Evidano home
Commentary on News

AI Qualitative Analysis Healthcare: HCV Lessons

Evidano9 min read

Healthcare researchers need to understand not only how often patients encounter barriers, but also why those barriers delay care. AI qualitative analysis healthcare workflows can help research teams organize interviews, identify recurring themes, and compare experiences across language, treatment, and access groups. A November 20, 2026 study in PLOS One provides a useful example: researchers combined program data from 344 Los Angeles County residents with 10 semi-structured interviews to examine access to Hepatitis C virus treatment. This post explains what the study found and how AI-assisted qualitative analysis can support similar public health research without replacing methodological judgment. The analysis is research-focused and non-diagnostic; clinical decisions should remain with qualified healthcare professionals.

Key Takeaways

According to the PLOS One study on Hepatitis C treatment access, barriers to HCV treatment in Los Angeles County were both personal and structural, with language, cost, transportation, provider delays, and limited treatment information shaping patient experiences.

The study shows why qualitative analysis is essential in healthcare research: quantitative data identified the frequency of reported barriers, while interviews explained how those barriers affected treatment decisions.

  • Between October 2024 and January 2025, Los Angeles County program data covered 344 case-residents, including 168 people who had been treated and 176 who had not received treatment, according to the PLOS One study.
  • The PLOS One study reported that 54% of case-residents experienced barriers, and among the 91 people who reported specific barriers, personal barriers accounted for 43%, provider-related barriers for 31%, insurance barriers for 13%, and inadequate medical access for 13%.
  • The qualitative sample included 10 interview participants, with 7 untreated participants and 3 treated participants, according to the PLOS One study.
  • The PLOS One study identified language support, patient navigation, care coordination, mobile clinics, treatment continuity after incarceration, and fewer insurance restrictions as potential intervention areas.
  • One untreated Spanish-speaking participant told the researchers, “I didn’t understand anything, ” illustrating how language and communication problems can become barriers to treatment engagement.

What the HCV Treatment Access Study Found

The mixed-methods study found that HCV treatment access depended on the interaction of patient circumstances, healthcare systems, providers, insurance, and social support.

The researchers analyzed de-identified program data from Project HCV Connect and conducted 30- to 60-minute interviews in English and Spanish between October 2024 and January 2025, according to the PLOS One methods section.

The quantitative component used descriptive frequencies and percentages because most specific barrier categories had sample sizes below 15, according to the PLOS One study. The qualitative component used inductive coding, iterative theme development, independent transcript coding, and team meetings to resolve coding differences.

The researchers used the Health Belief Model to examine concepts such as perceived barriers, perceived benefits, and self-efficacy. The researchers also used treatment status to compare experiences associated with different stages of treatment engagement.

The interviews added context that the program data could not provide by themselves. Untreated participants described cost, language barriers, transportation, limited information, and difficulty navigating the healthcare system, while treated participants described homelessness, incarceration, drug addiction, and long waits for specialist care.

A treated participant described a two-month wait to meet a specialist, according to the PLOS One study. Another participant said, “If they say this is a good idea, then I’m gonna do it, ” showing how trust in providers can facilitate treatment.

HCV Treatment Access Findings Snapshot

Date or periodMeasureValueResearch implication
October 2024 to January 2025Case-residents contacted344The program data provided the quantitative context for the interviews.
October 2024 to January 2025Case-residents already treated168, or 49%Treatment status enabled comparison between treated and untreated experiences.
October 2024 to January 2025Case-residents not treated176The untreated group helped identify delays and obstacles before treatment initiation.
October 2024 to January 2025Case-residents reporting barriers54%More than half of the program population reported at least one treatment access barrier.
October 2024 to January 2025Interviews completed10, including 7 untreated and 3 treated participantsInterviews explained the experiences behind the program-level patterns.
2019 to 2023People diagnosed with HCV in Los Angeles County27, 678The study placed treatment access within a substantial county-level public health burden.
As reported in the 2026 studyPeople reporting knowledge of HCV treatment30%Limited treatment knowledge may contribute to delayed engagement with care.
As reported in the 2026 studyPeople completing HCV treatment32%Completion remained low, particularly among some non-White minority groups.

Implications for Healthcare and Public Health Researchers

Why should healthcare teams combine quantitative and qualitative analysis?

Healthcare teams should combine quantitative and qualitative analysis when they need to measure the scale of a barrier and understand how that barrier operates in patients’ lives.

The PLOS One study used program data to show how frequently barriers were reported and interviews to explain experiences involving language, cost, transportation, stigma, trust, and fragmented care.

For research teams, the practical lesson is to preserve the connection between coded themes and the participant narratives that support them. AI can accelerate organization and comparison, but researchers should retain a transparent audit trail and review interpretations against the original transcripts.

How can researchers analyze language and treatment-status differences?

