Mendeley  

Zotero  

Shafizad M, Ehteshami S, Sobhanian P, Hosseinzade M. Artificial Intelligence for Improved Diagnosis of Spinal Stenosis: Implications for Neurosurgical Practice. Iran J Neurosurg 2025; 11 : 5
URL: http://irjns.org/article-1-461-en.html

Background and Aim: Spinal stenosis is a common condition in the elderly and is characterized by the narrowing of the spinal canal, leading to significant neurological symptoms. Traditional imaging methods, such as magnetic resonance imaging (MRI) and computed tomography (CT), have limitations, including interpretation and time consumption variability. Integrating artificial intelligence (AI), particularly deep-learning algorithms, into MRI analysis shows promise for enhancing diagnostic accuracy and efficiency. This narrative review aims to explore AI’s application in diagnosing spinal stenosis and its implications for treatment planning and patient outcomes in neurosurgery practice.

Methods and Materials/Patients: A literature search was conducted using Google Scholar, MEDLINE, and PubMed to identify original studies on AI in diagnosing lumbar and cervical spinal stenosis. Relevant studies were included after screening. Data extraction was performed using a structured spreadsheet, and findings were analyzed thematically to identify trends in AI applications for diagnostic accuracy.
Results: Integrating AI into the diagnostic process for lumbar and cervical spinal stenosis has significantly improved accuracy and efficiency. By employing advanced deep learning (DL) algorithms, particularly convolutional neural networks (CNNs), AI systems can analyze imaging data more effectively and identify subtle patterns indicative of stenosis that human clinicians may overlook. This capability enhances diagnostic precision and facilitates earlier interventions, ultimately improving patient outcomes. As research continues to advance in this field, the role of AI is expected to expand, further transforming the landscape of spinal stenosis diagnoses.
Conclusion: AI has shown significant promise in enhancing the diagnosis of cervical and lumbar spinal stenosis. By utilizing deep-learning algorithms, AI can analyze imaging data more accurately and efficiently, identifying subtle patterns indicative of stenosis that human observers may miss. This can ultimately facilitate earlier interventions and improve patient outcomes.