Physical therapy researchers often need to combine survey results with interview transcripts to understand whether a patient-reported outcome measure is acceptable, practical, and useful in routine care. The November 13, 2026 study in PLOS One on Dutch-Flemish PROMIS computerized adaptive tests shows why that synthesis matters: numerical adoption rates identify patterns, while interviews explain workflow friction, score-interpretation concerns, and patient expectations. This article refracts the study through AI qualitative analysis, showing how researchers can organize mixed-methods evidence without losing methodological transparency. The central lesson is that AI can accelerate transcript review and cross-segment comparison, but researchers still need clear coding frameworks, source traceability, and human judgment.
Key Takeaways
According to the Feasibility of patient-reported outcomes measurement information system (PROMIS) computerized adaptive tests in patients receiving physical therapy: A mixed-methods study, PROMIS computerized adaptive tests were feasible and generally acceptable in Dutch primary care physical therapy, but wider adoption depended on reducing duplicate questionnaires, improving score interpretation, and embedding the tools into clinical workflows.
AI qualitative analysis can help researchers process interview transcripts, compare patient and therapist perspectives, and connect qualitative themes with survey percentages while preserving a reviewable analytical trail.
- The PLOS One study published on November 13, 2026 included 25 physical therapists in a survey, plus interviews with 10 physical therapists and 9 patients across 14 physical therapy practices.
- The study reported that 80% of surveyed physical therapists were interested in using PROMIS CATs, while only 28% reported regular use in daily practice.
- The study found that 100% of surveyed physical therapists considered PROMIS CATs easy to administer, but only 40% considered them time-efficient.
- Interview participants described PROMIS CATs as quick and relevant, while therapists identified portal problems, uncertainty about T-score interpretation, and simultaneous use of legacy PROMs as barriers.
- The researchers used hybrid inductive-deductive thematic analysis, with two researchers independently coding transcripts before consensus meetings and review of unresolved disagreements.
What the PROMIS Study Shows About AI Qualitative Analysis
The PROMIS study shows that qualitative analysis explains why implementation metrics succeed or fail. The researchers assessed acceptability, demand, practicality, and implementation using a mixed-methods concurrent triangulation design, combining a physical therapist survey with semi-structured interviews.
The study collected interviews between March 21 and November 23, 2022, and reported interview lengths of 32 to 62 minutes. The researchers transcribed all interviews verbatim, checked the transcripts for accuracy, and analyzed them using hybrid inductive-deductive thematic analysis.
AI qualitative analysis is most useful in this setting as an organizing and synthesis layer. An AI system can identify recurring references to questionnaire burden, portal access, score interpretation, and item relevance, then help researchers compare whether those themes appear differently in patient and therapist accounts.
The PLOS One researchers found a notable divergence between data sources: only 24% of surveyed therapists believed patients were satisfied with PROMIS CATs, while interviewed patients generally described the CATs as quick, simple, and relevant. A qualitative analysis workflow makes that divergence visible rather than collapsing it into a single overall satisfaction result.
The study supports a human-led AI workflow rather than fully automated interpretation. Researchers should use AI to propose codes, cluster excerpts, and retrieve evidence, then validate themes against original quotations, study objectives, and the sampling context.
PROMIS Implementation Findings Snapshot
| Date or study detail | Metric | Value | Implication for qualitative researchers |
|---|---|---|---|
| November 13, 2026 | Study publication | PLOS One research article | Use the published methods and results as the primary source for coding and evidence extraction. |
| Study period | Physical therapy practices | 14 practices in the Netherlands | Compare implementation themes across sites when site-level data are available. |
| Survey | Physical therapists completing the survey | 25 therapists | Treat percentages as descriptive findings from a small professional sample. |
| Interviews | Physical therapists and patients interviewed | 10 therapists and 9 patients | Separate clinician and patient perspectives during thematic and cross-segment analysis. |
| Survey result | Therapists interested in PROMIS CATs | 80% | Interest was high, but interest alone did not produce routine implementation. |
| Survey result | Therapists reporting regular daily use | 28% | The gap between demand and adoption should become an implementation theme. |
| Survey result | Therapists finding CATs easy to administer | 100% | Technical simplicity did not eliminate broader workflow and interpretation barriers. |
| Survey result | Therapists considering CATs time-efficient | 40% | Researchers should distinguish tool usability from total workflow efficiency. |
Implications for Physical Therapy and Health Researchers
Physical therapy researchers should analyze patient-reported outcome implementation by separating acceptability, demand, practicality, and implementation rather than treating adoption as a single outcome. The PLOS One study used these four Bowen framework domains to structure both survey interpretation and qualitative themes.
Researchers should preserve participant-group differences during AI-assisted analysis. The PLOS One study found that therapist perceptions of patient satisfaction did not fully match the accounts of interviewed patients, demonstrating why cross-segment analysis is essential.
Researchers should code workflow burden separately from instrument burden. The PLOS One study reported that PROMIS CATs were easy to administer, yet the simultaneous use of legacy PROMs increased total respondent burden. An AI analysis system can distinguish comments about the CAT itself from comments about portals, duplicate instruments, missing emails, and clinic processes.
