Evidano home
Commentary on News

AI Thematic Analysis for Mixed-Methods Health Research

Evidano8 min read

Health researchers often need to connect epidemiological results with interviews, community perspectives, and healthcare-worker experiences. The challenge is not only coding qualitative data, but also comparing themes across participants, locations, and quantitative findings without losing context. A 2026 mixed-methods study of malaria in four Indigenous communities in the Peruvian Amazon shows why that integration matters: the study combined PCR-based screening with 14 semi-structured interviews to examine disease burden, access to care, and pandemic-related disruption. AI thematic analysis can help research teams organize this kind of evidence faster, while human researchers remain responsible for interpretation, ethics, and methodological judgment. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and research documents. The platform can support thematic, content, frequency, and cross-segment analysis for health researchers working with multilingual or mixed-format evidence.

Key Takeaways

According to the PLOS study on malaria care in Indigenous Peruvian Amazon communities, mixed-methods research showed that COVID-19-related disruptions affected malaria diagnosis, treatment availability, surveillance, and community follow-up during data collection in 2021 and 2022. AI thematic analysis can help researchers structure interview evidence and compare qualitative themes with epidemiological findings, but AI does not replace contextual interpretation by qualified researchers.

  • The PLOS study included 514 participants across four Indigenous communities and found PCR-confirmed malaria prevalence of 17.65% among participants surveyed in 2021 and 26.09% among participants surveyed in 2022.
  • The PLOS study analyzed 14 semi-structured interviews conducted in February 2022 with community members, community health workers, and local health personnel.
  • The PLOS study identified three major qualitative themes and eight subthemes concerning COVID-19 impacts, malaria-care disruptions, and barriers to diagnosis and prevention.
  • The PLOS study cautioned that the 2021 and 2022 prevalence estimates should not be interpreted as evidence of a temporal increase because the communities and recruitment strategies differed between study years.
  • AI thematic analysis is most useful in this setting for accelerating transcript organization, surfacing recurring patterns, and comparing themes across communities while researchers validate codes and preserve local meaning.

What the Peruvian Amazon Study Shows About AI Thematic Analysis

The Peruvian Amazon study shows that qualitative evidence can explain how health-service disruptions are experienced by communities, while quantitative testing measures the observed malaria burden. According to the PLOS study, researchers conducted a convergent parallel mixed-methods study in four communities in the Río Santiago district of Amazonas, Peru, collecting quantitative and qualitative data during October 4 to October 13, 2021, and February 28 to March 3, 2022.

The PLOS study used microscopy and PCR to detect malaria and used semi-structured interviews to examine healthcare access, prevention, diagnosis, and treatment. The researchers analyzed interviews thematically, reviewed codes and themes through discussions among three researchers, and integrated the quantitative and qualitative components using the Pillar Integration Process framework.

The PLOS study reported that interviewees described medication shortages, reduced surveillance, delayed diagnosis and treatment, and the prioritization of COVID-19 response activities over malaria control. One participant identified as P8 said, "... in this case they prioritized COVID... to be honest, I think it’s around 8 years that we have malaria here, and we can’t eliminate it."

The PLOS study also documented the importance of connecting lived experience with formal surveillance. One participant identified as P3 said, "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."

The study's design illustrates an important boundary for AI thematic analysis: an AI system can assist with coding, retrieval, comparison, and synthesis, but researchers must assess translation, cultural context, sampling limitations, and whether a theme is supported by the underlying data.

Findings Snapshot: Malaria, Interviews, and Mixed-Methods Evidence

Date or periodMetricValueImplication for qualitative research
2021Study participants514 total participants across the studyAI-assisted analysis can organize large participant-level datasets alongside qualitative evidence.
2021PCR-confirmed malaria prevalence17.65%Qualitative themes can help explain access, prevention, and care conditions surrounding a measured outcome.
2022PCR-confirmed malaria prevalence26.09%Cross-year comparisons require careful review because the PLOS study used different community participation and recruitment patterns.
February 2022Semi-structured interviews14 interviews lasting 10 to 30 minutesAI thematic analysis can speed transcript coding, but the small and uneven qualitative sample requires cautious interpretation.
2021 and 2022P. falciparum prevalence in Alianza Progreso24.19% in 2021 and 16.16% in 2022Segmented analysis can reveal community-level variation that overall averages may obscure.
2020 to 2021Global malaria cases cited by the PLOS study227 million to 241 millionHealth researchers can combine external reports, interview transcripts, and survey data to study system-level disruption.

Implications for Public Health and Healthcare Researchers

How can researchers connect interview themes with epidemiological findings?

Researchers can connect interview themes with epidemiological findings by creating a shared analytical structure for participants, communities, dates, symptoms, care barriers, and measured outcomes.

