Automatic evaluation of Nail Psoriasis Severity Index using deep learning algorithm

Abstract

Nail psoriasis is a chronic condition characterized by nail dystrophy affecting the nail matrix and bed. The severity of nail psoriasis is commonly assessed using the Nail Psoriasis Severity Index (NAPSI), which evaluates the characteristics and extent of nail involvement. Although the NAPSI is numeric, reproducible, and simple, the assessment process is time-consuming and often challenging to use in real-world clinical settings. To overcome the time-consuming nature of NAPSI assessment, we aimed to develop a deep learning algorithm that can rapidly and reliably evaluate NAPSI, thereby providing numerous clinical and research advantages. We developed a dataset consisting of 7054 single fingernail images cropped from images of the dorsum of the hands of 634 patients with psoriasis. We annotated the eight features of the NAPSI in a single nail using bounding boxes and trained the YOLOv7-based deep learning algorithm using this annotation. The performance of the deep learning algorithm (DLA) was evaluated by comparing the NAPSI estimated using the DLA with the ground truth of the test dataset. The NAPSI evaluated using the DLA differed by 2 points from the ground truth in 98.6% of the images. The accuracy and mean absolute error of the model were 67.6% and 0.449, respectively. The intraclass correlation coefficient was 0.876, indicating good agreement. Our results showed that the DLA can rapidly and accurately evaluate the NAPSI. The rapid and accurate NAPSI assessment by the DLA is not only applicable in clinical settings, but also provides research advantages by enabling rapid NAPSI evaluations of previously collected nail images.