EUVIMEDEUVIMED entdecken
Crossref

Cluster Analysis and Predictive Factors Influencing Physiotherapists’ Recommendations for Exercise Therapy for Musculoskeletal Pain

Annika Griefahn, Florian Avermann, Christoff Zalpour, Robert Percy Marshall

physioscience · 14.08.2026

DOI: 10.1055/a-2797-4664 ↗

Kurz gefasst

Fachartikel in der Zeitschrift physioscience, erschienen am 14.08.2026. Verfasst von Annika Griefahn und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The decision as to whether patients with musculoskeletal pain are suitable for exercise therapy is central to safe and effective physiotherapy care. Assessments by physiotherapists can provide important information about contraindications.

Objective

The study examined three research questions: (1) relationship between pain-related clusters and physiotherapeutic classification of contraindications for exercise therapy alone, (2) characteristic differences between the clusters in terms of pain-related parameters, and (3) predictive factors for the presence of a contraindication.

Method

In a retrospective secondary data analysis, data from 80 patient cases were evaluated that had been classified in a previous study by both a rule-based AI system and 20 physical therapists with regard to the presence of a contraindication for exercise therapy alone. To identify pain-related patterns, a k-means cluster analysis based on 24 pain-related variables was performed. Differences between the clusters were analyzed using ANOVA and post-hoc tests. A binary logistic regression was used to identify significant predictors for the presence of contraindication.

Results

3 clusters were identified. Significant predictors for the presence of a contraindication for exercise therapy were high pain intensity (numerical rating scale 7–10), persistent pain (especially at night), multiple pain regions, and pain descriptors such as “pressing” or “burning.” The final regression model showed high predictive power (Nagelkerke’s R² = 0.90).

Conclusion

Certain pain-related parameters can reliably predict the presence of a contraindication for exercise therapy alone. Integrating these factors into AI-supported systems has the potential to increase patient safety, avoid inappropriate therapies, and support personalized treatment decisions. Registration of primary study OSF, https://doi.org/10.17605/OSF.IO/YCNJQ, 30.12.2021

Zitieren

APA

Griefahn, A., Avermann, F., Zalpour, C., & Marshall, R. P. (2026). Cluster Analysis and Predictive Factors Influencing Physiotherapists’ Recommendations for Exercise Therapy for Musculoskeletal Pain. physioscience. https://doi.org/10.1055/a-2797-4664

Vancouver

Griefahn A, Avermann F, Zalpour C, Marshall RP. Cluster Analysis and Predictive Factors Influencing Physiotherapists’ Recommendations for Exercise Therapy for Musculoskeletal Pain. physioscience. 2026. doi:10.1055/a-2797-4664

BibTeX
@article{Griefahn2026,
  author = {Griefahn, Annika and Avermann, Florian and Zalpour, Christoff and Marshall, Robert Percy},
  title = {Cluster Analysis and Predictive Factors Influencing Physiotherapists’ Recommendations for Exercise Therapy for Musculoskeletal Pain},
  journal = {physioscience},
  year = {2026},
  doi = {10.1055/a-2797-4664}
}
Kostenlos starten →