Mobile app helps detect skin cancer in elderly patients
It’s no secret that the elderly and those living in assisted care facilities have had to exercise extra caution in the age of COVID-19. But by protecting themselves against the virus, through isolation and fewer in-person interactions, they could inadvertently increase another risk: skin cancer.
A new Stanford Medicine A study showed that strict protocols aimed at reducing potential exposure of the elderly led to a significant decrease in preventive cancer screenings.
Kavita Sarin, MD, PhD, associate professor of dermatology at Stanford Medicine, and colleagues have seen this decrease in their elderly patients first-hand at Stanford dermatology clinics. In fact, visits by this population decreased by 37% in 2020 compared to 2019, and the number of skin cancer diagnoses among seniors decreased by 23% over the same period.
The decrease was not due to a drop in the number of skin cancers among this population, but rather a drop in clinic visits for fear of contracting COVID-19. That’s a problem, Sarin said, because data has shown that older patients are most at risk of developing skin cancer.
So to help their elderly patients get the care they needed, Sarin and her team sat down to find options. “This study was born out of a clinical responsibility to our patients,” Sarin said.
They turned to the SkinIO mobile app, which allows everyday people and clinicians to capture high-quality photos of potentially cancerous lesions without visiting a clinic. The images are then delivered, via a secure portal, to a dermatologist for review.
Implementing machine learning
From November 2020 to July 2021, the team conducted a pilot study to test the effectiveness of the app with 27 residents of a retirement community living in the San Francisco Bay Area. The study was published June 27 at Health and skin diseases.
Sarin’s team knew from the start that many elderly patients might need a hand using the app to get quality images. SkinIO experts and a step-by-step guide on how to take the photos helped train clinical research coordinators to use the app on a tablet.
After extensive COVID-19 precautions, staff visited the retirement community and collected full-body images from patients.
The app uses machine learning to analyze photos, look for skin lesions or abnormalities, and flag any that looked suspicious. It is not a diagnostic tool, however, and is only intended to capture images and monitor a patient’s skin. “The software just says, ‘Hey, this might need further investigation,'” Sarin said. Doctors then make the diagnosis.
Using the app, the research coordinators shared the photos with Sarin, who reviewed them and flagged any images with lesions that appeared cancerous.
Sarin then instructed the research coordinators who were with the patient to take additional pictures of the suspicious lesions using a dermatoscope, an imaging device that takes detailed pictures of the outer layer of skin that does not is not visible to the naked eye. This tool often helps dermatologists diagnose skin diseases, such as melanoma. These more detailed images allowed Sarin to accurately diagnose the lesions.
Then the research coordinators held a virtual visit for all Sarin patients to review the results. Sarin then scheduled an in-person visit to the patient for further examination, recommended home treatment, or gave the patient a clean bill of health.
Of the lesions observed, the app reported that 63% required further investigation. The majority of these lesions ended up being benign.
“The lesion detection algorithm isn’t perfect, and there were a few issues with lesion detection, but for a triage situation it’s a good tool,” Sarin said.
Of the 27 people who took part in the study, the app and Sarin identified skin cancer in three of them. Eleven patients were scheduled for an in-person follow-up visit and four started treatment at home. Some of the skin cancers were lesions the patient hadn’t noticed before, meaning that without the app’s full body images, they might have been missed, Sarin said.
Help more patients
Fortunately, access to COVID-19 vaccines and boosters has made in-person dermatology visits safer for older patients. But the pandemic is far from over and barriers to care still exist for some patients, including those who are immobile or whose health is compromised, Sarin said.
“In some cases, skilled nursing facilities have to send patients to the clinic using an ambulance, which can be time-consuming and expensive,” she said. “If we could send our staff to take pictures of these patients, that could be extremely helpful for these patients and a great application of this system.”
In the future, Sarin and the research team are discussing the possibility of teaching elderly patients how to take their own photos, which would significantly reduce the time spent training and sending clinical staff.
It could also help dermatology teams spread the app more widely to patients who live alone or aren’t in a facility with a trained person who can help capture the images. Using the app could also to help patients save money because randomized trials have shown that dermatology televisits are very profitable.
“We must continue to think about how best to serve our most vulnerable patients during this difficult time,” Sarin said.