Evidano home
Commentary on News

AI Qualitative Analysis for Healthcare: HCV Access

Evidano8 min read

AI qualitative analysis for healthcare can help public health researchers move from interview transcripts and program data to clearer evidence about why patients delay treatment. The November 2026 PLoS ONE study on Hepatitis C virus treatment access in Los Angeles County shows why that workflow matters: quantitative data identified the scale and categories of barriers, while interviews explained how language, cost, transportation, trust, and healthcare navigation shaped treatment decisions. This article translates the study into practical guidance for qualitative researchers, health policy teams, patient-navigation programs, and UX researchers working in healthcare. It also explains how AI can support thematic analysis without replacing research judgment, participant protections, or clinical expertise. Because the source concerns healthcare access, the analysis below is research-focused and non-diagnostic.

Key Takeaways

The PLoS ONE study, “Exploring barriers and facilitators to Hepatitis C virus treatment access in Los Angeles County”, published on November 20, 2026, found that HCV treatment access was shaped by interacting personal, provider, insurance, language, and healthcare-system barriers.

AI qualitative analysis healthcare teams can use should connect frequency patterns from program data with the lived explanations found in interviews, while preserving de-identification, auditability, and human review.

  • According to the November 2026 PLoS ONE study, 54% of 344 Los Angeles County case-residents contacted between October 2024 and January 2025 reported barriers to HCV treatment.
  • According to the study, among 91 case-residents who reported specific barriers, personal barriers represented 43%, provider-related barriers represented 31%, insurance barriers represented 13%, and inadequate medical access represented 13%.
  • According to the study, researchers interviewed 10 participants between October 2024 and January 2025, including 7 untreated participants and 3 treated participants.
  • According to the study, Los Angeles County recorded 27, 678 HCV diagnoses between 2019 and 2023, while only 30% of people reported knowledge of HCV treatment and only 32% completed treatment.
  • According to the study, language support, patient navigation, care coordination, mobile clinics, treatment continuity after incarceration, and fewer insurance restrictions were potential responses to the identified barriers.

What the HCV Access Study Measured

The November 2026 PLoS ONE study used a convergent parallel mixed-methods design to examine why Los Angeles County residents diagnosed with HCV did or did not access treatment between October 2024 and January 2025.

The study analyzed de-identified program data from 344 case-residents in Project HCV Connect and conducted 30- to 60-minute semi-structured interviews with 10 participants. The quantitative analysis used descriptive frequencies and percentages, while the qualitative analysis used inductive coding and iterative thematic analysis.

The study reported that 168 of the 344 case-residents were already treated and 176 had not received treatment by the analysis period. The study did not perform inferential statistical tests because most specific barrier categories had sample sizes below 15.

The study’s qualitative findings added context that the program data alone could not provide. Untreated participants described cost, language barriers, transportation, limited HCV information, and difficulty navigating the healthcare system, while treated participants described homelessness, incarceration, drug addiction, and long waits for specialist care.

One untreated Spanish-speaking participant told the researchers, “Since I don’t speak 100% English... I didn’t understand very well what they were telling me.” The quotation illustrates why healthcare researchers should analyze language and communication as substantive access factors rather than treating them only as demographic descriptors.

HCV Treatment Access Findings Snapshot

Date or periodMetricValueResearch implication
October 2024 to January 2025Case-residents contacted344The program data provided the quantitative base for the mixed-methods analysis.
October 2024 to January 2025Case-residents reporting treatment barriers54%Barrier analysis should examine both individual and system-level causes.
October 2024 to January 2025Specific barrier reports analyzed91The most common categories were personal barriers at 43% and provider barriers at 31%.
October 2024 to January 2025Qualitative interview participants10, including 7 untreated and 3 treatedInterview analysis explained how barriers affected treatment decisions.
2019 to 2023HCV diagnoses in Los Angeles County27, 678The study placed local treatment access within a substantial county-level disease burden.
2019 to 2023People reporting knowledge of HCV treatment30%Patient education emerged as a relevant intervention target.
2019 to 2023People completing HCV treatment32%Treatment completion remained low, particularly among underserved and minority groups.

Implications for Healthcare Qualitative Researchers

Why should healthcare teams combine frequency analysis with thematic analysis?

Healthcare teams should combine frequency analysis with thematic analysis because counts show how often a barrier appears, while interview themes explain how the barrier operates in people’s lives.

The November 2026 PLoS ONE study demonstrated this distinction by pairing the finding that personal barriers accounted for 43% of specific reports with interview evidence about homelessness, addiction, cost, language, and health information.

An AI-assisted workflow can first organize recurring concepts, then compare themes by treatment status, language, insurance, or other approved segments. Researchers must still review codes, preserve context, and avoid treating frequency as proof of causal importance.

How can qualitative analysis reveal differences between treated and untreated participants?

Qualitative analysis can reveal differences between treated and untreated participants by comparing the barriers, motivations, and support systems present in each group.

