Evidano home
Commentary on News

What Yazd Shows: AI Qualitative Research in Healthcare

Evidano8 min read

Healthcare researchers and policy teams often need to combine interviews, stakeholder feedback, electronic health records, questionnaires, and implementation metrics before they can explain why a program is succeeding or falling short. The November 18, 2026 PLOS One study of Iran’s Integrated Geriatric Care Program in Yazd shows how participatory action research can connect those evidence types through repeated cycles of evaluation, intervention, and revision. The study’s total standardized score increased from 54.05 at baseline to 67.23 after the first intervention and 81.98 after the modified intervention. AI qualitative research in healthcare can help research teams organize the qualitative evidence behind those changes, compare stakeholder perspectives, and identify the implementation themes that quantitative scores alone cannot explain. This article translates the Yazd findings into a practical workflow for healthcare researchers, implementation scientists, and policy analysts.

Key Takeaways

According to the PLOS One study published on November 18, 2026, participatory action research improved several Integrated Geriatric Care Program indicators in one healthcare center in Yazd, Iran, although program reach did not improve significantly. AI qualitative research in healthcare can help teams analyze the stakeholder feedback, implementation notes, and open-ended responses that explain how those changes occurred.

  • The Yazd study ran from January 2023 to August 2024 and used two four-month intervention cycles to evaluate integrated geriatric care.
  • The Yazd study measured 1, 672 older adults with active electronic health records and collected questionnaire data from all 9 healthcare providers at the study center.
  • The Yazd study reported total standardized scores of 54.05 at baseline, 67.23 after the Proposed Intervention Plan, and 81.98 after the Modified Proposed Intervention Plan.
  • The Yazd study reported that the complete care indicator increased from 15.4% to 20.78% after the initial intervention, while the reach dimension remained statistically nonsignificant with P = 0.122.
  • The Yazd authors concluded that participatory action research can support geriatric care improvement through “iterative feedback and adaptation, stakeholder engagement, and integration of community resources.”

How the Yazd Participatory Action Research Worked

The Yazd study used a concurrent mixed-methods participatory action research design to evaluate and improve an Integrated Geriatric Care Program at the Imamshahr Healthcare Center. According to the authors, the six steps were problem identification, planning, implementation of the Proposed Intervention Plan, evaluation and revision, implementation of the Modified Proposed Intervention Plan, and final evaluation.

The Yazd research team combined electronic health record indicators with a researcher-made questionnaire completed by 9 healthcare providers. The questionnaire assessed the five RE-AIM dimensions: reach, effectiveness, adoption, implementation, and maintenance. The team standardized the dimensions to a 100-point scale and analyzed changes with repeated-measures ANOVA and Friedman tests.

The first intervention included five provider workshops, telephone follow-up with 300 older adults, home-based care for 25 high-risk older adults, and flyers distributed to 300 elderly residents. The second four-month cycle focused on depression care after the research team identified depression care as the weakest indicator.

The authors wrote that “continuous monitoring of the EHRs data, collaborative reflection among healthcare providers, and iterative modification of intervention strategies” were central mechanisms behind the observed improvements. The study also cautioned that its single-site design, lack of a control group, small provider sample, and absence of patient-centered clinical outcomes limit causal interpretation.

Yazd Study Findings Snapshot for Healthcare Researchers

Date or study stageMetricValueImplication
January 2023 to August 2024Study period20 monthsAccording to the PLOS One authors, the research covered baseline assessment and two iterative intervention cycles.
BaselineTotal standardized evaluation score54.05 ± 8.09According to the Yazd study, the score established the pre-intervention performance level.
After the Proposed Intervention PlanTotal standardized evaluation score67.23 ± 5.89According to the Yazd study, the first four-month cycle was associated with a substantial increase in overall evaluation scores.
After the Modified Proposed Intervention PlanTotal standardized evaluation score81.98 ± 6.61According to the Yazd study, the second cycle was associated with a further increase in overall evaluation scores.
After the initial interventionComplete care indicator20.78%According to the Yazd study, complete care improved, but the authors stated that coverage remained limited.
After the Modified Proposed Intervention PlanDepression care indicator22.14%According to the Yazd study, the targeted second cycle increased the depression care indicator.
Final evaluationReach dimension significance testP = 0.122According to the Yazd study, reach did not show a statistically significant change despite improvement in several other dimensions.

Implications of AI Qualitative Research in Healthcare

AI qualitative research in healthcare is most useful when researchers need to explain implementation patterns behind numeric outcomes, not when researchers want to replace participant engagement or clinical judgment. The Yazd study demonstrates why qualitative evidence matters: the quantitative results identified weak reach and depression care, while participatory discussions helped the team decide where to adapt the intervention.

