AI Thematic Analysis for Healthcare Research

According to the PLOS ONE study published on November 13, 2026, Dutch-Flemish PROMIS computerized adaptive tests were feasible and generally acceptable in primary care physical therapy, but successful implementation required better workflow integration, clinician training, reimbursement, and replacement of legacy questionnaires.

• The PLOS ONE study surveyed 25 physical therapists and interviewed 10 physical therapists and 9 patients across 14 Dutch primary care physical therapy practices.
• The survey conducted from May 2 to June 20, 2022 found that 80% of physical therapists were interested in using PROMIS CATs, while only 28% reported regular daily use.
• The study found that 100% of surveyed physical therapists considered PROMIS CATs easy to administer, but only 40% believed CATs took little time.
• Interview participants described PROMIS CATs as quick and relevant, while the study identified simultaneous use of legacy PROMs as a major source of respondent burden.
• The study used hybrid inductive-deductive thematic analysis, with two researchers independently coding transcripts before consensus meetings and thematic mapping to Bowen's feasibility domains.

The November 13, 2026 PLOS ONE study found that PROMIS CATs supported structured conversations about symptoms, functioning, and treatment progress, but feasibility depended on how the measures fit existing clinical workflows.

The researchers conducted a mixed-methods concurrent triangulation study in 14 physical therapy practices in the Netherlands. According to the study methods, PROMIS CATs were integrated into electronic health records and administered during routine care to adults with musculoskeletal conditions affecting the spine or upper extremity.

The study evaluated four feasibility domains: acceptability, demand, practicality, and implementation. Quantitative survey findings were analyzed descriptively, while interview transcripts were analyzed thematically by two independent researchers. The researchers then compared the quantitative and qualitative findings to identify convergence, complementary explanations, and divergence.

The study reported that physical therapists generally valued the graphs and longitudinal feedback, while some therapists worried that labels such as "severe" or red color coding could concern patients. One physical therapist said, "The graph helps patients see their progress, even when symptoms are still there." Another explained, "I can't always link the questionnaire scores directly to my treatment choices."

The study also identified a difference between clinician perceptions and patient accounts. Only 24% of surveyed physical therapists believed patients were satisfied with PROMIS CATs, while interviewed patients generally described the CATs as quick, simple, and relevant. The researchers interpreted this difference as a possible gap between clinician assumptions and patients' reported experiences.

AI thematic analysis can help healthcare researchers move from large collections of interviews and open-ended responses to an auditable map of barriers, facilitators, and stakeholder differences.

The PROMIS CAT study shows why healthcare analysis should not rely on frequency counts alone. The percentage of physical therapists interested in PROMIS CATs was 80%, but the qualitative interviews explained why interest did not become routine use: therapists wanted CATs to replace legacy PROMs, patients needed a clear purpose for completing them, and clinicians requested more support interpreting scores.

The study also demonstrates the value of cross-segment analysis. Physical therapists emphasized score interpretation, workflow, and clinical decision-making, while patients emphasized relevance, speed, and whether results were discussed during consultations. Comparing these groups can reveal implementation risks that a single stakeholder sample may hide.

For healthcare research teams, a practical AI-assisted workflow includes importing interview transcripts and survey comments, creating a code structure around feasibility domains, checking themes against stakeholder segments, reviewing contradictory cases, and preserving representative quotations for reporting. AI can accelerate these steps, but researchers should still validate codes, inspect source passages, protect sensitive patient information, and distinguish participant perceptions from measured outcomes.

The PLOS ONE researchers captured this implementation tension in a physical therapist's words: "If the CAT can replace NPRS, PSFS, and Quebec while giving the same information, that's a win-win." The quotation shows why thematic analysis must connect user preferences to operational decisions rather than treating every comment as an isolated sentiment.

The November 13, 2026 PLOS ONE study shows that PROMIS CATs can be feasible and useful in physical therapy, while qualitative evidence reveals the workflow, interpretation, and adoption conditions behind that conclusion.

AI thematic analysis can help healthcare researchers synthesize interviews, compare patient and clinician perspectives, connect qualitative themes with survey findings, and preserve evidence for transparent reporting.

Researchers should use AI to reduce repetitive analysis work while retaining human review, privacy safeguards, and clear documentation of coding decisions. To analyze healthcare interviews and mixed-methods evidence more efficiently, Try Evidano for free.