AI-enabled qualitative research helps teams collect, transcribe, code, and synthesize interview data faster and more transparently. The primary keyword for this post is "ai-enabled qualitative research" and the audience is qualitative researchers and health services teams who must interpret clinician views on large language model (LLM) use. According to the PLOS One protocol by Pokharel et al. (2026), published on August 7, 2026, primary care physicians in British Columbia will be interviewed using a theory-driven guide to reveal how clinicians weigh benefits, risks, and workflow fit for LLMs. This post refracts that protocol through the lens of AI-enabled qualitative research and shows practical mappings from protocol design to tools, reproducible coding, and cross-segment analysis.
Key Takeaways
According to the PLOS One protocol (Pokharel et al., 2026), published on August 7, 2026, the study will use semi-structured interviews with primary care physicians in British Columbia to examine perceptions of LLM adoption (PLOS One).
According to Pokharel et al. (2026), the study uses the technology adoption behavior (TAB) framework and combined deductive and inductive thematic analysis to generate policy-relevant insights.
- Pokharel et al. (2026) expect recruitment and data collection from August 1, 2025 to January 31, 2026 and reported the study design status on August 7, 2026.
- Pokharel et al. (2026) cite that the number of Canadians without a family doctor rose from 4.5 million in 2019 to about 6.5 million in 2023, framing primary care as a priority setting for LLM evaluation.
- Pokharel et al. (2026) will purposively sample physicians by self-reported LLM use: 50+ uses, 5–50 uses, and fewer than 5 uses, to ensure contrasting perspectives.
- Pokharel et al. (2026) note strengths and limits: “The semi-structured interview may reveal the interviewees’ internal views but limits the variety of insights gleaned, ” a caution the authors list under limitations.
What happened and how the protocol works
Answer: PLOS One published a qualitative study protocol on August 7, 2026 that specifies how primary care physicians’ perceptions of LLM adoption will be sampled, interviewed, and analyzed.
According to Pokharel et al. (2026) in PLOS One, the study uses a qualitative descriptive design with purposive sampling across usage strata to capture contrasting clinician experiences.
According to Pokharel et al. (2026), interviews will be semi-structured, recorded, transcribed verbatim, deidentified, and analyzed using both deductive codes derived from the TAB framework and inductive codes emerging from the data.
According to Pokharel et al. (2026), the interdisciplinary team plans reflexive memos and monthly team discussions to refine the codebook and move from codes to broader themes.
Findings Snapshot
| Date / Item | Metric | Value / Detail | Implication |
|---|---|---|---|
| Aug 7, 2026 | Publication | Protocol published in PLOS One | Provides a replicable study design for LLM adoption in primary care |
| Aug 1, 2025 - Jan 31, 2026 | Planned recruitment window | 6 months (expected) | Sets an achievable timeline for interview-based projects |
| 2019 → 2023 | Patients without family doctor | 4.5 million in 2019 → ~6.5 million in 2023 | Frames primary care capacity as a policy driver for technology adoption |
| LLM use categories | Sampling strata | 50+ uses, 5–50 uses, <5 uses | Enables contrastive thematic analysis across experience levels |
| July 18, 2025 → July 22, 2026 | Manuscript milestones | Received July 18, 2025; Accepted July 22, 2026 | Documents peer-review timeline useful for project planning |
Implications for qualitative researchers and health services teams
Answer: The PLOS One protocol shows how to combine a theory-driven interview guide with purposive sampling and mixed deductive/inductive coding to produce policy-relevant themes.
According to Pokharel et al. (2026), using the TAB framework ties interview prompts directly to constructs such as perceived ease of use, perceived usefulness, and task-technology fit, which helps teams develop a focused codebook before fieldwork begins.
According to Pokharel et al. (2026), purposive sampling across experience strata (50+, 5–50, <5 uses) supports analytic comparisons that reveal how familiarity with LLMs shifts perceived benefits and risks.
- Design tip: Use a pre-specified theoretical code set to speed initial coding and enable cross-case matrices, as modeled in the PLOS One protocol.
- Data quality tip: Record pilot interviews and refine prompts early, as Pokharel et al. (2026) pilots the first two interviews to ensure smooth flow.
- Policy translation tip: Map emergent themes to practice and regulatory levers, following Pokharel et al. (2026) plan to disseminate to policymakers and professional organizations.