The November 2026 PLoS ONE study found that untreated participants emphasized cost, language, transportation, information, and system navigation, while treated participants described social instability and referral delays alongside facilitators such as family support, provider trust, insurance coverage, and understanding treatment benefits.

Cross-segment analysis can help public health teams identify whether one intervention should be adapted for multiple groups rather than applied uniformly.

What safeguards matter when AI analyzes sensitive healthcare interviews?

Sensitive healthcare interviews require de-identification, access controls, transparent coding decisions, and human review before findings inform programs or policy.

The November 2026 PLoS ONE researchers removed identifying information, assigned participant IDs, obtained verbal informed consent, and stored recordings and transcripts securely. AI tools should support these protections rather than bypass them.

Healthcare researchers should treat AI-generated themes as analytical assistance, not clinical diagnoses or definitive explanations of patient behavior.

How Evidano Helps With AI Qualitative Analysis Healthcare Workflows

Problem: Healthcare teams spend too long organizing transcripts and documents

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

Evidano can ingest interview transcripts, research papers, reports, news, blogs, and spreadsheets, then generate thematic, content, frequency, and cross-segment analyses. A healthcare research team could use these capabilities to compare treated and untreated participants, English- and Spanish-language interviews, or program categories such as insurance and provider access.

Researchers can review the underlying documents and use AI chat over their uploaded materials and analyses to investigate where a theme appears and how it differs across segments.

Problem: Multilingual interviews can hide important access barriers

Evidano supports transcription and translation workflows that can help teams prepare multilingual qualitative data for consistent analysis.

The November 2026 PLoS ONE study conducted interviews in English and Spanish and identified language barriers as part of the treatment-access problem. Evidano’s translation capabilities can help researchers organize translated material while custom dictionaries preserve study-specific terminology.

Researchers should validate translations against the source language and retain culturally meaningful wording before finalizing themes.

Problem: Sensitive participant data requires strong privacy controls

Evidano provides encrypted data handling and states that customer data is never used to train third-party models.

These controls are relevant to healthcare qualitative research involving diagnoses, treatment histories, housing instability, incarceration, or substance use. Teams should still follow their own institutional review board requirements, consent procedures, retention rules, and access policies.

Researchers can review Evidano’s data security information when evaluating an AI-assisted qualitative analysis workflow.

FAQ: AI Qualitative Analysis Healthcare

What is AI qualitative analysis in healthcare research?

AI qualitative analysis in healthcare research uses artificial intelligence to organize, code, summarize, compare, and interrogate qualitative data such as interviews, focus groups, open-ended surveys, and documents.

The November 2026 PLoS ONE study provides a useful example of the data such systems can support: 10 interviews were thematically analyzed alongside program data from 344 case-residents.

Can AI replace human thematic analysis in healthcare studies?

AI should assist human thematic analysis rather than replace it in healthcare studies.

The November 2026 PLoS ONE researchers used iterative coding, independent transcript coding, team comparison, and discrepancy resolution. Those practices show why human researchers remain responsible for interpretation, context, ethics, and methodological decisions.

What did the Los Angeles County HCV study identify as the main barriers?

The Los Angeles County HCV study identified personal barriers as the most common category at 43%, followed by provider-related barriers at 31%, insurance barriers at 13%, and inadequate medical access at 13% among 91 people reporting specific barriers.

Interview themes included cost, language, transportation, lack of information, healthcare navigation, homelessness, incarceration, drug addiction, and long waits for providers, according to the November 2026 PLoS ONE study.

How can researchers analyze language differences in healthcare interviews?

Researchers can analyze language differences by preserving original-language transcripts, documenting translation decisions, and comparing themes across language groups.

The November 2026 PLoS ONE study included three Spanish-speaking participants in its untreated interview group and reported that Spanish-speaking participants frequently described language-related frustration and a need for provider guidance.

Is AI qualitative analysis appropriate for clinical decisions?

AI qualitative analysis is appropriate for research and program-improvement support, but it should not be used as a standalone basis for diagnosis or individual clinical decisions.

The November 2026 PLoS ONE study examined barriers and facilitators to treatment access, not clinical diagnoses. Healthcare teams should combine AI-assisted findings with validated clinical evidence, professional judgment, and participant protections.

Conclusion and Next Steps for HCV Access Research

The November 2026 PLoS ONE study shows that HCV treatment access cannot be understood through counts alone because interviews reveal how language, cost, trust, social instability, and healthcare navigation interact.

AI qualitative analysis healthcare teams can use should connect structured frequencies with participant narratives, support cross-segment comparisons, and maintain privacy and human oversight.

Evidano gives researchers a practical way to organize documents, analyze themes and frequencies, compare segments, and ask questions across their evidence base. Try Evidano for free to begin an AI-assisted qualitative research workflow.

Topics

  • AI qualitative analysis healthcare
  • AI thematic analysis healthcare
  • HCV treatment access research
  • qualitative healthcare research
  • patient experience analysis

Keep reading

Browse all articles