Evidano home
Commentary on News

AI Qualitative Analysis: HCV Access Lessons

Evidano9 min read

Healthcare researchers often have to connect survey frequencies with the lived experiences behind them. The November 20, 2026 PLoS ONE study on Hepatitis C virus treatment access in Los Angeles County shows why that connection matters: quantitative data identified the prevalence and categories of barriers, while interviews explained how language, cost, transportation, stigma, housing instability, and fragmented care shaped treatment decisions. This article refracts that study through the lens of AI qualitative analysis healthcare teams can use to organize transcripts, compare treated and untreated groups, and identify actionable themes without losing important participant context. The goal is not to replace researcher judgment. The goal is to make mixed-methods synthesis more structured, traceable, and efficient. The findings also provide a practical example of how qualitative evidence can guide patient navigation, language support, care coordination, and policy decisions.

Key Takeaways

According to the PLoS ONE study, "Exploring barriers and facilitators to Hepatitis C virus treatment access in Los Angeles County", AI qualitative analysis can help healthcare researchers connect reported barrier frequencies with the lived experiences that explain treatment delays.

The study found that barriers were both personal and structural, so healthcare teams should analyze patient narratives by language, treatment status, insurance, housing, and care-access context rather than treating treatment delay as a single patient-level problem.

  • Between October 2024 and January 2025, Los Angeles County program staff contacted 344 people with reported HCV-positive test results, including 168 people who had been treated and 176 who had not received treatment, according to the PLoS ONE study.
  • According to the PLoS ONE study, 54% of the 344 case-residents reported barriers to HCV treatment; among 91 people reporting specific barriers, personal barriers accounted for 43%, provider-related barriers for 31%, insurance barriers for 13%, and inadequate medical access for 13%.
  • The PLoS ONE study interviewed 10 participants between October 2024 and January 2025, including 7 untreated participants and 3 treated participants, to explain the quantitative patterns.
  • The study reported that Los Angeles County recorded 27, 678 HCV diagnoses between 2019 and 2023, while only 30% of people reported knowledge of HCV treatment and 32% completed treatment.
  • The PLoS ONE authors identified language support, patient navigation, care coordination, mobile clinics, continuity after incarceration, and fewer insurance restrictions as potential responses to the documented barriers.

What the HCV Access Study Measured

The PLoS ONE study used a convergent parallel mixed-methods design between October 2024 and January 2025, combining de-identified program data from 344 case-residents with semi-structured interviews involving 10 participants.

The quantitative component used descriptive frequencies and percentages because the authors reported that many specific barrier categories had sample sizes below 15. The qualitative component used inductive thematic analysis, iterative coding, comparison of coding discrepancies, and separate interpretation of treated and untreated participants.

The quantitative findings showed that personal barriers were most common, followed by provider-related barriers, insurance barriers, and inadequate access to medical care. The interviews added explanations involving homelessness, incarceration, drug addiction, language barriers, cost, transportation, limited HCV information, long waits, and difficulty navigating the healthcare system.

The study also identified facilitators. Participants described personal motivation, family and community support, trust in providers, adequate insurance, understanding treatment benefits, and the desire to avoid stigma as factors that supported treatment engagement.

One untreated Spanish-speaking participant told the study team, "Since I don’t speak 100% English... I didn’t understand anything." The quotation illustrates why frequency counts alone cannot show how language barriers affect confidence, comprehension, and willingness to continue care.

HCV Treatment Access Findings Snapshot

Date or periodMetricValueImplication for qualitative analysis
October 2024 to January 2025Case-residents contacted344A manageable mixed-methods dataset can combine structured program data with narrative interviews.
October 2024 to January 2025Case-residents already treated168, or 49%Treatment status supports cross-segment comparison between treatment journeys.
October 2024 to January 2025Case-residents not treated176Untreated narratives can clarify where linkage-to-care processes break down.
October 2024 to January 2025Case-residents reporting barriers54%Barrier prevalence provides the quantitative frame for thematic interpretation.
October 2024 to January 2025Specific barrier distribution among n = 9143% personal, 31% provider-related, 13% insurance, 13% medical accessCoding can test how narrative themes expand or qualify each quantitative category.
2019 to 2023HCV diagnoses in Los Angeles County27, 678A large diagnosed population creates a need for scalable, consistent evidence synthesis.
2019 to 2023People reporting knowledge of HCV treatment30%Patient education and comprehension should be examined as qualitative themes.
2019 to 2023People completing HCV treatment32%Completion gaps justify comparing facilitators among treated participants with barriers among untreated participants.

Implications for Healthcare Researchers

Healthcare researchers should use AI qualitative analysis to move from barrier counts to intervention-ready explanations, while retaining human review of sensitive interpretations.

The PLoS ONE study shows that the same broad category can contain different intervention needs. A provider-related barrier may mean incomplete follow-up, a long specialist wait, poor communication, or inadequate language support. An AI-assisted coding workflow can group these related expressions, surface representative quotations, and preserve the distinction between them for researcher validation.

