The ALT-70 Predictive Model Outperforms Thermal Imaging for the Diagnosis of Lower Extremity Cellulitis: A Prospective Evaluation. Journal Article


Authors: Li, DG; Dewan, AK; Di Xia, F; Khosravi, H; Joyce, C; Mostaghimi, A
Article Title: The ALT-70 Predictive Model Outperforms Thermal Imaging for the Diagnosis of Lower Extremity Cellulitis: A Prospective Evaluation.
Abstract: BACKGROUND: We previously demonstrated dermatology consultation to substantially reduce cellulitis misdiagnosis rates; however, broad implementation is impractical due to existing practice patterns and reimbursement systems. Meanwhile, efforts to improve diagnostic accuracy have culminated in point-of-care tools, including the ALT-70 predictive model for lower extremity cellulitis and thermal imaging. OBJECTIVE: To prospectively evaluate the performance of ALT-70 and thermal imaging in diagnosing lower extremity cellulitis in a head-to-head comparison. METHODS: We collected ALT-70 and thermal imaging data from patients with presumed lower extremity cellulitis and compared classification measures and accuracy for ALT-70, thermal imaging, and combination testing (ALT-70 plus thermal imaging). RESULTS: We enrolled 67 patients with ALT-70 and thermal imaging data. ALT-70 conferred the highest sensitivity (97.8%) and negative predictive value (90.9%), while combination testing had the highest specificity (71.4%) and positive predictive value (86.6%). ALT-70 had improved classification measures compared to thermal imaging. Combination testing conferred a marginal benefit to ALT-70 alone. LIMITATIONS: Single-center design may limit generalizability. CONCLUSION: ALT-70 outperformed thermal imaging in diagnosing lower extremity cellulitis. The accuracy of the ALT-70 was high and consistent with previously published reports. Broad implementation of ALT-70 into clinical practice may decrease misdiagnosis rates of lower extremity cellulitis.
Journal Title: Journal of the American Academy of Dermatology
ISSN: 1097-6787; 0190-9622
Publisher: Mosby, Inc  
Date Published: 2018