Citation: Richarz NA, Boada A, Jaka A, et al. UV Irradiation of Nevi: Impact on Performance of Electrical Impedance Spectroscopy and a Convolution Neural Network. Dermatol Pract Concept. 2022;12(4):e2022162. DOI: https://doi.org/10.5826/dpc.1204a162 Accepted: February 9, 2022; Published: October 2022 Copyright: ©2022 Richarz et al. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial License (BY-NC-4.0), https://creativecommons.org/licenses/by-nc/4.0/, which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original authors and source are credited. Funding: None. Competing interests: None. Authorship: All authors have contributed significantly to this publication. Corresponding author: Nina A. Richarz, MD, Department of Dermatology University Hospital Germans Trias i Pujol. Address: Carretera de Canyet s/n, 08916 Badalona, Barcelona, Spain. Phone: +34 934651200 E-mail: richarznina@gmail.com Introduction: In vivo reflectance confocal microscopy (RCM) is a useful tool for assessing pre-surgical skin tumor margins when performed by a skilled, experienced user. The technique, however, poses significant challenges to novice users, particularly when a handheld RCM (HRCM) device is used. Objective: To evaluate the performance of an HRCM device operated by a novice user to delineate basal cell carcinoma (BCC) margins before Mohs micrographic surgery (MMS) Methods: We performed a prospective study of 17 consecutive patients with a BCC in a high-risk facial area (the H zone) in whom tumor margins were assessed by HRCM and dermoscopy before MMS. Predicted surgical defect areas (cm2) were calculated using standardized photographic digital documentation and compared to final defect areas after staged excision. Results: No significant differences were observed between median HRCM-predicted and observed surgical defect areas (2.95 cm2 [range: 0.83–17.52] vs 2.52 cm2 [range 0.71–14.42]; p=0.586). Dermoscopy, by contrast, produced significantly underestimated values (median area of 1.34 cm2 [0.41-4.64] vs 2.52 cm2 [range 0.71-14.42]; p<0.001). Confounders leading to poor agreement between predicted and observed areas were previous treatment (n=5), a purely infiltrative subtype (n=1), and abundant sebaceous hyperplasia (n=1). Conclusion: Even in the hands of a novice user, HRCM is more accurate than dermoscopy for delineating lateral BCCs margins in high-risk areas and performs well at predicting final surgical defects. Keywords : reflectance confocal microscopy, basal cell carcinoma, micrographic Mohs surgery, margin control This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.