Evaluation of the Accuracy of Infrared Thermographic Imaging for the Diagnosis of Periodontal Diseases: A Cross-Sectional Study

Abstract

Aim: To evaluate the diagnostic accuracy of thermographic imaging for differentiating healthy gingiva, site-level inflammation and sites with clinical attachment loss. Subjects and Methods: A calibrated periodontist examined 511 teeth in systemically healthy individuals attending the periodontology clinic. Clinical assessments were performed at buccal/facial sites within the anterior and premolar regions, with parameters including bleeding on probing (BOP), plaque index (PI), gingival index (GI), probing depth (PD) and clinical attachment level (CAL). Each tooth was classified into one of three subgroups based on CAL and BOP: clinically healthy sites (Group1/CH); inflamed sites without attachment loss (Group2/INF); and sites with clinical attachment loss (Group3/AL). Thermal imaging of the same sites was performed by a blinded operator. Diagnostic performance was assessed using receiver operating characteristic (ROC) curves as well as sensitivity and specificity analyses. Results: The mean temperature values were 37.8°C ± 1.6°C for Group2/INF, 38.7°C ± 1.2°C for Group3/AL and 34.8°C ± 2.4°C for Group1/CH (p < 0.001). ROC analysis resulted in an area under the curve (AUC) of 0.94 for Group2/INF and 0.86 for Group3/AL, high sensitivity (93% and 90.7%) and moderate to high specificity (83.8% and 64.5%), respectively, with significant correlations between thermal values, PI and CAL (p < 0.001). Conclusions: Thermographic imaging could effectively differentiate between clinically healthy sites and those showing site-specific inflammation or attachment loss. These findings reflect periodontal status at the site level and are not intended for full-mouth diagnosis of gingivitis or periodontitis. Trial Registration: The trial was registered at https://clinicaltrials.gov/ under the number (NCT06290414) on 14/8/2024.