Evidano home
Commentary on News

AI Qualitative Analysis of Healthcare Barriers

Evidano8 min read

Public-health and healthcare researchers often need to explain not only how many people face a barrier, but also why that barrier changes behavior. The November 2026 PLOS One study on Hepatitis C virus treatment access in Los Angeles County shows the value of combining program data with interview narratives. This article refracts that study through the lens of AI qualitative analysis in healthcare, showing how researchers can organize barriers, compare patient segments, preserve participant language, and move from raw transcripts to actionable findings. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and healthcare documents. The goal is not to replace methodological judgment, but to make evidence review more consistent, traceable, and efficient while keeping the study design and ethical safeguards in view.

Key Takeaways

According to the Exploring barriers and facilitators to Hepatitis C virus treatment access in Los Angeles County: A mixed-methods study, AI qualitative analysis can help healthcare researchers connect the frequency of reported barriers with the lived experiences behind those barriers. The study, published on November 20, 2026, found that treatment access was shaped by personal, provider-related, insurance, language, transportation, and healthcare-navigation factors.

  • Between October 2024 and January 2025, the Los Angeles County program contacted 344 people with reported Hepatitis C virus-positive test results, and 54% reported barriers to treatment, according to the PLOS One study.
  • Among 91 case-residents who reported specific barriers between October 2024 and January 2025, personal barriers accounted for 43%, provider-related barriers for 31%, insurance barriers for 13%, and inadequate medical access for 13%, according to the PLOS One study.
  • The qualitative sample included 10 interviews between October 2024 and January 2025, with 7 untreated and 3 treated participants, according to the PLOS One study.
  • The PLOS One study identified language barriers, unclear treatment information, long provider wait times, transportation problems, homelessness, incarceration, and drug addiction as important barriers or contextual factors.
  • The PLOS One study identified motivation, family and community support, provider trust, adequate insurance, treatment knowledge, and reduced stigma as facilitators of treatment access.

What the Los Angeles County Study Found

The November 20, 2026 PLOS One study found that quantitative program data showed the scale of Hepatitis C treatment barriers, while interviews explained how those barriers affected treatment decisions. The convergent parallel mixed-methods design collected and analyzed both forms of evidence during October 2024 to January 2025, then compared the findings during interpretation.

The PLOS One researchers used de-identified programmatic data from 344 case-residents and descriptive statistics because many specific barrier categories had fewer than 15 observations. The researchers also conducted 30- to 60-minute semi-structured interviews in English and Spanish, transcribed the interviews verbatim, and used iterative inductive coding with regular discussions to resolve coding discrepancies.

The interview evidence shows why frequency counts alone can be incomplete. One untreated Spanish-speaking participant said, “Since I don’t speak 100% English... I didn’t understand anything, ” while another untreated participant said, “I hadn’t heard so much about [HCV at the time of my diagnosis].” These quotations, reported in the November 20, 2026 PLOS One study, connect language and information gaps to delayed treatment engagement.

The study also identified system-level delays among treated participants. One participant reported that “to start my medication, I took 2 months to meet the doctor, ” according to the November 20, 2026 PLOS One study. The finding suggests that qualitative analysis should distinguish personal reluctance from obstacles created by referrals, wait times, insurance processes, or fragmented care.

Healthcare Barrier Analysis Snapshot

Date or study periodMeasureValueImplication for qualitative research
October 2024 to January 2025Case-residents contacted344 peopleA large program dataset can establish the prevalence and distribution of reported barriers.
October 2024 to January 2025Case-residents already treated168 people, or 49%Treatment status enables cross-segment comparison between treated and untreated experiences.
October 2024 to January 2025Case-residents not treated176 peopleUntreated participants can help explain why diagnosis does not consistently lead to treatment.
October 2024 to January 2025Case-residents reporting barriers54%Barrier analysis should examine both prevalence and the narratives behind each category.
October 2024 to January 2025Specific barrier reports, n = 91Personal 43%, provider-related 31%, insurance 13%, inadequate medical access 13%Frequency analysis can prioritize themes for deeper interview and segment analysis.
October 2024 to January 2025Qualitative interviews10 participants, 7 untreated and 3 treatedSmall samples can provide explanatory context but should not be treated as broadly generalizable.
2019 to 2023People diagnosed with HCV in Los Angeles County27, 678 peopleThe regional scale makes local barriers relevant to public-health program design.
2019 to 2023People reporting knowledge of HCV treatment30%Knowledge gaps can be analyzed as a distinct theme rather than merged with access barriers.
2019 to 2023People completing HCV treatment32%Treatment completion data supports comparison between access, initiation, and continuation.

Implications for Public-Health and Healthcare Researchers

Healthcare researchers can use AI qualitative analysis to connect barrier frequencies with patient language, segment differences, and intervention priorities. The November 20, 2026 PLOS One study demonstrates that a reported “personal barrier” may reflect homelessness, incarceration, addiction, limited health information, or the belief that treatment is not an immediate priority.

