Evidano home
Commentary on News

AI Qualitative Analysis: Hepatitis C Treatment Barriers

Evidano8 min read

Public health researchers need to explain why people diagnosed with Hepatitis C do not begin or complete treatment, but the answer is often distributed across program data, interview transcripts, language groups, and healthcare experiences. AI qualitative analysis can help research teams organize that evidence while preserving the context behind percentages. This article examines the November 20, 2026 PLoS ONE study of Hepatitis C treatment access in Los Angeles County and translates its mixed-methods design into practical guidance for public health, healthcare, and UX research teams. The goal is not to replace trained qualitative researchers. The goal is to accelerate transcript review, compare themes across segments, and connect lived experience with quantitative findings. The source study also shows why Spanish-language interviews, patient navigation, insurance access, stigma, and provider communication must be analyzed together. Because the topic involves health research, AI-assisted analysis should support non-diagnostic research and policy decisions, not provide medical advice.

Key Takeaways

The November 20, 2026 Exploring barriers and facilitators to Hepatitis C virus treatment access in Los Angeles County: A mixed-methods study found that Hepatitis C treatment access is shaped by personal, provider, insurance, language, transportation, and healthcare-system barriers.

  • According to the PLoS ONE study, researchers analyzed de-identified data from 344 Los Angeles County case-residents contacted between October 2024 and January 2025.
  • According to the PLoS ONE study, 54% of case-residents reported barriers, with personal barriers accounting for 43% of specified barriers, provider-related barriers for 31%, insurance barriers for 13%, and inadequate medical access for 13%.
  • According to the PLoS ONE study, qualitative interviews included 10 participants, seven untreated and three treated, and identified cost, language, transportation, limited information, homelessness, incarceration, addiction, and long provider wait times as important barriers.
  • According to the PLoS ONE study, facilitators included personal motivation, family and community support, trust in providers, adequate insurance, understanding treatment benefits, and the desire to reduce stigma.
  • According to the PLoS ONE study, AI-assisted qualitative analysis could help public health teams compare themes across treated and untreated participants, English and Spanish interviews, and quantitative barrier categories, provided researchers validate interpretations.

What the Los Angeles County Study Measured

The PLoS ONE study combined programmatic data with semi-structured interviews to explain both how often Hepatitis C treatment barriers occurred and why those barriers affected treatment decisions.

According to the PLoS ONE study, the quantitative component used de-identified linkage-to-cure data collected from October 2024 through January 2025, while the qualitative component used 30- to 60-minute interviews conducted in English and Spanish.

According to the PLoS ONE study, researchers used descriptive frequencies and percentages for the quantitative analysis because most specific barrier categories had samples smaller than 15, making inferential analysis unsuitable.

According to the PLoS ONE study, researchers used inductive thematic analysis, independently coded transcripts, compared coding discrepancies, and refined themes through team discussion. The study also used the Health Belief Model and Transtheoretical Model to interpret treatment-seeking behavior.

The PLoS ONE study reported that one untreated Spanish-speaking participant said, “Since I don’t speak 100% English... I didn’t understand anything, ” illustrating how language access can become a treatment barrier rather than a simple demographic variable.

The PLoS ONE study reported that one untreated English-speaking participant said, “I didn’t get this information previously, ” showing how unclear diagnosis and treatment information can affect engagement.

Hepatitis C Treatment Barriers: Findings Snapshot

Date or study groupMeasureValueResearch implication
October 2024 to January 2025, PLoS ONE studyCase-residents contacted344Program data provided the quantitative base for mixed-methods analysis.
October 2024 to January 2025, PLoS ONE studyCase-residents already treated168, or 49%Treatment status enabled comparisons between treated and untreated groups.
October 2024 to January 2025, PLoS ONE studyCase-residents untreated176Untreated participants represented a substantial treatment-linkage population.
October 2024 to January 2025, PLoS ONE studyCase-residents reporting barriers54%More than half of the program population reported obstacles to treatment.
October 2024 to January 2025, PLoS ONE studySpecified barrier categoriesPersonal 43%, provider-related 31%, insurance 13%, inadequate medical access 13%Barrier analysis should distinguish patient circumstances from system and provider factors.
October 2024 to January 2025, PLoS ONE studyQualitative interviews10 participants, seven untreated and three treatedInterviews added context and mechanisms behind the quantitative categories.
2019 to 2023, Los Angeles County data cited by the PLoS ONE studyPeople diagnosed with Hepatitis C27, 678The scale of diagnosis creates a large need for effective linkage-to-care research.
2019 to 2023, Los Angeles County data cited by the PLoS ONE studyPeople reporting knowledge of Hepatitis C treatment30%Patient education remains a key qualitative research topic.
2019 to 2023, Los Angeles County data cited by the PLoS ONE studyPeople completing Hepatitis C treatment32%Treatment completion is a separate outcome from diagnosis or initial linkage.

Implications for Public Health and Healthcare Researchers

Public health researchers should analyze Hepatitis C treatment barriers as interacting individual, provider, and structural factors rather than as isolated patient choices.

