Omnia Health is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

AI tool examines skin conditions for melanoma - fast

Article-AI tool examines skin conditions for melanoma - fast

Piction Health also uses machine learning to streamline dermatology referrals.

An MIT alumna has developed a mobile app that uses AI to classify various skin conditions, ranging from melanoma to shingles.

Co-founded by MIT alumna Susan Conover, Piction Health aims to help primary care physicians recognise skin conditions so they can quickly refer patients to dermatologists who may have life-threatening melanoma.

She was inspired by her own experience of finding a suspicious mole but was informed it would take three months before she could see a dermatologist. Though her mole turned out to be benign, she realised there was a need for a more efficient process.

The original objective was to identify skin cancer based on images taken with the mobile app, but Conover and her co-founder, Pranav Kuber, expanded their database to assist clinicians with identifying more frequent skin conditions, such as acne, eczema and shingles.

“All these other conditions are the ones that are often referred to in dermatology, and dermatologists become frustrated because they’d prefer to be spending time on skin cancer cases or other conditions that need their help. We realised we needed to pivot away from skin cancer in order to help skin cancer patients see the dermatologist faster,” Conover told SciTechDaily.

Training an algorithm to identify various skin diseases is much more complex than only diagnosing melanoma. Piction has accumulated what it said is the world’s largest image database of rashes with more than 1 million photos from 18 countries, taken by dermatologists.

“We decided it’s better to just jump to making the full product … that identifies all different rashes across multiple body parts and skin tones and age groups,” said Conover.

The machine learning tool can assist physicians with distinguishing between skin diseases for better patient care. Conover said the software can decrease the case evaluation time by 30 per cent, which can expedite potential melanoma cases to dermatologists while allowing primary care physicians to treat more routine cases. Most of the skin conditions diagnosed by clinicians are skin rashes such as eczema, rosacea, or psoriasis.

The model can also decrease costs for health care institutions by eliminating needless prescriptions, unwarranted referrals, or repeated doctor’s visits.

Piction plans on launching several pilots, including platforms that can assist with wound treatment or identify infectious diseases, such as leprosy. The company wants to partner with nonprofit groups to assist clinicians who do not have easy access to specialists or diagnostic tools. 

This article was originally published on AI Business.

Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.