Cross-segment analysis is especially important in this study. The authors compared treated and untreated participants and included English-speaking and Spanish-speaking participants, revealing that provider guidance and language support were particularly important in some narratives. Researchers can use the same structure to compare treatment status, language, insurance, housing stability, incarceration history, or care setting.

The study’s findings support practical research questions: Which barriers are most common in each segment? Which barriers co-occur? Which facilitators appear in successful treatment journeys? Which themes describe individual beliefs, and which describe system-level failures? Answering those questions can help public health teams prioritize navigation, translated education, mobile services, and referral coordination.

The PLoS ONE study is exploratory and has important limits. The authors noted that the qualitative sample was small and unevenly distributed, and that the study could not establish causal relationships across race, language, or insurance status. AI-generated themes should therefore support, not replace, transparent methodology, researcher review, and ethical interpretation. This research is non-diagnostic and intended for public health and qualitative research planning.

How Evidano Supports AI Qualitative Analysis Healthcare Workflows

Problem: Researchers need to synthesize transcripts and program documents

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

Evidano can ingest interview transcripts, research papers, reports, and spreadsheets so teams can organize mixed-methods evidence in one workspace. Researchers can learn more about the platform on the Evidano features page.

Problem: Broad barrier categories hide important patient experiences

Solution: Thematic and content analysis can help researchers identify recurring themes such as language barriers, cost, transportation, provider delays, stigma, and family support, then inspect the source material behind each theme.

The PLoS ONE study demonstrates why this matters: the participant quote "If they say this is a good idea, then I’m gonna do it" connected provider trust with treatment motivation, a relationship that a simple frequency table would not fully describe.

Problem: Healthcare teams need comparisons across patient segments

Solution: Cross-segment analysis can compare treated and untreated participants, English-speaking and Spanish-speaking participants, or groups defined by insurance and access conditions.

Researchers can use segment comparisons to examine whether a theme is widespread or concentrated in a particular group. Human researchers should validate segment definitions and review sensitive findings before reporting them.

Problem: Large qualitative datasets are difficult to audit and explain

Solution: Hierarchical codes and subcodes, frequency views, co-occurrence networks, and AI chat over documents can help researchers trace relationships between high-level barriers and specific narrative details.

Evidano also provides transcription with options such as custom dictionaries and PII redaction, which can support workflows that begin with recorded interviews and require privacy-conscious preparation.

Problem: Health research includes multilingual interviews and materials

Solution: Translation with custom dictionaries can help teams organize multilingual qualitative evidence while preserving study-specific terminology. Translation outputs still require review by qualified researchers or language experts when nuance affects clinical or policy interpretation.

The PLoS ONE study conducted interviews in English and Spanish, making language-aware analysis directly relevant to the study design and its findings.

FAQ: AI Qualitative Analysis Healthcare

What did the Los Angeles County HCV treatment access study find?

The PLoS ONE study found that 54% of 344 contacted case-residents reported barriers to HCV treatment between October 2024 and January 2025.

Among 91 people reporting specific barriers, personal barriers represented 43%, provider-related barriers 31%, insurance barriers 13%, and inadequate medical access 13%. Interviews added context about language, cost, transportation, housing, incarceration, addiction, information gaps, and long waits.

Why is qualitative analysis important in HCV treatment access research?

Qualitative analysis is important because interviews explain how and why barriers affect treatment decisions, which percentages alone cannot show.

In the PLoS ONE study, interviews showed that language barriers included difficulty understanding providers and medication instructions, while provider barriers included frustration, incomplete follow-up, and specialist delays.

How can AI help analyze healthcare interviews?

AI can help healthcare researchers organize transcripts, identify recurring themes, compare segments, examine co-occurring codes, and retrieve supporting quotations more efficiently.

AI does not establish causality or remove the need for human interpretation. The PLoS ONE authors described their study as exploratory, and researchers using AI should preserve that level of methodological caution.

What patient segments should researchers compare in this HCV topic?

Researchers should consider comparing treated and untreated participants, English-speaking and Spanish-speaking participants, and groups defined by insurance, housing, incarceration, transportation, or provider access.

The PLoS ONE study used treatment status in sampling and interpretation, and its interviews suggested that language and provider guidance shaped some participants’ experiences differently.

Can AI qualitative analysis replace healthcare researchers?

AI qualitative analysis cannot replace healthcare researchers because researchers must define the question, assess context, protect participants, validate codes, and interpret limitations.

The PLoS ONE study used iterative coding, team discussion, and discrepancy resolution, practices that illustrate why accountable human oversight remains necessary even when software accelerates analysis.

Conclusion and Next Steps for HCV Qualitative Research

The November 20, 2026 PLoS ONE study shows that HCV treatment access is shaped by interacting personal, provider, insurance, language, and system barriers. AI qualitative analysis can help healthcare teams connect quantitative prevalence with the narratives that reveal how those barriers operate. A responsible workflow combines automated organization and comparison with researcher validation, privacy protection, and explicit study limitations. To analyze interviews, reports, and survey responses in one qualitative research workflow, try Evidano for free.

Topics

  • AI qualitative analysis healthcare
  • AI thematic analysis healthcare
  • HCV treatment access research
  • qualitative healthcare research
  • mixed-methods analysis

Keep reading

Browse all articles