The PLoS ONE study found that untreated participants described cost, language barriers, transportation, limited information, and difficulty navigating the healthcare system. Researchers can translate these themes into intervention questions about bilingual education, patient navigation, mobile clinics, transportation support, and care coordination.

The PLoS ONE study found that treated participants still experienced homelessness, incarceration, drug addiction, and long waits for specialist care. Comparing treated and untreated narratives can therefore reveal barriers that delay care even after a person becomes motivated to seek treatment.

AI qualitative analysis is especially useful when a study includes multiple evidence types. A research team can use thematic coding to identify recurring concepts, frequency analysis to show how often concepts occur, and cross-segment analysis to compare language, treatment status, insurance, or demographic groups.

The PLoS ONE study cautioned that its qualitative sample was small and unevenly distributed, and that the findings were exploratory rather than broadly generalizable. AI-generated themes should therefore be treated as an audit and synthesis aid, with human researchers reviewing excerpts, code definitions, contradictions, and minority viewpoints.

How Evidano Supports AI Qualitative Analysis

Problem: Reviewing bilingual interview transcripts takes time

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

Evidano can transcribe interview recordings, translate research materials, and support custom dictionaries for recurring clinical or program terms. Researchers can learn more about the relevant Evidano transcription and speech-to-text features before importing interview data.

For a study like the PLoS ONE research, a team could preserve English and Spanish source material while organizing translated content for comparison. Translation outputs still require human review, especially for culturally specific language and sensitive health narratives.

Problem: Connecting percentages to lived experience is difficult

Evidano supports thematic, content, frequency, and cross-segment analyses across transcripts, reports, papers, and survey spreadsheets.

A public health team could compare quantitative barrier categories with interview themes such as language access, cost, provider trust, stigma, transportation, and treatment motivation. Researchers could then inspect the supporting passages instead of relying only on aggregate counts.

Evidano’s visualizations, including code hierarchies and co-occurrence networks, can help teams show how barriers and facilitators appear together. Visual outputs should support, not replace, the study’s documented coding framework.

Problem: Researchers need a secure way to interrogate a large evidence set

Evidano provides AI chat over uploaded documents and analyses, allowing researchers to ask focused questions about themes, segments, and supporting evidence.

A researcher could ask which barriers occur most often in untreated interviews, how Spanish-speaking narratives differ from English-speaking narratives, or which facilitators appear alongside provider trust. Researchers should verify every answer against the original transcript and maintain a transparent audit trail.

Evidano states that data is encrypted and never used to train third-party models, which is relevant when analyzing de-identified but sensitive health research materials. Teams should still follow their institutional review board, consent, retention, and de-identification requirements.

FAQ: AI Qualitative Analysis of Hepatitis C Treatment Barriers

What were the main Hepatitis C treatment barriers in the Los Angeles County study?

The main barriers were personal, provider-related, insurance, and inadequate medical access barriers, according to the PLoS ONE study published on November 20, 2026.

Interview themes added homelessness, incarceration, drug addiction, language barriers, cost, transportation, limited information, long wait times, and difficulty navigating the healthcare system.

How many people were included in the Los Angeles County Hepatitis C analysis?

The PLoS ONE study analyzed programmatic data from 344 case-residents and interviewed 10 participants between October 2024 and January 2025.

The interview group included seven untreated participants and three treated participants, while the program data included 168 treated and 176 untreated case-residents.

How can AI qualitative analysis help public health researchers?

AI qualitative analysis can accelerate transcript organization, thematic coding, frequency summaries, and comparisons across participant segments.

Human researchers must validate AI-generated codes, review source excerpts, preserve negative cases, and avoid treating exploratory findings as causal or representative without appropriate study design.

Can AI qualitative analysis replace a qualitative research team?

AI qualitative analysis should support, not replace, qualitative researchers who define the research questions, assess context, resolve ambiguity, and interpret ethical implications.

The PLoS ONE study used independent coding and team discussions to strengthen analytical rigor, practices that remain important when AI tools assist with synthesis.

What facilitators helped people access Hepatitis C treatment?

The PLoS ONE study identified personal motivation, family and community support, trust in medical providers, adequate insurance, understanding treatment benefits, and the desire to avoid stigmatization as facilitators.

The study reported that one treated participant described family accountability by saying, “She was always telling me, ‘Did you take your meds? ’”

Conclusion and Next Steps for AI Qualitative Analysis

The November 20, 2026 PLoS ONE study shows that Hepatitis C treatment access depends on connected personal, linguistic, financial, provider, and structural experiences.

AI qualitative analysis can help public health teams move from raw transcripts and spreadsheets to defensible themes, segment comparisons, and evidence-linked decisions, while trained researchers remain responsible for interpretation.

Teams studying treatment access can begin by combining de-identified program data with bilingual interview analysis, defining a transparent codebook, and checking every AI-supported finding against source evidence.

Start your next mixed-methods research project with Try Evidano for free.

Topics

  • AI qualitative analysis
  • Hepatitis C treatment barriers
  • qualitative analysis in public health
  • AI thematic analysis
  • mixed-methods research analysis

Keep reading

Browse all articles