From Stories to Evidence: AI Qualitative Analysis for Health Research

According to the PLOS Neglected Tropical Diseases study on storytelling, stigma, and empowerment, participatory storytelling in Karachi, Pakistan, was associated with movement from shame and concealment toward greater self-acceptance, confidence, and openness among people affected by leprosy.

The study suggests that qualitative health research analysis must examine both personal change and structural constraints, because gender norms, visible disability, community misconceptions, and economic barriers limited wider social change.

• The study collected data in June 2025 through 14 in-depth interviews and photovoice with 16 participants, representing a total sample of 17 people.
• The researchers found that the strongest reported effects occurred at the individual level, particularly reduced internalized and anticipated stigma and increased intrapersonal empowerment.
• The study reported that all participants described increased confidence, although community-level stigma continued for some participants with visible Grade 2 disability.
• The researchers concluded that sustainable impact requires regular community contact, peer leadership, inclusive outreach to women and people with visible impairments, and links to socioeconomic opportunities.
• AI qualitative analysis can help researchers compare themes across interviews, demographic segments, languages, and data collection methods, but human researchers must validate interpretations and protect participant confidentiality.

The 2026 PLOS Neglected Tropical Diseases study examined how a participatory storytelling intervention influenced stigma and empowerment among people affected by leprosy in Pakistan.

According to Ibrahim and colleagues, a one-year pilot began in Karachi in 2024 through the Marie Adelaide Leprosy Centre, with peer support groups, creative activities, health education, advocacy, and contact-based engagement. The qualitative evaluation recruited participants between May 30 and June 20, 2025, and collected interview data during a four-week period in June 2025.

The study combined 60 to 90 minute in-depth interviews with photovoice. Participants typically created up to 10 photographs over approximately three weeks, then selected two to three images for discussion and interpretation. The researchers analyzed interviews, captions, group discussions, and field notes thematically using the Social Ecological Model and an integrated framework of stigma and empowerment.

The researchers used both deductive and inductive coding. A preliminary codebook reflected the interview guide, stigma, empowerment, and social ecological domains, while new codes were added as patterns emerged. A senior researcher reviewed the developing codebook and a subset of coded transcripts, and disagreements were resolved through discussion.

The study reported that participants moved from shame and concealment toward self-acceptance, confidence, openness, and pride. One participant described the experience this way: “I have no fear, no shame, not feeling any guilt. I’m feeling like, if someone accept his crime in front of someone. I accept all those crimes, I feel lighter and so relaxed.”

The authors also reported important limits. The study had no baseline or comparison group, women represented 4 of the 17 participants, and the findings describe perceived impact rather than proving that the intervention alone caused the reported changes.

Health researchers should analyze stigma interventions across multiple social levels rather than treating personal confidence as the only outcome.

According to the study, the intervention produced its clearest gains at the individual level. Participants described increased confidence, self-respect, communication skills, and willingness to disclose their experiences. Peer groups also created solidarity and belonging, while organizational endorsement helped participants act as storytellers and peer educators.

The study found that community-level change was less consistent. Some participants felt more respected and were approached for advice, but persistent misconceptions and social avoidance remained, particularly for people with visible impairments. The researchers therefore recommended sustained, targeted contact instead of isolated awareness events.

The study also shows why cross-segment analysis is essential. All female participants required permission from husbands or male relatives to attend, while travel costs, distance, care responsibilities, and work schedules affected participation. Participants with visible Grade 2 disability reported more persistent public stigma. An AI qualitative analysis workflow can compare these patterns by gender, disability status, employment, age, location, and intervention exposure, while researchers retain responsibility for interpreting power and context.

A participant summarized the value of communication and listening by saying, “My communication skills are better. I can relate to different stories, and I can convince people better.” The quote illustrates why frequency counts alone are insufficient: researchers must connect recurring codes with participant language, mechanisms, and context.

For health research, policy, and program teams, the practical lesson is to use AI for organization and comparison, then use human review for meaning, ethics, reflexivity, and decisions. The findings are research evidence, not clinical advice or a diagnostic assessment.

The November 2, 2026 PLOS study shows how qualitative health research can make changes in stigma, confidence, peer relationships, and structural barriers visible through interviews and photovoice.

AI qualitative analysis can help research teams process multilingual transcripts, compare participant segments, trace themes to source evidence, and ask focused questions across a study corpus. Human researchers remain responsible for interpretation, participant protection, reflexivity, and accurate claims about what the data can establish.

Teams studying health stigma, empowerment, patient experience, or community interventions can use Evidano to bring documents and analyses into one reviewable workflow. Try Evidano for free and turn qualitative evidence into clearer, more traceable research insight.