Evidano home
Commentary on News

From Care Data to Action: Qualitative Analysis in Healthcare

Evidano9 min read

Healthcare researchers often need to connect qualitative feedback, electronic health records, questionnaires, and implementation metrics before they can explain why a program improved or stalled. The November 2026 PLOS One study of Iran’s Integrated Geriatric Care Program in Yazd demonstrates how participatory action research can turn mixed-method evidence into iterative service improvements. This article refracts the study through the lens of AI-enabled qualitative analysis in healthcare, showing how research teams can organize stakeholder feedback, compare intervention cycles, and identify gaps that numbers alone may miss. The study is especially relevant to public health researchers, implementation scientists, gerontology teams, and healthcare evaluators working with complex programs. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, reports, and other healthcare documents. AI-assisted analysis can accelerate synthesis, but healthcare teams still need transparent methods, human review, privacy controls, and ethical oversight.

Key Takeaways

According to the PLOS One study on integrated geriatric care in Yazd, participatory action research combined quantitative indicators and qualitative problem identification to improve implementation of a geriatric care program between January 2023 and August 2024. The study shows why qualitative analysis in healthcare is valuable: implementation scores improved substantially, while the reach of the program did not improve significantly.

  • According to the Yazd study, total standardized evaluation scores increased from 54.05 at baseline to 67.23 after the first intervention and 81.98 after the modified intervention in 2023 and 2024.
  • According to the Yazd study, the research team evaluated the program through six steps and two four-month action research cycles from January 2023 to August 2024.
  • According to the Yazd study, the complete care indicator increased from 15.4% before the intervention to 20.78% after the first intervention.
  • According to the Yazd study, the reach dimension did not show a statistically significant change, with P = 0.122, even though effectiveness, adoption, implementation, and maintenance improved.
  • According to the study authors, participatory action research can improve geriatric care through “iterative feedback and adaptation, stakeholder engagement, contextual tailoring, and integration of community resources.”

How Qualitative Analysis in Healthcare Supported the Yazd Study

The Yazd research team used a concurrent mixed-methods design to evaluate and improve the Integrated Geriatric Care Program at the Imamshahr Healthcare Center in Iran. According to the November 2026 PLOS One article, researchers combined electronic health record data, a researcher-made questionnaire completed by all 9 healthcare providers, qualitative barrier analysis, expert input, and the RE-AIM framework.

The study followed six sequential steps: problem identification, planning, implementation of a Proposed Intervention Plan, evaluation and revision, implementation of a Modified Proposed Intervention Plan, and final evaluation. According to the study authors, the first cycle lasted four months from November 2023 to February 2024, and the second cycle lasted four months from April to July 2024.

Qualitative analysis was used to identify barriers and challenges in providing and receiving geriatric care before the intervention. According to the PLOS One study, the research team integrated qualitative and quantitative findings so that numerical results could be checked against stakeholder and service-delivery evidence.

The researchers then used an importance and modifiability matrix to prioritize problems. According to the study, seven gerontology specialists and three healthcare providers ranked the identified issues, helping the team focus its intervention plan on problems that were both important and changeable.

The study authors described this process as creating “shared ownership among healthcare providers.” That finding matters for AI-enabled research because automated theme extraction can organize evidence quickly, while researchers and stakeholders remain responsible for interpreting context, prioritizing problems, and deciding what action is appropriate.

Yazd Integrated Geriatric Care Findings Snapshot

Date or study stageMetricValueImplication
January 2023 to August 2024Study period20 monthsAccording to the PLOS One study, the long evaluation period allowed researchers to examine baseline conditions, two intervention cycles, and subsequent revisions.
Baseline, 2023Total standardized evaluation score54.05 ± 8.09According to the study, the baseline score established the starting point for the RE-AIM evaluation.
After the Proposed Intervention Plan, 2024Total standardized evaluation score67.23 ± 5.89According to the study, the first four-month cycle was associated with a higher overall implementation score.
After the Modified Proposed Intervention Plan, 2024Total standardized evaluation score81.98 ± 6.61According to the study, the second cycle produced a further increase, with the overall difference statistically significant at P < 0.001.
After the first intervention cycle, 2024Complete care indicator20.78%According to the study, complete care increased from a 15.4% pre-intervention level, but coverage remained limited.
After the second intervention cycle, 2024Depression care indicator22.14%According to the study, depression care increased after the modified plan focused on the weakest indicator.
Across evaluation stages, 2023 to 2024Reach dimensionP = 0.122According to the study, the reach change was not statistically significant, showing that improved implementation did not automatically produce broader participation.

Implications for Healthcare Researchers and Implementation Teams

Why should healthcare teams combine qualitative and quantitative evidence?

Healthcare teams should combine qualitative and quantitative evidence because program metrics can show what changed without fully explaining why the change occurred. According to the Yazd study, qualitative barrier analysis helped researchers interpret program indicators and identify practical problems before designing an intervention.

The study’s approach gives implementation teams a repeatable workflow: measure outcomes, collect stakeholder explanations, compare the evidence, prioritize modifiable barriers, and reassess after action. AI-enabled qualitative analysis can support this workflow by grouping recurring themes across interviews, reports, questionnaires, and open-ended responses.

What does the unchanged reach score teach researchers?

