FDA Authorizes Use of AI-Powered Medical Device to Detect the Most Common Skin Cancers


The Food and Drug Administration (FDA) has authorized the first-of-its-kind non-invasive artificial intelligence-powered medical device to detect three of the most common skin cancers in real time.

The FDA said on Jan. 16 that it had cleared the DermaSensor Inc. device, made by the Miami-based company of the same name, to be used by physicians on patients aged 40 and over.

According to DermaSensor Inc., the wireless, handheld device uses spectroscopy (the absorption and emission of light and other radiation by matter) and FDA-cleared algorithms to evaluate cellular and subcellular characteristics of a skin lesion to identify potential cancer cells in seconds.

Typically, skin cancer is identified through a procedure known as dermatoscopy, in which a medical professional examines the skin for signs of cancer using a specialized magnifying glass or through a visual examination.

The DermaSensor Inc. device can detect all three of the most common types of skin cancer—basal cell carcinoma, squamous cell carcinoma, and melanoma, which is the most deadly form of skin cancer—allowing health care providers to determine whether or not to refer a patient to a dermatologist, according to the company.

One in five Americans will have had some type of skin cancer by the age of 70 and more than two people die of skin cancer in the United States every hour, according to The Skin Cancer Foundation.

Related Stories

Legislators Race to Protect Minors From AI Deepfake Exploitation
British Standards Institution Publishes 1st Guide on How to Manage AI Safely
However, 99 percent of skin cancers, including melanoma, are curable if detected early.

‘Golden Age of Predictive, Generative AI’

DermaSensor Inc. co-founder and CEO Cody Simmons told media that due to technological advances, the healthcare industry is now entering the “golden age” of predictive and generative artificial intelligence (AI), noting that these capabilities “are being paired with novel types of technology, like spectroscopy and genetic sequencing, to optimize disease detection and care.”

Equipping primary care physicians to better evaluate the most common cancer in the country has been a “major, long-standing unmet need in medicine,” he said.

“While dozens of companies have attempted to address this problem in recent decades, we are honored to be the first device cleared by the FDA that provides PCPs with an automated tool for evaluation of suspicious lesions,” Mr. Simmons added.

According to the FDA, the DermaSensor Inc. device should be used “in conjunction with the totality of clinically relevant information from the clinical assessment, including visual analysis of the lesion, by physicians who are not dermatologists.”

It should also be used on lesions “already assessed as suspicious for skin cancer and not as a screening tool.”

“The device should not be used as the sole diagnostic criterion nor to confirm a diagnosis of skin cancer,” the FDA said.

The agency is also requiring that DermaSensor Inc. conduct additional post-market clinical validation performance testing of the device in patients from demographic groups representative of the U.S. population, including populations who are at lower risk of skin cancer.

A doctor from the American Academy of Dermatology checks Christine Trerotoli for signs of skin cancer (Spencer Platt/Getty Images)
A doctor from the American Academy of Dermatology checks Christine Trerotoli for signs of skin cancer (Spencer Platt/Getty Images)

Risks of AI in Cancer Diagnosis

DermaSensor Inc.’s FDA clearance was based on a study of over 1,000 patients, which showed that the device had a sensitivity of 96 percent across all 224 skin cancers.

A negative result recorded on the device has a 97 percent chance of being benign for all skin cancers, the agency said.

In a companion clinical utility study among 108 physicians, the DermaSensor device was found to decrease the number of missed skin cancers by half (from 18 percent to 9 percent), increasing the physicians’ accuracy and confidence in assessing cancerous lesions, according to DermaSensor Inc.

However, some experts have warned that some AI medical devices and systems being developed to diagnose skin cancer could result in less accurate results in some patients, specifically those with darker skin tones, due to a lack of freely available image databases to help train AI systems.

“If you train an algorithm on a data set that inherently in itself is biased and does not have within it enough examples of cancer or whatever skin manifestation of disease, it will not be able to then accurately make that diagnosis once it’s fully trained,” Dr. Adewole Adamson, an assistant professor in the department of internal medicine at the University of Texas at Austin Dell Medical School, told ABC News.

Others have said that AI being used to help detect skin cancer in patients runs the risk of overdiagnosing, noting that not all tumors become life-threatening, and cautioned overuse and sensible deployment of such technology.

According to Reuters, DermaSensor Inc.’s device, which is already commercially available in Europe and Australia, will be priced through a subscription model at $199 a month for five patients or $399 a month for unlimited use.


Source link

Leave a Reply

Your email address will not be published. Required fields are marked *