Healthcare researchers need qualitative methods that capture more than clinical terminology. Patients and communities may describe the same condition through local words, spiritual explanations, family histories, or experiences of stigma. AI qualitative analysis in healthcare can help research teams organize these patterns across interviews, languages, locations, and participant groups, but interpretation must remain culturally grounded. A November 2026 study in PLOS Neglected Tropical Diseases shows why. Researchers analyzed interviews with people affected by leprosy and community members in French Guiana, where terms such as “kokobe” and “gwasi” carried meanings that did not map neatly onto the biomedical category of leprosy. This article explains the study’s findings, the implications for culturally sensitive health research, and how AI-assisted thematic analysis can support, rather than replace, expert interpretation.
Key Takeaways
According to the November 2026 PLOS Neglected Tropical Diseases study, culturally sensitive qualitative research can reveal how local terminology, spiritual beliefs, stigma, and treatment experiences shape healthcare journeys for people affected by leprosy in French Guiana. AI qualitative analysis in healthcare can help researchers compare these themes across interviews, languages, and participant groups, but clinical and cultural expertise remains essential.
- The study conducted between April and September 2025 included 20 patients and 37 community members across 37 interviews in French Guiana.
- According to the study authors, “kokobe” was mainly associated with deformities and amputations, while “gwasi” was mainly associated with skin lesions.
- The study reported that only 2 patients and 1 community member mentioned bacteria as a cause of leprosy, while spiritual, familial, environmental, and animal explanations were more common.
- The study found that local plant-based remedies were widely used, but the reported use of those remedies did not appear to reduce adherence to multidrug therapy.
- The authors concluded in November 2026 that culturally sensitive communication should clarify person-to-person transmission while taking local terminology and practices into account.
What the French Guiana Study Reveals About Qualitative Health Research
The November 2026 study examined how people affected by leprosy and members of Maroon communities in western French Guiana understood the disease, its causes, its symptoms, and its treatment. The researchers used semi-structured interviews because the study setting included substantial linguistic diversity, different literacy levels, and overlapping biomedical and local explanations of illness.
The researchers interviewed 20 patients recruited through French Guiana health centres and 37 community members connected to villages near the former Acarouany leprosarium between April and September 2025. The researchers continued recruitment until thematic saturation and used deductive and inductive thematic analysis.
The study authors found that local terms did not simply function as translations of the biomedical term leprosy. The study associated “gwasi” primarily with skin lesions and “kokobe” primarily with deformities or amputations. One community participant explained the progression as follows: “It starts with spots... If you don't treat it, your fingers can bend.”
The study identified several explanatory models. Maroon and Haitian participants often described spiritual causes, taboo transgression, curses, or family lineage, while bacterial causation was rarely mentioned. The study also reported confusion between leprosy and diabetes, concerns about transmission, delayed diagnosis, transport barriers, and discrimination.
The authors emphasized that the findings illustrate diverse perspectives rather than generalizable characteristics of every cultural group in French Guiana. The study also stated that interview transcripts could not be publicly shared because rare disease narratives and contextual details could make participants identifiable.
Findings Snapshot: AI-Ready Evidence From the 2025 Interviews
| Date or period | Metric | Value | Implication for qualitative researchers |
|---|---|---|---|
| April to September 2025 | Patient participants | 20 | Patient interviews provided evidence about lived experience, explanatory models, stigma, and care pathways, according to the November 2026 PLOS study. |
| April to September 2025 | Community participants | 37 | Community interviews added collective memories and culturally specific interpretations, according to the November 2026 PLOS study. |
| April to September 2025 | Total interviews | 37 | The dataset combined individual and group interviews across patients and western French Guianese communities, according to the study. |
| April to September 2025 | Patient interviews requiring mediation or a relative | 12 of 19 | Language and communication context were material to interpretation, according to the study's results. |
| April to September 2025 | Community interviews requiring mediation | 17 of 18 | AI-assisted analysis should preserve language, translation, and mediator context rather than flattening all responses into one category. |
| 2015 to 2021 | Reported annual leprosy prevalence in French Guiana | About 1 case per 10, 000 inhabitants | The disease remained a public health concern in the study setting, according to the earlier epidemiological evidence cited by the authors. |
Implications for AI Qualitative Analysis in Healthcare
Why should healthcare researchers analyze local terminology separately?
Healthcare researchers should analyze local terminology as its own qualitative theme because the November 2026 PLOS study found that “kokobe” and “gwasi” referred to visible manifestations and disability, not exact biomedical equivalents.
A coding framework that merges every local term into “leprosy” could erase differences between skin lesions, deformity, stigma, spiritual causation, and perceived severity. AI-assisted coding can identify recurring terms and co-occurring concepts, while researchers should validate meanings with cultural mediators and domain experts.
How can researchers use AI to compare cultural explanatory models?
Researchers can use AI to compare explanatory models by segmenting interviews by community, language, location, clinical status, or participant type before reviewing themes across those groups.
The November 2026 study found that spiritual explanations were prominent among Maroon and Haitian participants, while bacterial explanations were rarely mentioned. A cross-segment analysis can make such contrasts easier to inspect without treating them as prevalence estimates.
How can AI help identify stigma and care barriers?
AI can help identify stigma and care barriers by linking codes for nondisclosure, discrimination, transport, diagnostic delay, work interruption, and fear of contagion across many transcripts.
