Prospective, comparative evaluation of a deep neural network and dermoscopy in the diagnosis of onychomycosis

Abstract

Background Onychomycosis is the most common nail disorder and is associated with diagnostic challenges. Emerging non-invasive, real-time techniques such as dermoscopy and deep convolutional neural networks have been proposed for the diagnosis of this condition. However, comparative studies of the two tools in the diagnosis of onychomycosis have not previously been conducted. Objectives This study evaluated the diagnostic abilities of a deep neural network (http://nail. modelderm.com) and dermoscopic examination in patients with onychomycosis. Methods A prospective observational study was performed in patients presenting with dystrophic features in the toenails. Clinical photographs were taken by research assistants, and the ground truth was determined either by direct microscopy using the potassium hydroxide test or by fungal culture. Five board-certified dermatologists determined a diagnosis of onychomycosis using the clinical photographs. The diagnosis was also made using the algorithm and dermoscopic examination. Results A total of 90 patients (mean age, 55.3; male, 43.3%) assessed between September 2018 and July 2019 were included in the analysis. The detection of onychomycosis using the algorithm (AUC, 0.751; 95% CI, 0.646-0.856) and that by dermoscopy (AUC, 0.755; 95% CI, 0.654-0.855) were seen to be comparable (Delong's test; P = 0.952). The sensitivity and specificity of the algorithm at the operating point were 70.2% and 72.7%, respectively. The sensitivity and specificity of diagnosis by the five dermatologists were 73.0% and 49.7%, respectively. The Youden index of the algorithm (0.429) was also comparable to that of the dermatologists' diagnosis (0.230±0.176; Wilcoxon rank-sum test; P = 0.667).

Nondermatophyte mould onychomycosis

“…4,60 Histology of nail clippings using PAS staining has shown high sensitivity, roughly 88%. 61,62 However, this technique does not provide information on the nature or the viability of the causative organism. 4 New diagnostic methods such as molecular biology techniques are being used more frequently.…”

“…72,73,78 Dermoscopy or nail plate videodermoscopy provides a quick, simple, differential diagnostic tool that can increase accuracy in diagnosing onychomycosis. 62,71,79 Additionally, it is possible to use dermoscopy to identify the ideal location to obtain samples for subsequent mycological examination. 74,77 Gupta et al identified 6 major criteria used to diagnose exclusive NDM onychomycosis: (i) direct microscopy using potassium hydroxide (KOH) preparation, (ii) isolation of mould in culture, (iii) repeated isolation in culture, (iv) inoculum counting, (v) dermatophyte exclusion in culture, i.e.…”

“…Histology is an alternative method which uses periodic acid‐Schiff stain (PAS) or haematoxylin and eosin (H&E) staining to visualize the fungal elements 4,60 . Histology of nail clippings using PAS staining has shown high sensitivity, roughly 88% 61,62 . However, this technique does not provide information on the nature or the viability of the causative organism 4 …”

Diagnosis of Onychomycosis: From Conventional Techniques and Dermoscopy to Artificial Intelligence

“…More recently, the group reported that the deep neural network at operating point achieved 70.2% sensitivity, 72.7% specificity and AUC of 0.75 in diagnosing onychomycosis in a prospective cohort of 90 patients (62). This was comparable to the performance of dermoscopy (sensitivity 72.7%, specificity 72.9%, AUC 0.755; p = 0.952) and experienced dermatologists (mean Youden index 0.230 ± 0.176; p = 0.667).…”

Deep Learning for Diagnostic Binary Classification of Multiple-Lesion Skin Diseases

“…Recently Wu et al did show an impressive 95% overall diagnostic accuracy in classifying atopic dermatitis, eczema and psoriasis on selected image material (13). Studies comparing the accuracy of CAD models to clinicians are generally based on image classification equivalent to retrospective analysis, though some head to head studies were conducted with prospective collected image material (12,14,15).…”