The unchanged reach score teaches researchers that stronger delivery processes do not necessarily increase participation among the intended population. According to the PLOS One study, reach had a P value of 0.122, while effectiveness, adoption, implementation, and maintenance showed significant differences across study stages.

Healthcare researchers should therefore analyze access barriers separately from provider behavior and program execution. Segmenting qualitative evidence by older adults, caregivers, providers, neighborhood, risk level, or service type can reveal why a program performs well for some groups but remains difficult to access for others.

How can researchers preserve human judgment when using AI?

Researchers can preserve human judgment by using AI to organize evidence rather than allowing AI to make unreviewed clinical or policy decisions. According to the Yazd study, the intervention depended on expert prioritization, stakeholder discussion, repeated evaluation, and contextual adaptation.

A responsible workflow should include a documented codebook, review of representative excerpts, comparison of AI-generated themes with source material, checks for missing or contradictory voices, and explicit separation between implementation findings and clinical outcomes. The Yazd authors cautioned that their single-site design, lack of a control group, small provider sample of 9, and absence of patient-centered clinical outcomes limited causal and generalizable conclusions.

How Evidano Helps With AI-Enabled Healthcare Research

Problem: Mixed-method evidence is difficult to synthesize

Evidano is an AI-powered qualitative data analysis platform that ingests interview transcripts, research papers, reports, news, blogs, and survey spreadsheets for structured analysis. Researchers can use thematic, content, frequency, and cross-segment analyses to compare stakeholder perspectives with program indicators.

For a study modeled on the Yazd research, a team could organize provider interviews, older-adult feedback, implementation documents, and open-ended questionnaires in one analysis workspace. Researchers can explore the source evidence through AI chat and retain the original documents for verification.

Problem: Repeated intervention cycles create large volumes of text

Evidano can help research teams compare themes across baseline, first-cycle, and second-cycle data. Hierarchical codes and subcodes can represent categories such as reach, effectiveness, adoption, implementation, maintenance, depression care, home-based services, and community outreach.

Frequency and co-occurrence visualizations can show which barriers appear together, while cross-segment analysis can compare healthcare providers with older adults or compare different intervention stages. These outputs can support, but should not replace, expert interpretation.

Problem: Healthcare research requires privacy safeguards

Evidano provides transcription with PII redaction, and its data is encrypted and never used to train third-party models. Healthcare and public health teams can review the platform’s data security information when assessing whether an AI-enabled qualitative workflow fits their governance requirements.

Researchers should still obtain informed consent, follow institutional review requirements, minimize unnecessary personal data, and avoid using AI outputs as diagnostic conclusions. The Yazd study reported written informed consent and approval from the Research Ethics Committee of Tabriz University of Medical Sciences.

FAQ: Qualitative Analysis in Healthcare

What is qualitative analysis in healthcare?

Qualitative analysis in healthcare is the systematic interpretation of non-numerical evidence, such as interviews, focus groups, open-ended surveys, reports, and observations, to identify meanings, barriers, experiences, and themes.

According to the November 2026 Yazd study, qualitative barrier analysis complemented electronic health record data and provider questionnaires during evaluation of an integrated geriatric care program.

How did the Yazd study use participatory action research?

The Yazd study used participatory action research through six steps and two four-month intervention cycles conducted between January 2023 and August 2024.

According to the study, researchers and local stakeholders identified problems, prioritized modifiable issues, implemented an intervention, reviewed results, modified the plan, and evaluated the second cycle.

What were the main results of the Yazd geriatric care study?

The main result was an increase in total standardized evaluation scores from 54.05 at baseline to 67.23 after the first intervention and 81.98 after the modified intervention.

According to the study, the complete care indicator reached 20.78%, depression care reached 22.14% after the modified plan, and reach did not change significantly with P = 0.122.

Can AI replace healthcare qualitative researchers?

AI cannot replace healthcare qualitative researchers because interpretation, ethical judgment, contextual knowledge, and stakeholder accountability remain human responsibilities.

AI can help researchers organize large document collections, identify recurring themes, compare segments, and locate supporting excerpts. According to the Yazd study, expert panels and healthcare providers were central to prioritizing problems and adapting the intervention.

How can AI be used safely for healthcare qualitative research?

AI can be used safely when research teams apply consent, de-identification, access controls, human review, and documented validation procedures.

Healthcare teams should distinguish implementation evidence from clinical evidence and should not treat automated themes as diagnoses. The Yazd study itself reported limitations involving a single site, no control group, a provider sample of 9, and no patient-centered clinical outcomes.

Conclusion and Next Steps

The 2026 Yazd study shows that qualitative analysis in healthcare is most useful when it is connected to measurable indicators, stakeholder participation, and repeated cycles of action and review. The study also shows why teams must examine reach separately from implementation: provider adoption and program maintenance can improve while participation remains limited. AI-enabled qualitative research can make this evidence review faster by organizing themes, comparing segments, and linking findings back to source documents, provided that researchers maintain human oversight and privacy safeguards. Teams that want to test this workflow can try Evidano for free.

Topics

  • qualitative analysis in healthcare
  • AI qualitative research healthcare
  • mixed-methods healthcare research
  • geriatric care program evaluation
  • participatory action research analysis

Keep reading

Browse all articles