Remote Telemedicine Tool Found Highly Accurate in Diagnosing Melanoma

Collecting images of suspicious-looking skin growths and sending them off-site for specialists to analyze is as accurate in identifying skin cancers as having a dermatologist examine them in person, a new study shows.

According to the study authors, the findings add to evidence that such technology could help to reliably address diagnostic and treatment disparities for lower-income populations with limited access to dermatologists. It may also help dermatologists quickly catch cases of melanoma, a serious form of skin cancer that kills more than 8,000 Americans a year.

Their new system, which the researchers call SpotCheck, enables skin cancer specialists to remotely examine skin lesions using an established technique called dermoscopy, in which experts use a camera connected to a specialized magnifying lens to peer beneath the skin’s surface.

While previous research has explored telemedicine options for speeding diagnoses of melanoma and compared in-person and remote evaluation of dermoscopy images, the authors say their work is among the first to target skin growths identified first by concerned patients rather than by primary care physicians. This is important, the research team says, because most cases of melanoma are initially spotted by patients or their friends and family.

Led by a team at NYU Langone Health and its Perlmutter Cancer Center, the new analysis used SpotCheck to evaluate dermoscopic images of 375 skin lesions from volunteers who were concerned that their skin blemishes might be cancerous. According to the results, which published online Nov. 9 in the Journal of the American Academy of Dermatology, dermoscopy experts who remotely reviewed all of the samples were 91% accurate in their diagnoses, based on later biopsies. Dermatologists who instead performed an evaluation of all of the volunteers in a doctor’s office had an accuracy of 93%.

"Our findings suggest that this method of teledermoscopy may not only help healthcare providers catch potentially dangerous skin cancers early, it may also reduce expensive, anxiety-causing referrals to specialists for benign lesions," said study senior author David Polsky, MD, PhD.

According to the United States Centers for Disease Control and Prevention, melanoma is the most common form of cancer in the country and is notoriously difficult to treat after tumors spread throughout the body. Past studies have shown that the disease often goes undetected in people from lower-income neighborhoods, who may have difficulty finding dermatologists in their area or may struggle to take time off work to attend appointments.

For the research, the team administered questionnaires to 147 men and women who had responded to newspaper ads after identifying suspicious lesions on their skin. The surveys assessed personal and family history of skin cancer, melanoma risk factors, and the history of each worrisome skin spot, among other factors. Then, a general dermatologist performed a physical exam using the visual appearance of the blemishes and a dermatoscope to make a diagnosis, and if needed, performed a biopsy.

Next, the study coordinator captured clinical and dermoscopic images, which were sent to a central server for remote review by a separate team of skin cancer specialists with expertise using dermoscopy. They reviewed the questionnaires and images in order to make their own diagnoses. This group of dermatologists was not made aware of the results of the in-person evaluation. The researchers also conducted a phone survey one week after the patients’ appointments to assess their satisfaction.

Among the findings, the study showed that overall, 97% of the evaluated lesions were later determined by biopsy to be benign. Notably, both the dermatologists who examined the participants in-person and those who instead relied on clinical photos and dermoscopy alone detected 11 out of the 13 cases of skin cancer, including two melanomas.

The results further revealed that nearly 90% of the patients were satisfied with the telemedicine experience, with one-fifth reporting that they preferred this method of exam over an in-person appointment with a specialist.

"A key advantage of teledermoscopy platforms is that community health workers can be trained to collect images and send them out for expert review," said Polsky, the Alfred W. Kopf, MD, Professor of Dermatologic Oncology at NYU Grossman School of Medicine. "As a result, this technology could be used in the future to offer virtual triage services in walk-in clinics, pharmacies, and community centers."

Polsky, also a professor in the Department of Pathology at NYU Grossman School of Medicine, adds that next, the research team plans to identify neighborhoods with higher rates of late-stage melanoma for possible SpotCheck deployment.

He cautions that the tool is meant to assess specific skin concerns and is not a substitute for a full-body check in a doctor’s office. The participants in the study had to limit their lesions of concern to three.

Funding for the study was provided by the Melanoma Research Alliance, the Sergei S. Zlinkoff Fund for Medical Research and Education, and the Orbuch Brand Pilot Program for Diseases of the Skin.

Ingrassia JP, Bajaj S, Kolla A, Li V, Shah P, Gulati N, Criscito MC, Xing Y, Lopez A, Tran DC, Ramachandran V, Kakpovbia E, Meehan S, Shao Y, Lo Sicco K, Milam EC, Bieber AK, Levine A, Liebman TN, Stein JA, Polsky D.
SpotCheck: A Skin Cancer Diagnostic Accuracy Study Comparing Teledermoscopy with and without Electrical Impedance Spectroscopy to In-Person Dermatologist Evaluation of Patient-Identified Lesions Concerning them for Skin Cancer.
J Am Acad Dermatol. 2024 Nov 9:S0190-9622(24)03115-3. doi: 10.1016/j.jaad.2024.10.067

Most Popular Now

AI System Helps Doctors Identify Patient…

A new study from Vanderbilt University Medical Center shows that clinical alerts driven by artificial intelligence (AI) can help doctors identify patients at risk for suicide, potentially improving prevention efforts...

Smartphone App can Help Reduce Opioid Us…

Patients with opioid use disorder can reduce their days of opioid use and stay in treatment longer when using a smartphone app as supportive therapy in combination with medication, a...

AI's New Move: Transforming Skin Ca…

Pioneering research has unveiled a powerful new tool in the fight against skin cancer, combining cutting-edge artificial intelligence (AI) with deep learning to enhance the precision of skin lesion classification...

Predicting the Progression of Autoimmune…

Autoimmune diseases, where the immune system mistakenly attacks the body's own healthy cells and tissues, often have a preclinical stage before diagnosis that’s characterized by mild symptoms or certain antibodies...

AI can Improve Ovarian Cancer Diagnoses

A new international study led by researchers at Karolinska Institutet in Sweden shows that AI-based models can outperform human experts at identifying ovarian cancer in ultrasound images. The study is...

Major EU Project to Investigate Societal…

A new €3 million EU research project led by University College Dublin (UCD) Centre for Digital Policy will explore the benefits and risks of Artificial Intelligence (AI) from a societal...

Using AI to Uncover Hospital Patients�…

Across the United States, no hospital is the same. Equipment, staffing, technical capabilities, and patient populations can all differ. So, while the profiles developed for people with common conditions may...

New AI Tool Uses Routine Blood Tests to …

Doctors around the world may soon have access to a new tool that could better predict whether individual cancer patients will benefit from immune checkpoint inhibitors - a type of...

New Method Tracks the 'Learning Cur…

Introducing Annotatability - a powerful new framework to address a major challenge in biological research by examining how artificial neural networks learn to label genomic data. Genomic datasets often contain...

Picking the Right Doctor? AI could Help

Years ago, as she sat in waiting rooms, Maytal Saar-Tsechansky began to wonder how people chose a good doctor when they had no way of knowing a doctor's track record...

From Text to Structured Information Secu…

Artificial intelligence (AI) and above all large language models (LLMs), which also form the basis for ChatGPT, are increasingly in demand in hospitals. However, patient data must always be protected...

AI Innovation Unlocks Non-Surgical Way t…

Researchers have developed an artificial intelligence (AI) model to detect the spread of metastatic brain cancer using MRI scans, offering insights into patients’ cancer without aggressive surgery. The proof-of-concept study, co-led...