Artificial intelligence in diagnosis of maxillary sinusitis: A clinical study

Area of Science:

• Radiology
• Artificial Intelligence in Medicine
• Medical Imaging Analysis

Background:

• Maxillary sinusitis is a prevalent inflammatory condition affecting the sinuses.
• Diagnosis often relies on imaging techniques like cone-beam computed tomography (CBCT).
• Interpreting CBCT scans for sinusitis can be challenging, necessitating advanced diagnostic tools.

Purpose of the Study:

• To evaluate the diagnostic performance of an artificial intelligence (AI) model for maxillary sinusitis detection.
• To assess the reliability of AI in analyzing CBCT scans for this condition.
• To determine if AI can enhance the efficiency and consistency of clinical imaging interpretation.

Main Methods:

• A prospective clinical study involved 200 patients with suspected maxillary sinusitis.
• Cone-beam computed tomography (CBCT) scans were acquired for all participants.
• An AI model was developed and tested for its ability to diagnose maxillary sinusitis on these scans.

Main Results:

• The AI model achieved high diagnostic accuracy (90.4%), with excellent sensitivity (89.1%) and specificity (91.7%).
• Positive predictive value was 92.5% and negative predictive value was 87.8%.
• The area under the ROC curve was 0.948, signifying strong diagnostic discrimination.

Conclusions:

• AI demonstrates significant reliability in diagnosing maxillary sinusitis from CBCT images.
• AI can serve as a valuable adjunct tool for clinicians in interpreting sinus imaging.
• The integration of AI may lead to improved diagnostic efficiency and consistency in clinical practice.