necessary.

Conclusion and Next Steps

The 2026 Peru malaria study demonstrates that qualitative interviews can reveal how treatment shortages, geographic isolation, fear, and changing health priorities influence measured disease burden.

AI thematic analysis can help healthcare researchers process mixed-methods evidence faster, compare stakeholder experiences, and preserve a traceable path from theme to quotation, provided that human review remains central.

Evidano supports this workflow with thematic analysis, cross-segment comparison, document chat, transcription, and privacy-focused data handling. Try Evidano for free to analyze interviews, surveys, and healthcare research documents in one workspace.

Topics

  • AI thematic analysis healthcare
  • AI qualitative research
  • mixed-methods healthcare research
  • qualitative analysis of healthcare interviews
  • malaria research interviews

Keep reading

Browse all articles