Researchers should treat quotations as evidence, not decoration. One physical therapist told the study team, "I can’t always link the questionnaire scores directly to my treatment choices, " while another participant said, "The adaptive questions are useful; with one CAT you may replace several longer questionnaires." These quotations connect implementation percentages to the practical reasoning of users.
Healthcare researchers should apply additional privacy safeguards when analyzing interview transcripts. The PLOS One authors stated that interview data could not be shared publicly because the sensitive patient information could not be completely anonymized. AI tools used for comparable research should therefore support controlled access, encryption, and clear data-use policies.
How Evidano Helps With PROMIS Qualitative Research
Problem: Reviewing interview transcripts takes time
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.
Evidano can organize transcript evidence into thematic and content analyses, helping researchers review recurring implementation issues such as questionnaire fatigue, digital access, score interpretation, and item relevance. Researchers can inspect the underlying document context instead of relying only on a summary.
Teams studying PROMIS implementation can explore Evidano's qualitative research features to compare AI-assisted synthesis with their existing coding process.
Problem: Patient and therapist perspectives can diverge
Evidano supports cross-segment analysis so researchers can compare themes across groups such as patients, physical therapists, practice owners, or implementation sites.
A cross-segment workflow can help surface contrasts like the PLOS One study's difference between therapists' survey perceptions of patient satisfaction and interviewed patients' descriptions of PROMIS CATs as quick and relevant.
Problem: Researchers need to connect themes with frequencies
Evidano can combine thematic analysis with frequency analysis and visualizations such as word clouds, co-occurrence networks, and hierarchical codes with subcodes.
Researchers can use these outputs to identify which implementation concerns recur most often, then return to the original excerpts for interpretation. Frequencies should support, not replace, contextual qualitative judgment.
Problem: Sensitive health interviews require careful data handling
Evidano encrypts data and does not use customer data to train third-party models, which is relevant when researchers work with patient or clinician interviews.
Researchers should still follow their institutional ethics approvals, consent requirements, access controls, and applicable health-data regulations. AI analysis is non-diagnostic and should be used for research synthesis, not clinical decision-making.
FAQ: AI Qualitative Analysis for PROMIS Research
What is AI qualitative analysis in physical therapy research?
+
AI qualitative analysis uses artificial intelligence to organize, code, compare, and synthesize qualitative data such as interviews and open-ended survey responses.
In PROMIS implementation research, AI can help identify themes about questionnaire burden, usability, score interpretation, and workflow integration, while researchers remain responsible for methodological decisions and final interpretations.
What did the 2026 PROMIS physical therapy study find?
+
The 2026 PLOS One study found that PROMIS CATs were generally feasible, acceptable, and clinically useful in primary care physical therapy, but implementation remained limited.
The study included 25 surveyed physical therapists, interviews with 10 therapists and 9 patients, and practices across 14 locations. Reported barriers included legacy PROM duplication, online portal difficulties, and uncertainty about interpreting CAT scores.
How can AI help analyze PROMIS interview transcripts?
+
AI can help researchers retrieve relevant excerpts, group related codes, compare patient and therapist segments, and connect qualitative themes to survey findings.
Researchers should validate AI-generated codes against the transcripts, document analytical decisions, and preserve contradictory or divergent evidence.
Can AI replace human thematic analysis for healthcare research?
+
AI should support rather than replace human thematic analysis in healthcare research.
The PROMIS study used independent coding, consensus meetings, a disagreement log, and peer debriefing, demonstrating the value of structured human oversight. AI can accelerate these activities, but it cannot independently establish whether a theme is clinically meaningful or appropriate for the study context.
What privacy issues matter when using AI on patient interviews?
+
Researchers should use AI tools with strong security controls, clear data-use policies, and support for sensitive research data.
The PROMIS authors did not publicly share interview data because the patient information could not be completely anonymized. Researchers should obtain ethics approval, minimize identifiable information, and confirm that their analysis platform does not use research data to train unrelated third-party models.
Conclusion and Next Steps for AI Qualitative Analysis
The November 13, 2026 PLOS One study shows that PROMIS CATs can be feasible and useful in physical therapy, but successful implementation depends on workflow fit, understandable feedback, training, and reduced duplication.
AI qualitative analysis can make this type of mixed-methods research more manageable by organizing transcripts, comparing patient and therapist perspectives, and linking themes to concrete survey findings.
Researchers should use AI for speed and discovery while retaining human oversight, source traceability, privacy controls, and transparent coding decisions. Try Evidano for free to analyze qualitative research data with AI-assisted thematic and cross-segment workflows.
Topics
- AI qualitative analysis
- PROMIS qualitative research
- thematic analysis physical therapy
- patient-reported outcomes research
- AI analysis of interview transcripts
Keep reading
- Commentary on NewsAI Qualitative Analysis for Mixed-Methods ResearchSee how AI qualitative analysis turns mixed-methods evidence into traceable themes, comparisons, and decisions for education and health researchers.
- Commentary on NewsPROMIS CATs: AI Qualitative Analysis of Patient InterviewsLearn how AI qualitative analysis clarifies PROMIS CAT feasibility, patient burden, and implementation barriers, with practical lessons for health researchers.
- Commentary on News31 Determinants: Qualitative Analysis of SEN ResearchSee how AI qualitative analysis clarifies SEN implementation research, from 31 determinants to eight strategies, and turn workshop data into usable insights.