The French Guiana study reported experiences including public-service discrimination, social withdrawal, transport difficulty, and prolonged diagnostic pathways. Researchers can use thematic frequency and co-occurrence views to prioritize questions for health communication and service design.
What safeguards are needed for sensitive health interviews?
Sensitive health interview analysis requires privacy controls, human review, and careful handling of small or identifiable communities. The November 2026 study withheld its transcripts because contextual details could allow participants to be identified even after pseudonymization.
AI analysis should support secure research workflows, avoid exposing raw narratives unnecessarily, and distinguish analytic convenience from ethical permission to share data. Healthcare researchers should also document translation choices, mediator involvement, coding decisions, and interpretive uncertainty.
How Evidano Helps With Culturally Sensitive Health Research
Problem: Manual thematic coding slows multilingual interview analysis
Evidano is an AI-powered qualitative data analysis platform that helps healthcare researchers analyze interview transcripts, open-ended surveys, research papers, and reports.
Evidano can organize documents into thematic and hierarchical code structures, helping research teams review themes such as local terminology, transmission beliefs, treatment adherence, stigma, and access barriers. Researchers can learn more about the platform's relevant qualitative analysis features.
Problem: Cultural differences disappear in aggregate summaries
Evidano supports cross-segment analysis so researchers can compare themes across participant groups, locations, languages, or other study segments.
For a study like the French Guiana research, segments could include patients and community members, Maroon and Haitian participants, or interviews requiring mediation. Researchers must still validate culturally specific meanings rather than treating AI-generated categories as final interpretations.
Problem: Important concepts are difficult to trace across transcripts
Evidano can support AI chat over uploaded documents and analyses, allowing researchers to ask focused questions about where themes occur and how concepts relate.
A research team could query how terms such as “kokobe” and “gwasi” relate to disability, skin lesions, stigma, treatment, or disclosure, then review the underlying excerpts before reporting findings.
Problem: Sensitive transcripts require careful data governance
Evidano states that data is encrypted and never used to train third-party models, a relevant safeguard for research involving rare diseases, stigmatized conditions, and small communities.
Researchers should still apply informed-consent requirements, institutional policies, access controls, and human review. AI tools do not replace research ethics or cultural consultation.
FAQ: AI Qualitative Analysis in Healthcare
What is AI qualitative analysis in healthcare?
+
AI qualitative analysis in healthcare uses artificial intelligence to organize, code, compare, and summarize unstructured research data such as interviews, open-ended survey responses, and field notes.
The November 2026 PLOS study demonstrates why healthcare researchers need this support: the study combined 37 interviews with culturally specific terms, multiple languages, and different explanatory models of leprosy.
What qualitative method did the French Guiana leprosy study use?
+
The French Guiana study used semi-structured interviews and thematic analysis between April and September 2025.
The researchers combined deductive coding based on the interview guide with inductive coding for emergent themes, and they continued recruitment until thematic saturation.
What did the study find about the terms kokobe and gwasi?
+
The November 2026 PLOS study found that “gwasi” was mainly associated with skin lesions, while “kokobe” was mainly associated with deformities and amputations.
The study authors cautioned that neither term exactly matched the biomedical category of leprosy, which makes local terminology important for culturally sensitive communication.
Can AI replace human researchers in culturally sensitive health studies?
+
AI cannot replace human researchers in culturally sensitive health studies because cultural meaning, translation, ethics, and clinical context require expert judgment.
The November 2026 study used a multidisciplinary team that included dermatologists, a medical anthropologist, and a Maroon cultural health mediator, illustrating the value of contextual interpretation.
How should researchers protect sensitive qualitative health data?
+
Researchers should protect sensitive qualitative health data through informed consent, pseudonymization, secure storage, controlled access, and careful reporting of small-community findings.
The November 2026 PLOS study did not publicly share its transcripts because participants could potentially be identified through detailed personal narratives and contextual information.
Conclusion and Next Steps for Healthcare Researchers
The November 2026 PLOS study shows that qualitative health research can reveal cultural meanings that clinical categories alone may miss. The study's 20 patients and 37 community members described local terminology, spiritual and familial explanations, treatment experiences, stigma, and practical barriers that have direct implications for communication and care design.
AI qualitative analysis can help healthcare research teams manage complex interview datasets, compare segments, trace themes, and preserve an auditable path from code to evidence. Human researchers must remain responsible for cultural interpretation, ethical decisions, and clinical accuracy.
Teams analyzing interviews, open-ended surveys, or health research documents can Try Evidano for free to accelerate qualitative synthesis while keeping expert review at the center.
Topics
- AI qualitative analysis healthcare
- AI thematic analysis healthcare
- qualitative health research
- cultural healthcare research
- leprosy stigma research
Keep reading
- Commentary on NewsWhat Qualitative Leprosy Research RevealsLearn how qualitative leprosy research in French Guiana reveals cultural beliefs, stigma, and care pathways, and how AI improves thematic analysis.
- Commentary on NewsQualitative Research on Stigma Interventions: PakistanLearn what qualitative research found about storytelling, stigma, and empowerment in Pakistan, and how AI can accelerate thematic analysis for health teams.
- Commentary on NewsCulturally Aware AI Qualitative Analysis for LeprosyLearn how AI qualitative analysis can surface cultural beliefs, stigma, and care barriers in leprosy research, using a 2026 French Guiana study.