Researchers can analyze language and treatment-status differences by creating consistent segment variables before comparing themes across groups.

The PLOS One study compared treated and untreated participants and included English-speaking and Spanish-speaking interviewees, although the authors described the qualitative findings as exploratory and limited by the small sample.

An AI-assisted workflow can help identify whether themes such as provider guidance, cost, information gaps, or trust appear differently across segments, while researchers decide whether those differences are meaningful or require further sampling.

What should public health interventions prioritize?

Public health interventions should prioritize language support, patient navigation, care coordination, culturally appropriate education, transportation access, and continuity of treatment, according to the PLOS One authors.

The study also identified family support, provider trust, insurance coverage, understanding treatment benefits, and the desire to avoid stigma as facilitators. These findings can help teams design interview guides, outreach messages, and implementation studies around specific modifiable barriers.

How Evidano Supports AI Qualitative Analysis Healthcare Workflows

Problem: Healthcare interview synthesis is slow

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

Researchers can upload interview transcripts and reports to generate thematic, content, frequency, and cross-segment analyses. Thematic analysis can help organize findings such as language barriers, cost, provider trust, transportation, and treatment knowledge before researchers review the evidence.

Teams can explore the platform's relevant capabilities through Evidano's qualitative analysis features.

Problem: Segment comparisons are difficult to maintain consistently

Evidano can support cross-segment analysis of qualitative data so researchers can compare groups such as treated and untreated participants, language groups, insurance categories, or geographic populations.

Researchers remain responsible for interpreting small samples and avoiding overgeneralization. The HCV study's authors specifically noted that the 10-person interview sample and uneven distribution between treated and untreated participants limited generalizability.

Problem: Multilingual interviews can hide meaning during synthesis

Evidano supports transcription and translation workflows that can help teams prepare English- and Spanish-language interview data for analysis.

Researchers can use custom dictionaries for specialized terminology and review translated or transcribed material against the source data. The PLOS One study demonstrates why preserving language-specific context matters when participants describe healthcare communication and trust.

Problem: Sensitive healthcare data requires careful handling

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

Healthcare researchers should still follow their institutional review board requirements, consent procedures, de-identification practices, and applicable privacy controls. The PLOS One researchers received USC Institutional Review Board approval and removed identifying information from interview data.

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, and compare interviews, open-ended responses, and documents while researchers oversee interpretation.

The approach is useful for identifying recurring themes and differences across patient groups, but the PLOS One study's small qualitative sample illustrates why AI outputs should not replace methodological review or contextual judgment.

What were the main HCV treatment barriers in Los Angeles County?

The main HCV treatment barriers were personal circumstances, provider-related problems, insurance obstacles, inadequate medical access, language barriers, limited information, transportation, and difficulty navigating the healthcare system, according to the November 20, 2026 PLOS One study.

The study reported that 54% of 344 case-residents experienced barriers, with personal barriers representing 43% of the 91 people who reported specific barriers.

How many people participated in the HCV qualitative interviews?

Ten people participated in the HCV qualitative interviews, including 7 untreated participants and 3 treated participants, according to the PLOS One study.

The interviews were conducted in English and Spanish between October 2024 and January 2025, and the researchers used inductive coding and team-based discrepancy resolution.

Can AI qualitative analysis replace healthcare researchers?

AI qualitative analysis cannot replace healthcare researchers because researchers must assess context, ethics, sampling limits, alternative explanations, and the meaning of participant language.

AI can reduce repetitive synthesis work, but the PLOS One authors' discussion of small subgroup sizes and limited generalizability shows why human methodological oversight remains essential.

How can researchers protect sensitive qualitative healthcare data?

Researchers can protect sensitive qualitative healthcare data through informed consent, de-identification, access controls, secure storage, institutional review, and privacy-conscious analysis tools.

The PLOS One researchers obtained institutional review board approval, used verbal informed consent, removed identifying information, and assigned unique participant IDs. Evidano also provides encrypted data handling and does not use customer data to train third-party models.

Conclusion and Next Steps for AI Qualitative Analysis Healthcare

The November 20, 2026 PLOS One study shows that HCV treatment access cannot be understood through percentages alone: interviews revealed how language, information, trust, cost, housing, incarceration, and healthcare delays shaped treatment journeys.

AI qualitative analysis healthcare workflows can help public health and healthcare research teams move from large collections of transcripts to structured themes, segment comparisons, and evidence-informed questions for further study.

Researchers should use AI to accelerate analysis while preserving participant context, documenting decisions, and treating small samples as exploratory evidence rather than definitive population estimates.

To analyze interviews, surveys, and healthcare documents with Evidano, try Evidano for free.

Topics

  • AI qualitative analysis healthcare
  • qualitative analysis of healthcare barriers
  • AI thematic analysis healthcare
  • HCV treatment access research
  • healthcare interview analysis

Keep reading

Browse all articles