Healthcare implementation teams can use AI-assisted thematic analysis to compare perspectives from providers, older adults, caregivers, and community volunteers. A structured analysis can identify recurring barriers such as limited awareness, access difficulties, workflow constraints, and reluctance to engage with depression-related services, while preserving links back to the underlying transcripts or documents.

AI analysis can also support cross-segment comparisons. Researchers can compare themes by stakeholder group, intervention cycle, care indicator, or RE-AIM dimension. That comparison can show whether a reported implementation problem is shared across participants or concentrated among a specific group.

The Yazd study authors described “shared ownership among healthcare providers” as an important implementation mechanism. Researchers should therefore use AI to accelerate synthesis and make patterns visible, while retaining human review, participant protections, methodological transparency, and ethical oversight. AI-generated themes are research aids, not clinical diagnoses or substitutes for validated evaluation.

How Evidano Helps Analyze Participatory Healthcare Research

Problem: Healthcare evidence is spread across transcripts, papers, reports, and spreadsheets

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

Researchers can bring mixed evidence into one workspace and use thematic, content, frequency, and cross-segment analyses to examine how stakeholder experiences relate to implementation indicators. Teams can learn more about the platform through Evidano's qualitative research features.

Problem: Manual coding slows iterative action research cycles

Evidano can accelerate first-pass coding and theme discovery across large collections of qualitative material, helping researchers review barriers, facilitators, and proposed adaptations before a team discussion.

Researchers remain responsible for validating codes, resolving disagreements, checking context, and documenting methodological decisions. That human review is especially important in healthcare and geriatric research.

Problem: Aggregate scores do not explain differences between stakeholder groups

Evidano supports cross-segment analysis so teams can compare themes across providers, older adults, caregivers, locations, intervention cycles, or other research-defined groups.

Researchers can use visualizations such as co-occurrence networks and hierarchical codes with subcodes to inspect relationships among barriers, actions, and outcomes.

Problem: Researchers need to interrogate evidence after the initial analysis

Evidano provides AI chat over uploaded documents and analyses, allowing research teams to ask targeted questions about recurring themes, conflicting accounts, and evidence linked to a specific intervention stage.

Evidano encrypts data and does not use customer data to train third-party models, which is relevant for teams handling sensitive healthcare research materials.

FAQ: AI Qualitative Research in Healthcare

What did the 2026 Yazd study find about integrated geriatric care?

The Yazd study found that overall Integrated Geriatric Care Program evaluation scores increased from 54.05 at baseline to 81.98 after two participatory intervention cycles.

The PLOS One authors reported improvements in effectiveness, adoption, implementation, and maintenance, but the reach dimension did not change significantly, with P = 0.122.

How can AI qualitative analysis support participatory action research?

AI qualitative analysis can organize stakeholder feedback, identify recurring barriers, compare perspectives across groups, and help research teams track themes across action research cycles.

AI does not replace participatory decision-making; researchers must validate machine-assisted themes against source material and stakeholder knowledge.

What data did the Yazd researchers combine?

The Yazd researchers combined electronic health record indicators with a researcher-made questionnaire completed by all 9 healthcare providers at the study center.

The research team evaluated the program using the RE-AIM dimensions of reach, effectiveness, adoption, implementation, and maintenance.

Why did the Yazd study focus its second intervention on depression care?

The Yazd research team focused the second intervention on depression care because the depression care indicator remained the weakest program indicator after the first cycle.

According to the study, the depression care indicator increased to 22.14% after the Modified Proposed Intervention Plan.

Can AI qualitative research prove that a healthcare intervention caused better outcomes?

AI qualitative research cannot establish causality by itself, and the Yazd study did not claim definitive causal proof.

The authors identified important limitations, including a single study site, no control group, a provider sample of 9, and no assessment of patient-centered clinical outcomes.

How should healthcare researchers use AI responsibly in qualitative analysis?

Healthcare researchers should use AI to support organization, coding, comparison, and retrieval while preserving human interpretation, participant confidentiality, auditability, and ethical review.

Researchers should also distinguish implementation findings from clinical outcomes and avoid treating AI-generated themes as diagnoses or validated measures.

Conclusion and Next Steps for AI Qualitative Research in Healthcare

The November 2026 Yazd study shows that participatory action research can turn mixed evidence and stakeholder feedback into iterative changes in geriatric care implementation. The findings also show why qualitative analysis is essential: improved aggregate scores did not eliminate weak reach, and targeted discussion helped identify depression care as a priority. AI qualitative research in healthcare can make that evidence review faster, more systematic, and easier to compare across stakeholder groups, provided that researchers retain human validation and ethical safeguards. To analyze healthcare interviews, documents, and open-ended survey responses in one workspace, try Evidano for free.

Topics

  • AI qualitative research in healthcare
  • AI qualitative analysis healthcare
  • participatory action research healthcare
  • geriatric care program evaluation
  • RE-AIM framework qualitative research

Keep reading

Browse all articles