How Evidano helps AI-enabled qualitative research
Definition and fit
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Evidano ingests audio, produces verbatim transcripts with custom dictionaries and PII redaction, and supports multi-language projects, aligning with Pokharel et al. (2026) emphasis on verbatim, deidentified transcripts.
Problem: Slow transcription and deidentification → Solution: automated, auditable transcripts
Evidano provides transcription with custom dictionaries and PII redaction so teams can follow the protocol step of destroying audio and analyzing deidentified transcripts, as required by Pokharel et al. (2026).
Evidano’s transcription features speed time-to-analysis and maintain an auditable trail that complements the ethical safeguards described in the PLOS One protocol.
Problem: Reconciling deductive and inductive codes → Solution: combined codebook workflows
Evidano supports thematic and hierarchical coding, enabling teams to import a TAB-derived deductive code set and iteratively add inductive codes while tracking code provenance.
Evidano’s visualizations and exportable codebooks reproduce the reflexive memoing and monthly codebook reviews that Pokharel et al. (2026) plan to use.
Problem: Cross-segment comparisons (experience strata) → Solution: rapid cross-segment analysis
Evidano’s cross-segment frequency and co-occurrence analyses let researchers compare physicians who report 50+ LLM uses vs 5–50 uses vs <5 uses, matching the protocol’s sampling strategy.
For tool details see Evidano features.
FAQ: ai-enabled qualitative research
What is AI-enabled qualitative research for studying LLM adoption?
Answer: AI-enabled qualitative research uses AI tools to accelerate transcription, coding, and synthesis while preserving interpretive rigor.
According to Pokharel et al. (2026), rigorous qualitative work still requires purposive sampling, reflexive memos, and close team review; AI tools should support, not replace, those practices.
How does the TAB framework in the PLOS One protocol guide interviews and coding?
Answer: The TAB framework supplies pre-defined constructs (perceived ease of use, perceived usefulness, task-technology fit) that serve as deductive codes and interview prompts.
According to Pokharel et al. (2026), using TAB lets researchers anchor interviews to tested constructs while leaving room for inductive themes to emerge during analysis.
Can AI platforms process deidentified clinical interviews and protect privacy?
Answer: Yes, platforms that support PII redaction and local data control can be used to analyze deidentified clinical interviews.
Evidano provides PII redaction and stores encrypted data, and Evidano’s workflow supports the protocol step where Pokharel et al. (2026) state that audio is destroyed and transcripts are deidentified for analysis.
How should researchers report timelines and sampling in protocol papers?
Answer: Report exact dates, sample criteria, and planned analytic methods so readers can assess feasibility and replicability.
Pokharel et al. (2026) exemplify this by listing recruitment dates (August 1, 2025 to January 31, 2026), sampling strata by LLM use, and intended deductive/inductive thematic analysis methods.
Conclusion & Next Steps
According to Pokharel et al. (2026) in PLOS One, a transparent, theory-driven qualitative protocol can produce actionable themes to guide safe and effective LLM integration into primary care.
Researchers who adopt AI-enabled qualitative research workflows can speed transcription, maintain deidentification, and run cross-segment analyses that mirror the TAB-guided contrasts in the PLOS One protocol.
If you want to operationalize a protocol like Pokharel et al. (2026) and scale from interview to policy-ready themes, try tools that combine secure transcription, iterative coding, and cross-segment visualizations.
Get started: Try Evidano for free
Topics
- ai-enabled qualitative research
- LLM adoption primary care
- qualitative analysis of LLMs
Keep reading
- Commentary on NewsAI-enabled Qualitative Analysis: LLM Adoption in Primary CarePractical guide to qualitative analysis of LLM adoption in primary care using the PLOS ONE protocol (Aug 7, 2026). Methods, numbers, and AI-enabled research tools explained.
- Commentary on NewsActionable Insights: LLM Adoption in Primary CareHow primary care physicians view LLM adoption and what AI-enabled qualitative research teams should do next. Learn method details and practical steps.
- Commentary on NewsPhysician Perceptions of LLMs: Adoption in Primary CarePractical explainer of physician perceptions of LLMs from a PLOS One protocol (7 Aug 2026). Learn methods, timelines, and how AI-enabled qualitative research accelerates insight.