Skin Surface Temperatures Measured by Thermal Imaging Aid in the Diagnosis of Cellulitis

Warmth is a characteristic but nondiagnostic feature of cellulitis. We assessed the diagnostic utility of skin surface temperature in differentiating cellulitis from pseudocellulitis. Adult patients presenting to the emergency department of a large urban hospital with presumed cellulitis were enrolled. Patients were randomized to dermatology consultation (n = 40) versus standard of care (n = 32). Thermal images of affected and unaffected skin were obtained for each patient. Analysis was performed on dermatology consultation patients to establish a predictive model for cellulitis, which was then validated in the other cohort. Of those evaluated by dermatology consultation, pseudocellulitis was diagnosed in 28%. Cellulitis patients had an average maximum affected skin temperature of 34.1°C, which was 3.7°C warmer than the corresponding unaffected area (95% confidence interval = 2.7-4.8°C, P < 0.00001). Pseudocellulitis patients had an average maximum affected temperature of 31.5°C, which was 0.2°C warmer than the corresponding unaffected area (95% confidence interval = -1.1 to 1.5°C, P = 0.44). Temperature differences between sites were greater in cellulitis patients than in pseudocellulitis patients (3.7 vs. 0.2°C, P = 0.002). A logistic regression model showed that a temperature difference of 0.47°C or greater conferred a 96.6% sensitivity, 45.5% specificity, 82.4% positive predictive value, and 83.3% negative predictive value for cellulitis diagnosis. When validated in the other cohort, this model gave the correct diagnosis for 100% of patients with cellulitis and 50% of those with pseudocellulitis. A difference threshold of 0.47°C or greater between affected and unaffected skin showed an 87.5% accuracy in cellulitis diagnosis.