AI-Powered Qualitative Analysis of Autonomic Dysfunction

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. This post shows how AI-enabled qualitative analysis can accelerate interpretation of lived-experience research on autonomic dysfunction, using the PLOS One study as an example. The primary keyword for this guide is "qualitative analysis autonomic dysfunction" and the guidance below is aimed at academic researchers, clinical teams, and UX/health researchers who need reproducible, mixed-methods insights from interviews and surveys.

Key Takeaways

According to the PLOS One study, published August 17, 2026, 489 people completed a survey and 45 completed semi-structured interviews about living with conditions marked by autonomic dysfunction (PLOS One).

According to the PLOS One study, in May 2026 participants most commonly reported depression, anxiety, sleep problems, brain fog, and fatigue, and reported major impacts on employment: 19% (n = 77) lost or left work or school, and 42% (n = 165) reduced work or school hours.

489 participants completed the survey between November 18, 2023 and June 7, 2024, with 45 interviews completed, according to PLOS One (published August 17, 2026).
In the PLOS One data, 56% of participants followed provider recommendations and 81% did their own research about treatments in the survey (reported in the study results, PLOS One, 2026).
Only 58% of participants reported satisfaction with care in the PLOS One survey, and participants described frequent symptom dismissal in qualitative interviews (PLOS One, 2026).

What happened and why it matters for qualitative analysis

Answer: Shah et al., in PLOS One (published August 17, 2026), ran a mixed-methods study to describe lived experiences of people with symptoms associated with autonomic dysfunction and to integrate survey frequencies with 45 semi-structured interviews.

According to the PLOS One study, recruitment ran from November 18, 2023 to June 7, 2024 and included outreach via electronic health records, social media, flyers, and community networks, yielding 489 survey respondents and 45 interview transcripts that were thematically coded by multiple analysts.

According to the PLOS One study, the research team used thematic analysis with analyst triangulation, a draft codebook refined through rounds of coding, peer debriefing, and an audit trail to achieve data saturation (PLOS One, 2026).

Findings snapshot

Date / Range	Metric	Value	Implication
Nov 18, 2023–Jun 7, 2024	Survey participants	489	Large-scale mixed-method sample suitable for cross-segment analysis
Aug 17, 2026 (publication)	Interview transcripts	45	Sufficient depth for thematic analysis and exemplar quotations
Study report (2026)	Job/school impact	19% lost/left (n = 77); 42% reduced hours (n = 165)	Economic and functional impact is measurable and should be coded as outcome domains
Study report (2026)	Treatment behaviors	56% follow provider recommendations; 81% did own research	Patient self-directed information seeking is a prominent theme to cross-tab with demographics
Study report (2026)	Care satisfaction	58% satisfied with care	Mixed quantitative/qualitative signals: frequencies vs. salient narratives of dismissal

Implications for researchers and clinical teams

Answer: Integrating frequencies with interview salience reveals different decisions: quantify prevalence, then use AI-enabled thematic coding to surface the most consequential narratives.

According to the PLOS One study, quantitative data showed generally positive provider behaviors by frequency, while qualitative interviews emphasized symptom dismissal; researchers should therefore preserve both prevalence (counts) and qualitative salience (intensity) in analyses (PLOS One, 2026).

When a study like PLOS One (2026) reports 489 surveys and 45 interviews, researchers should run cross-segment analyses that link demographic groups to both symptom prevalence and narrative themes.
When interview quotes show emotional impact (for example, Participant 170: "Ever since having COVID, I feel like a very different person… There is a significant amount of brain fog…"), code for intensity and functional consequences to prioritize interventions.
For clinical teams, the PLOS One authors recommend simple communication practices: "I am listening, " "I believe you, " and "I don’t know, but we will work together to find answers/help" (Shah et al., PLOS One, 2026).

How Evidano helps with studies like the PLOS One mixed-methods work

Problem: Large survey plus many interview transcripts slows synthesis

Solution: Evidano automates thematic extraction and frequency matrices from transcripts and open-text survey answers, enabling faster integration of quantitative counts and qualitative salience.

Feature mapping: bulk ingest of transcript files, automated thematic clustering, and co-occurrence networks let teams reproduce the PLOS One joint-display approach at scale. See relevant features at Evidano Features.

Problem: Maintaining coder reliability and audit trails

Solution: Evidano tracks coding versions, supports multiple coders, and exports audit trails and codebooks for transparency, matching the trustworthiness practices reported by Shah et al. in PLOS One (2026).

Feature mapping: hierarchical codes → subcodes, inter-coder comparison views, and exportable audit logs streamline COREQ-style reporting.

Problem: Linking demographic segments to theme prevalence

Solution: Evidano generates cross-segment thematic frequency tables and visualizations, so teams can test whether themes like "symptom dismissal" cluster in particular demographic groups as the PLOS One study suggests.

Feature mapping: cross-tabulations, word co-occurrence networks, and downloadable charts accelerate mixed-methods integration.

FAQ: qualitative analysis autonomic dysfunction

How do I combine survey frequencies with interview themes in one analysis?

Answer: Use a joint-display mixed-methods workflow that aligns quantitative metrics with qualitative themes, then test divergences.

Supporting detail: The PLOS One study integrated counts (e.g., 489 surveys, 45 interviews) with thematic quotes to show where frequencies and salience diverged, and recommended presenting them side-by-side for interpretation (PLOS One, 2026).

What sample sizes support thematic saturation for lived-experience studies?

Answer: Saturation can be achieved with tens of interviews, depending on heterogeneity; in PLOS One the team reported data saturation after coding their 45 interviews (Shah et al., PLOS One, 2026).

Supporting detail: The PLOS One authors documented iterative codebook refinement and an audit trail, which are reproducible practices when using AI-assisted coding to accelerate rounds of review.

Can wearable biomarkers be integrated with qualitative themes?

Answer: Yes, pair time‑aligned HRV or wearable data with qualitative timestamps to create multimodal evidence of autonomic changes linked to experiences.

Supporting detail: Shah et al., PLOS One (2026) recommended HRV as a validated marker and suggested future studies incorporate wearable HRV data to tie physiological signals to reports of stress and invalidation.

How can AI-tools avoid amplifying bias in qualitative coding?

Answer: Use human-in-the-loop workflows with diverse analyst teams, transparent codebooks, and validation against independent coders.

Supporting detail: The PLOS One team used analyst triangulation and peer debriefing to reduce bias; similar guardrails should be implemented in AI workflows to preserve trustworthiness (PLOS One, 2026).

Conclusion & Next Steps

Answer: Mixed-methods studies like Shah et al., PLOS One (published August 17, 2026) generate both prevalence counts and deeply consequential narratives, and AI-enabled qualitative analysis speeds reproducible synthesis.

Shah et al., PLOS One (2026) concluded that "the lived experience for people with autonomic dysfunction is multilayered" and that patient-provider interactions and system barriers can reinforce physiological dysregulation.

If you run mixed-methods health research, use AI tools to produce joint displays, preserve qualitative salience, and generate exportable audit trails for publication and policy conversations: start by exploring Evidano Features to see how automated thematic and cross-segment analyses map to your protocol.

Next step: Try Evidano for free.

Topics

qualitative analysis autonomic dysfunction
AI qualitative research
patient experience autonomic dysfunction
thematic analysis interviews

Keep reading

Browse all articles