Artificial Intelligence in the Evaluation of Telemedicine Dermatology Patients

February 2022 | Volume 21 | Issue 2 | Original Article | 191 | Copyright © February 2022


Published online January 24, 2022

doi:10.36849/JDD.6277

Mandy Majidian BA,a,b Izhaar Tejani BA,c Tory Jarmain BA,c Lisa Kellett MD,c Ronald L. Moy MDb

aTulane University School of Medicine, New Orleans, LA
bMoy-Fincher-Chipps Facial Plastics & Dermatology, Beverly Hills, CA
cTriage Technologies Inc, Toronto, Canada

Abstract
Background: Background: Early detection of malignant skin lesions reduces morbidity. There is increased need for a telemedicine triage tool to prioritize patients who require in-person evaluation for potential malignancy.
Objective: To evaluate the utility of artificial intelligence (AI) in telemedicine triage and diagnosis of cutaneous lesions.
Methods: Clinical photographs of unbiopsied skin lesions were presented to AI software and three board-certified dermatologists with 18 years average clinical experience. Diagnoses were compared with biopsy reports of the same lesions.
Results: Results from 100 images revealed no significant diagnostic difference between AI and a panel of three dermatologists when using the AI top three differential diagnoses. The AI correctly identified 63% of the cases whereas the dermatology group correctly identified 64.3% of the cases (P<.05). In summary, there was no statistically significant difference when evaluating lesions.
Conclusion: The use of artificial intelligence as a method of triaging patients with potential skin cancer is a very useful option in telemedicine, as AI identification of BCC, SCC, and melanoma did not significantly differ from board-certified dermatologists. Both dermatologists and non-dermatologists will benefit from an AI triage system, prioritizing lesions that the software deems malignant.

J Drugs Dermatol. 2022;21(2):191-194. doi:10.36849/JDD.6277

INTRODUCTION

For many patients, in-person access to a consultation with a board-certified dermatologist in a timely fashion can be difficult. With the advent of a global pandemic by the novel infection caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), this access has been made even more challenging. Furthermore, the practice of telemedicine in dermatology has simultaneously increased in order to decrease in-person visits. It is estimated that during the pandemic in 2020, 30% of all patient visits were conducted via telemedicine in the United States, increasing from pre-pandemic rates by 23 times.1 Recently, Triage Snap, an online tool powered by TriageNet was developed. TriageNet is a proprietary artificial intelligence (AI) algorithm that uses computer vision and machine learning (ML) to review and generate a differential diagnosis given skin image data.2

Based on the prevalence and incidence of skin cancer, early detection and treatment is of critical clinical importance. When treated expeditiously, skin cancer treatment has a 99% success rate. However, morbidity can result from neglected lesions, with delays to diagnosis significantly increasing the morbidity rate. In 2017, the American Academy of Dermatology (AAD) determined that patients with Stage 1 malignant melanoma who were treated 4 months after being biopsied had a 41% increased risk of death compared with those treated within the first month.3 Early-stage malignant melanomas are well established as being associated with reduced mortality relative to later-stage malignant melanomas.4

The initial step in the process of having a potentially malignant skin lesion evaluated as potentially cancerous is a visit to a board-certified dermatologist. However, a 2019 report from the Greater Access for Patients Partnership (GAPP) found that long wait times for dermatology appointments were standard. Furthermore, this placed patients at increased risk of disease progression and morbidity.5 A 2017 Merritt Hawkins Survey found the average wait time for a dermatology appointment is 32.3 days, a 46% increase from 22.1 days in 2009.6 In the GAPP report, 4 in 10 patients (40%) reported waiting between one and six months for their initial dermatology appointment, and an average of six weeks for a follow-up appointment. Appointment wait time also varies by location, with patients living in rural areas experiencing longer wait times than those living in urban or suburban areas. There is also a wide geographical variation.

Another impediment to expedient dermatology consultations is that many health insurance plans require a referral from a primary care physician. For that reason, most skin lesions are evaluated by a non-dermatologist – most often a primary care or internal medicine physician. The national average wait time for an appointment in primary care is 29.3 days. Coupled with the subsequent average 32.3-day wait time for a dermatologist appointment, an individual who suspects a malignant skin