Physical therapists' perspectives on a large language model-powered knowledge translation tool for guideline adherence: A qualitative focus group study.
Clinical Snapshot
PICO Framework
| P — Population | German physical therapists working in inpatient (university hospital) and outpatient settings |
| I — Intervention | A prototype digital knowledge translation tool powered by a large language model (LLM), with content derived from two exemplary high-quality German national clinical practice guidelines |
| C — Comparator | No formal comparator; comparative element is between inpatient versus outpatient physical therapist perspectives on the tool |
| O — Outcomes | Therapists' experiences using the tool, perceived utility in clinical practice, barriers and facilitators to implementation, and differences in anticipated use across care settings |
Bottom Line
This qualitative focus group study explores German physical therapists' perspectives on a prototype LLM-powered knowledge translation tool designed to improve clinical guideline adherence. Twenty participants across inpatient and outpatient settings reported broadly positive experiences, with response speed identified as the primary usability concern. A clinically meaningful finding is the setting-specific anticipated use pattern: inpatient therapists envisioned between-session use for self-directed learning, while outpatient therapists anticipated in-session use for patient education — with implications for how such tools should be designed and deployed. The study is methodologically sound in its design and analytical approach, but is limited by a small, potentially self-selected sample, absence of reflexivity reporting, undescribed sampling strategy, and unconfirmed ethical governance. Researcher allegiance bias is a meaningful concern given institutional overlap between tool developers and investigators. Findings are exploratory and hypothesis-generating rather than confirmatory. For Australian clinicians and health service managers, the study's core message is relevant: LLM-assisted guideline tools hold genuine promise for allied health knowledge translation, but successful implementation requires investment in digital infrastructure, attention to workflow integration, and rigorous evaluation of LLM output quality and safety before clinical deployment.
Key Findings
P Value: Not applicable — qualitative study
Effect Size: Not applicable — qualitative study; no quantitative effect sizes reported
Primary Outcome: Overall experiences with the LLM-powered knowledge translation tool were positive among both inpatient and outpatient physical therapists. Prolonged response times were the primary criticism. Utilisation was anticipated to depend on time availability and workplace digitisation levels.
Nnt Or Sensitivity: Not applicable — qualitative study. Key qualitative finding: inpatient therapists envisioned between-session use for personal knowledge enhancement; outpatient therapists anticipated in-session use for patient education — a clinically meaningful distinction for implementation planning
Confidence Interval: Not applicable — qualitative study
Clinical Application
Feasibility is contingent on digital infrastructure availability, adequate response speed of the LLM system, and users' baseline digital literacy. The study identifies these as key implementation prerequisites. Time constraints in clinical workflows — particularly in outpatient settings — are a practical barrier that must be addressed in tool design and deployment planning. In Australia, physiotherapy guideline adherence is a recognised priority for the Australian Physiotherapy Association (APA) and RACGP-adjacent allied health quality frameworks. The NDIS, hospital-based physiotherapy services, and private outpatient practices represent analogous inpatient/outpatient dichotomies to those studied. The TGA's evolving regulatory framework for Software as a Medical Device (SaMD) would apply to any LLM-based clinical decision support tool deployed in Australia. Digital health infrastructure disparities between metropolitan and rural/remote settings are particularly relevant in the Australian context. The Australian Digital Health Agency's national digital health strategy and My Health Record ecosystem provide a policy backdrop for considering LLM tool integration. PBS considerations are not directly applicable, but Medicare-funded physiotherapy services (e.g., Chronic Disease Management plans) would be a relevant implementation context. Physical therapists and allied health professionals working in both inpatient and outpatient settings who engage with clinical practice guidelines; potentially extensible to other allied health disciplines considering LLM-assisted clinical decision support
Abstract
BACKGROUND: Clinical practice guidelines support healthcare professionals in making evidence-based decisions, yet guideline adherence among physical therapists remains inconsistent. To address this gap, a prototype digital knowledge translation tool powered by a large language model (LLM) was developed, with content based on two exemplary high-quality German national guidelines. OBJECTIVE: To (1) explore the experiences of German physical therapists using the tool, (2) assess their perspectives on its utilization in clinical practice, and (3) compare perceptions between outpatient and inpatient settings. METHODS: Six focus group interviews were conducted: three in a university hospital inpatient setting and three in outpatient physical therapy practices. Discussions were analyzed using qualitative content analysis with inductive and deductive coding. RESULTS: Twenty physical therapists (11 inpatient, 9 outpatient) participated. Overall experiences were positive, though prolonged response times were criticized. Utilization was thought to depend on time availability and workplace digitization. The tool's potential assisting with clinical questions was highlighted. No considerable differences in experiences across settings were noted. Inpatient therapists envisioned using the tool between sessions for personal knowledge enhancement, whereas outpatient therapists anticipated utilization during sessions for patient education. CONCLUSION: LLM-based knowledge translation tools may contribute to improving guideline adherence among physical therapists. Successful implementation requires assessment of digital infrastructure, relevance to clinical needs, and users' digital literacy. Further research should evaluate the quality of LLM-generated summaries to ensure validity and trustworthiness, and optimize the tools' usability regarding speed and content. Development should also prompt ethical considerations about their role in clinical decision-making and patient care.
References
- 1.Rosen, D., Zwanzig, D., Vogel, B., Erhart, M., & Reiter, N. L. (2025). Physical therapists' perspectives on a large language model-powered knowledge translation tool for guideline adherence: A qualitative focus group study. Physiotherapy Theory and Practice. Advance online publication. https://doi.org/10.1080/09593985.2025.2606058
Related Research
The Knee
Artificial intelligence in the management of sports knee injuries: a narrative review.
3 Aug 2026
Archives of orthopaedic and trauma surgery
Shoulder injuries in rugby union: a systematic review and meta-analysis
31 July 2026
JMIR mHealth and uHealth
Perceptions of Adults Aged 50 Years and Older Regarding the Use of Wearable mHealth Technologies to Promote Physical Activity: Systematic Review and Meta-Ethnography
30 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service