Primary care teams need clear, methodical evidence about clinician attitudes toward large language models, and qualitative research protocols supply that evidence. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. This post explains the study protocol published in PLOS One and translates its methods and timelines into actionable steps for AI-enabled qualitative research teams who want to study LLM adoption in clinical settings.
Key Takeaways
According to the PLOS One protocol, primary care physicians view LLM adoption as promising for documentation and administrative efficiency but also fraught with ethical, workflow, and liability concerns (PLOS One).
- According to PLOS One (Pokharel et al., 2026), the protocol was published on 7 August 2026 and frames a descriptive qualitative study of family physicians in British Columbia.
- According to PLOS One (Pokharel et al., 2026), the study planned participant recruitment and data collection from 1 August 2025 to 31 January 2026, a six-month window intended to reach sample sufficiency.
- According to PLOS One (Pokharel et al., 2026), the protocol notes that the number of Canadians without a family doctor increased from 4.5 million in 2019 to about 6.5 million in 2023, motivating focus on primary care.
- According to PLOS One (Pokharel et al., 2026), the research will purposively sample physicians by self-reported LLM use: frequent (50+ uses), occasional (5–50 uses), and rare (<5 uses).
What Happened and How the Study Works
The PLOS One protocol describes a qualitative descriptive study using semi-structured interviews to explore physician perceptions of LLMs in primary care.
According to PLOS One (Pokharel et al., 2026), the research team will purposively sample practicing family physicians in British Columbia to capture a range of LLM experience and years in practice.
According to PLOS One (Pokharel et al., 2026), interviews will be audio- or video-recorded, transcribed verbatim, deidentified, and analyzed using both deductive codes from the authors' Technology Adoption Behavior (TAB) framework and inductive thematic coding.
According to PLOS One (Pokharel et al., 2026), the authors write, "we aim to use thematic analysis drawing on deductive and inductive approaches to describe physicians’ perceptions, " which signals an explicit hybrid coding strategy.
According to PLOS One (Pokharel et al., 2026), the team plans reflexive memos, monthly codebook review, and NVivo software for data management and analysis, with senior oversight to ensure interpretive rigor.
Study Snapshot
| Date / Period | Metric | Value / Detail | Implication (per PLOS One 2026) |
|---|---|---|---|
| 7 August 2026 | Publication date | Protocol published in PLOS One | Protocol defines methods and dissemination targets for clinician, policy, and academic audiences |
| 1 Aug 2025 to 31 Jan 2026 | Planned recruitment window | Six months | Recruitment designed to reach sample sufficiency across LLM-use strata |
| 2019 and 2023 | Primary care access | Patients without a family doctor rose from 4.5 million (2019) to ~6.5 million (2023) | Authors use worsening access to motivate focus on primary care where LLMs might address clerical overload |
| LLM use counts (protocol) | Sampling strata | Frequent: 50+ uses; Occasional: 5–50 uses; Rare: <5 uses | Stratified sampling supports cross-experience thematic contrasts |
Implications for qualitative researchers and primary care teams
Answer: Researchers should design interview sampling and coding strategies that capture both perceived usefulness and technology–environment fit, as the PLOS One protocol recommends.
According to PLOS One (Pokharel et al., 2026), the Technology Adoption Behavior (TAB) framework combines perceived ease of use and perceived usefulness with task and user fit, and researchers should plan deductive codes from TAB while allowing inductive themes to emerge.
According to PLOS One (Pokharel et al., 2026), purposive recruitment across LLM-experience levels (50+, 5–50, <5 uses) yields contrasts that clarify whether concerns are practice- or exposure-driven.
According to PLOS One (Pokharel et al., 2026), reflexive memos and team discussion are central to interpretation, so research teams should budget time for iterative codebook revision and multidisciplinary review.
How Evidano Helps: AI-enabled qualitative research for LLM adoption studies
Problem: Long transcription and redaction cycles slow time-to-insight
Solution: Evidano automates transcription with custom dictionaries and PII redaction and reduces prep time so teams can begin coding sooner.
Practical fit: Researchers following the PLOS One protocol can record interviews, use Evidano’s transcription pipeline, and receive deidentified transcripts ready for NVivo-style coding or import.
Problem: Integrating deductive framework codes (TAB) with inductive themes is tedious
Solution: Evidano performs thematic extraction and crosswalks deductive codes with emergent themes to speed iterative codebook development.
Practical fit: According to PLOS One (Pokharel et al., 2026), teams must balance TAB-guided codes with inductive insights; Evidano accelerates that process and preserves audit trails for reflexive memos.
Problem: Cross-segment frequency and co-occurrence analysis is time-consuming
Solution: Evidano offers frequency, cross-segment analyses, and visualizations (word clouds and co-occurrence networks) to show how themes vary by LLM-use strata.
Practical fit: Teams can use these visual outputs to present findings to clinician groups and policymakers, aligning with PLOS One’s dissemination goals.
Learn more
Visit the Evidano features page to compare specific tools for transcription, thematic analysis, and secure data handling.
FAQ: physician perceptions of LLMs
What design and sampling does the PLOS One protocol use?
Answer: The protocol uses a qualitative descriptive design with purposive sampling of family physicians in British Columbia.
According to PLOS One (Pokharel et al., 2026), sampling targets physicians across three LLM-experience strata (50+, 5–50, <5 uses) and varies years in practice to ensure diverse perspectives.
Which analytical approach does the study plan to use?
Answer: The study plans hybrid thematic analysis, combining deductive codes from the TAB framework with inductive coding.
According to PLOS One (Pokharel et al., 2026), the team will use NVivo for data management, reflexive memos to document interpretation, and monthly codebook review to finalize themes.
When did the protocol publish and when was the study planned?
Answer: The protocol was published on 7 August 2026 and the team planned recruitment from 1 August 2025 to 31 January 2026.
According to PLOS One (Pokharel et al., 2026), the authors state, "we expect participant recruitment and data collection to be completed within six months (anticipated timeline from August 1, 2025, to January 31, 2026)."
How will the study protect participant privacy and ethics?
Answer: The study uses ethics board approval and transcript deidentification procedures described in the protocol.
According to PLOS One (Pokharel et al., 2026), the team obtained UBC Behavioral Research Ethics Board approval (H25-01658), will destroy audio after transcription, and will work only with deidentified transcripts.
Conclusion & Next Steps
The PLOS One protocol provides a reproducible qualitative path to understand how primary care physicians weigh benefits and risks of LLMs in clinical practice.
According to PLOS One (Pokharel et al., 2026), rigorous sampling, hybrid deductive–inductive coding, reflexivity, and clear dissemination plans are core to producing policy-relevant findings.
If your team plans a similar study, using AI-enabled tools for transcription, deidentification, and rapid thematic synthesis can shorten the route from data collection to usable insight.
Get started with a hands-on trial: Try Evidano for free.
Topics
- physician perceptions of LLMs
- LLM adoption in primary care
- qualitative study LLMs
- AI-enabled qualitative research
Keep reading
- Commentary on NewsProtocol: Physician perceptions of LLMsHow primary care physicians view large language models, per a PLOS ONE protocol (Aug 7, 2026); learn methods, numbers, and how AI-enabled qualitative research accelerates insights.
- Commentary on NewsStudy Protocol: Physician Perceptions of LLMsReview of a PLOS One protocol on primary care physician perceptions of LLMs, with dates, sample metrics, and AI-enabled qualitative research guidance.
- Commentary on NewsPhysician Perceptions of LLMs: Qualitative AnalysisWhat primary care physicians think about LLM adoption and how AI-enabled qualitative research can speed insight. Learn methodological takeaways and next steps.