EUVIMEDEUVIMED entdecken
Crossref

Limitations of Parameter-Based AI Models in the MRI Evaluation of Lumbar Spinal Stenosis: A Clinical Perspective

Bilal Ertuğrul

Balkan Journal of Electrical and Computer Engineering · 28.07.2026 · 14

DOI: 10.17694/bajece.1933652 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Balkan Journal of Electrical and Computer Engineering, online erschienen am 28.07.2026. Verfasst von Bilal Ertuğrul. Die Arbeit nennt 17 Literaturangaben. Gefördert von: No specific funding was received for this study..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AbstractBackground: Lumbar spinal stenosis (LSS) is a prevalent degenerative spinal disorder in neurosurgical practice, where magnetic resonance imaging (MRI) plays a central role in diagnosis and surgical planning. In recent years, artificial intelligence (AI), particularly deep learning–based models, has shown promising results in automated MRI analysis, including stenosis grading and segmentation. However, most existing AI systems rely heavily on predefined quantitative parameters, raising concerns regarding their clinical applicability.

Objective

This study aims to critically evaluate the limitations of parameter-based AI models in the MRI assessment of LSS and to propose a conceptual framework for clinically aligned, explainable hybrid AI approaches.

Methods

A narrative and conceptual analysis was conducted based on current literature and clinical experience. The limitations of parameter-based AI models were examined in terms of standardization, clinical decision-making complexity, clinicoradiological mismatch, multilevel disease evaluation, imposed parameterization, and labeling variability.

Results

Parameter-based AI models demonstrate important limitations in reflecting real-world clinical decision-making. The lack of standardized thresholds, inability to integrate multidimensional clinical factors, and challenges in identifying symptomatic levels in multilevel disease reduce their clinical utility. Additionally, interobserver variability in labeling introduces noise that negatively affects model performance and generalizability.

Conclusion

While parameter-based AI models contribute to the quantitative evaluation of LSS, they remain insufficient for comprehensive clinical decision support. Explainable hybrid AI approaches that integrate imaging data with clinical variables and structured knowledge representations may offer a more reliable and clinically meaningful framework for future applications.

Förderung

  • No specific funding was received for this study.

Zitieren

APA

Ertuğrul, B. (2026). Limitations of Parameter-Based AI Models in the MRI Evaluation of Lumbar Spinal Stenosis: A Clinical Perspective. Balkan Journal of Electrical and Computer Engineering, 14. https://doi.org/10.17694/bajece.1933652

Vancouver

Ertuğrul B. Limitations of Parameter-Based AI Models in the MRI Evaluation of Lumbar Spinal Stenosis: A Clinical Perspective. Balkan Journal of Electrical and Computer Engineering. 2026;14. doi:10.17694/bajece.1933652

BibTeX
@article{Erturul2026,
  author = {Ertuğrul, Bilal},
  title = {Limitations of Parameter-Based AI Models in the MRI Evaluation of Lumbar Spinal Stenosis: A Clinical Perspective},
  journal = {Balkan Journal of Electrical and Computer Engineering},
  year = {2026},
  volume = {14},
  doi = {10.17694/bajece.1933652}
}
Kostenlos starten →