  • Separate barrier categories from their underlying mechanisms: the PLOS One interviews show that cost, language, transportation, and navigation problems can produce different forms of treatment delay.
  • Compare treated and untreated participants: the PLOS One study found that treated participants described homelessness, incarceration, addiction, and specialist wait times, while untreated participants emphasized cost, language, transportation, information, and system navigation.
  • Preserve multilingual meaning: the PLOS One study included English and Spanish interviews, making translation quality and language-specific coding important parts of analysis.
  • Distinguish facilitators from barriers: the PLOS One study identified provider trust, family support, motivation, insurance coverage, treatment knowledge, and reduced stigma as potential intervention assets.
  • Treat exploratory evidence proportionately: the PLOS One authors state that the small qualitative sample limits generalizability, so AI-generated themes should support human interpretation rather than replace it.

For public-health teams, the practical output is an evidence map linking each barrier to a possible response. The November 20, 2026 PLOS One study specifically points to language support, patient navigation, care coordination, mobile clinics for people experiencing homelessness, continuity of treatment after incarceration, and reduced insurance restrictions as possible strategies.

How Evidano Supports AI Qualitative Analysis in Healthcare

Problem: Researchers must synthesize many interviews and documents

Evidano supports thematic, content, frequency, and cross-segment analysis across interview transcripts, reports, papers, and other research documents. A healthcare research team could organize themes such as language access, cost, transportation, provider trust, and treatment motivation, then compare those themes across treated and untreated participants.

Researchers can explore the platform's relevant capabilities on the Evidano features page.

Problem: Multilingual interviews can hide important differences

Evidano provides transcription and translation workflows with custom dictionaries, which can help researchers process English and Spanish interview materials while preserving study-specific terminology. Human review remains important for culturally specific expressions, clinical language, and quotations used in publication.

Problem: Analysts need to interrogate evidence without losing context

Evidano's AI chat can answer questions over uploaded documents and analyses, helping researchers investigate questions such as which barriers appear most often, how treated and untreated participants differ, and which quotations support a theme. Researchers should verify every extracted claim against the source transcript and study protocol.

Problem: Healthcare data requires careful privacy controls

Evidano offers transcription with PII redaction, encrypted data handling, and a policy that customer data is never used to train third-party models. Those controls are relevant when researchers work with sensitive interviews, although institutional review board requirements and approved data-governance procedures still govern the research.

FAQ: AI Qualitative Analysis of Healthcare Barriers

What is AI qualitative analysis in healthcare research?

AI qualitative analysis in healthcare research uses artificial intelligence to organize, code, compare, and query interviews, open-ended responses, and documents while researchers retain responsibility for interpretation. The November 20, 2026 PLOS One study illustrates why AI should connect quantitative barrier counts with contextual interview evidence.

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

The main barriers were personal circumstances, provider-related problems, insurance, inadequate medical access, language, cost, transportation, limited treatment information, and difficulty navigating the healthcare system, according to the November 20, 2026 PLOS One study. The interviews added homelessness, incarceration, drug addiction, and long waits for specialists as important contextual factors.

How many people participated in the qualitative interviews?

Ten people participated in the qualitative interviews conducted between October 2024 and January 2025, according to the November 20, 2026 PLOS One study. The interview group included 7 untreated participants and 3 treated participants.

Can AI replace human thematic analysis in healthcare studies?

AI can accelerate thematic organization and comparison, but AI should not replace human thematic analysis in healthcare studies. The November 20, 2026 PLOS One researchers used iterative coding, team discussion, and discrepancy resolution, practices that show the importance of researcher oversight.

How should researchers analyze multilingual healthcare interviews?

Researchers should combine accurate transcription, carefully reviewed translation, language-aware coding, and direct examination of original quotations when analyzing multilingual healthcare interviews. The November 20, 2026 PLOS One study used English and Spanish interviews and found that language barriers were themselves part of the treatment-access experience.

Conclusion and Next Steps

The November 20, 2026 PLOS One study shows that healthcare barrier analysis is strongest when descriptive statistics and participant narratives are interpreted together. AI qualitative analysis can help public-health and healthcare researchers identify recurring themes, compare segments, locate supporting quotations, and translate complex evidence into intervention priorities. Researchers should pair AI assistance with de-identification, methodological transparency, multilingual review, and human validation, especially when working with sensitive clinical experiences. Teams that want to accelerate this workflow can try Evidano for free.

Topics

  • AI qualitative analysis healthcare barriers
  • qualitative analysis in healthcare
  • AI thematic analysis public health
  • mixed-methods healthcare research
  • healthcare barrier analysis

Keep reading

Browse all articles