The PLOS study used the Pillar Integration Process to compare quantitative and qualitative results, which helped identify relationships between malaria burden, healthcare access, continuity of care, and community perceptions. AI-assisted qualitative analysis can support this process by retrieving relevant excerpts, grouping related codes, and comparing themes across segments before researchers build the final joint display.

Why does cross-segment analysis matter in remote-community health research?

Cross-segment analysis matters because health experiences can differ by community, participant role, year, access to a health post, and exposure to disease-control activities.

The PLOS study found that Alianza Progreso had particularly high observed P. falciparum prevalence and that communities without health posts faced additional access barriers. Researchers can use AI to compare community members, health workers, and health personnel, then verify whether apparent differences reflect genuine patterns or sampling limitations.

What should researchers validate before publishing AI-assisted themes?

Researchers should validate whether AI-generated codes are grounded in participant language, whether translations preserve meaning, whether minority or contradictory views are represented, and whether the sample supports the strength of the conclusion.

The PLOS study reported that all interviews were conducted in Spanish even though Indigenous languages were primarily spoken in the communities, and the study acknowledged that interviews were not conducted in Caterpiza. These details demonstrate why AI outputs require human review of language, coverage, consent, and representation.

How Evidano Helps With AI Thematic Analysis

Problem: Manual transcript coding slows mixed-methods synthesis

Evidano can support thematic analysis by organizing interview transcripts and documents into recurring themes, codes, and subcodes for researcher review.

Researchers studying healthcare access can use Evidano's qualitative research features to move from raw transcripts to structured thematic findings, while retaining responsibility for codebook decisions and interpretation.

Problem: Community perspectives are difficult to compare across roles and locations

Evidano supports cross-segment analysis, allowing research teams to compare themes across communities, participant groups, time periods, or other categories represented in the data.

For a study like the Peruvian Amazon research, teams could compare accounts from inhabitants, community health workers, and health personnel, then inspect excerpts behind each recurring theme.

Problem: Multilingual interviews create transcription and translation friction

Evidano provides transcription and translation workflows with custom dictionaries that can help research teams standardize specialized health terminology before qualitative analysis.

Researchers should still review transcripts and translations for Indigenous terms, culturally specific expressions, and clinically important distinctions before using AI-generated themes in a report.

Problem: Researchers need traceable answers from a growing evidence base

Evidano's AI chat enables researchers to ask questions across uploaded documents and analyses, helping locate supporting excerpts and compare findings across a research corpus.

Evidano states that data is encrypted and never used to train third-party models, which is relevant for teams handling sensitive interview transcripts and health-related research data.

FAQ: AI Thematic Analysis for Mixed-Methods Health Research

What is AI thematic analysis?

AI thematic analysis is the use of artificial intelligence to assist with identifying, organizing, comparing, and summarizing patterns in qualitative data such as interview transcripts and open-ended survey responses.

AI can accelerate repetitive analysis tasks, but researchers must review the evidence, define the analytic framework, assess alternative interpretations, and report limitations.

Did the Peruvian Amazon malaria study use AI thematic analysis?

No, the PLOS study describes a manual initial coding process followed by iterative review and refinement among three researchers.

The study provides a useful example of where AI could assist future mixed-methods teams, particularly in transcript retrieval, cross-segment comparison, and evidence organization, without implying that AI produced the study's findings.

How many interviews were included in the malaria study?

The PLOS study included 14 semi-structured interviews conducted in February 2022.

The interviewees included nine community inhabitants, two community health workers, and three local Ministry of Health personnel, although no qualitative interviews were conducted in Caterpiza.

What were the main qualitative themes in the study?

The PLOS study identified themes involving community impacts of COVID-19, disruptions to malaria care, and barriers to malaria diagnosis and prevention.

The study reported participant accounts of medication shortages, reduced follow-up, fear of COVID-19, migration to farm areas, and reliance on herbal or traditional medicine.

Can AI replace human researchers in qualitative health research?

AI cannot replace human researchers in qualitative health research because interpretation depends on context, ethics, participant meaning, sampling, and methodological judgment.

The PLOS study's discussion of language, community coverage, recruitment differences, and unequal representation shows why human oversight is necessary when interpreting sensitive community data.

Conclusion and Next Steps for AI Qualitative Research

The 2026 PLOS study demonstrates how mixed-methods health research can connect measured malaria prevalence with community accounts of disrupted care, limited access, and changing prevention behavior. AI thematic analysis can help health researchers organize transcripts, compare participant segments, retrieve supporting evidence, and integrate qualitative findings with surveys or epidemiological datasets. Researchers should use AI as an auditable support layer, not as a substitute for contextual interpretation, community engagement, or ethical review. Teams that want to analyze interviews, documents, and survey responses in one workspace can Try Evidano for free.

Topics

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

Keep reading

Browse all articles