DeepGestalt Can Identify Rare Genetic Disorders by Just Looking At Face

Must Read

Centre asks states to divide states into hotspot and non-hotspot areas

New Delhi, April 16 (IANS) Union Health Secretary Preeti Sudan on Wednesday wrote to chief secretaries of states and...

Dietary supplements important weapon for fighting off COVID-19

New York, April 25 (IANS) Supplements containing vitamins C and D and other micronutrients are a safe, effective and...

NASA’s OSIRIS-REx found water on Asteroid Bennu

NASA's Origins, Spectral Interpretation, Resource Identification, Security-Regolith Explorer (OSIRIS-REx) mission has found water locked inside the asteroid Bennu --...
Richahttps://onlinericha.com
More than just being a girl next door, a homemaker and a mother, Richa is an aware human being too. She loves everything about this world, but never ready to compromise with the wrongs. Here she presents the world the way she views it. Richa, a Biotech Professional writes here about all the health-related topics and Lifestyle trends. Write to me at richa.blueshadow@gmail.com

 DeepGestalt Can Identify Rare Genetic Disorders by Just Looking At FaceAccording to a recent study, a new artificial intelligence technology can accurately identify rare genetic disorders using a photograph of a patient’s face.

Named DeepGestalt, the AI technology outperformed clinicians in identifying a range of syndromes in three trials and could add value in personalised care, CNN reported.
The study was published in the journal Nature Medicine.

- Advertisement -

According to the study, eight per cent of the population has disease with key genetic components and many may have recognisable facial features.

The study further adds that the technology could identify, for example, Angelman syndrome, a disorder affecting the nervous system with characteristic features such as a wide mouth with widely spaced teeth etc.

Speaking about it, Yaron Gurovich, the chief technology officer at FDNA and lead researcher of the study said, “It demonstrates how one can successfully apply state of the art algorithms, such as deep learning, to a challenging field where the available data is small, unbalanced in terms of available patients per condition, and where the need to support a large amount of conditions is great.”

The study saw researchers training DeepGestalt, a deep learning algorithm, by using 17,000 facial images of patients from a database of patients diagnosed with over 200 distinct genetic syndromes.

The team found that the AI technology outperformed clinicians in two separate tests to identify a target syndrome among 502 chosen images.

In each test, the AI proposed a list of potential syndromes and identified the correct syndrome in its top 10 suggestions 91 per cent of the time.

Another test looked into identifying different genetic subtypes in Noonan syndrome, which carries a range of distinctive features and health problems, such as heart defects. Here, the algorithm had a success rate of 64 per cent.

According to researchers, the technology works by applying the deep learning algorithm to the facial characteristics of the image provided, then producing a list of possible syndromes.

However, the study added that it does not explain which facial features led to its prediction. To help the researchers better understand, the technology produces a heat map visualisation looking at what regions of the face contributed to the classification of diseases, explained Gurovich.

 

 

(Source: ANI)

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Latest News

We succeeded in saving country from stage 3: Health Minister

New Delhi, April 25 (IANS) Union Health Minister Harsh Vardhan on Friday said we have saved India from going...

Dietary supplements important weapon for fighting off COVID-19

New York, April 25 (IANS) Supplements containing vitamins C and D and other micronutrients are a safe, effective and low-cost means of helping your...

Instagram launches in-app food delivery to support businesses

San Francisco, April 25 (IANS) Facebook-owned photo and video-sharing app Instagram has launched a new feature that allows food orders to be placed through...

India has so far gifted $5 million medical supplies to world to combat Covid-19

New Delhi, April 24 (IANS) India has gifted USD 5 million worth of medicines and other Covid-19 related supplies to the world so far...

India needs to incentivise charger manufacturing: Top industry body

New Delhi, April 24 (IANS) Smartphone chargers and Printed Circuit Board Assembly (PCBA) are two mobile components that could help India achieve its manufacturing...

No exponential rise in Covid-19 cases in country: Health Ministry

New Delhi, April 23 (IANS) The Centre said on Thursday that the rise in coronavirus cases in the country has been more or less...

Google will now verify all of its advertisers on its platforms

San Francisco, April 23 (IANS) To provide greater transparency and equip users with more information about who is advertising to them, Google on Thursday...

HP to provide free resources to students, educators in India

New Delhi, April 23 (IANS) PC and printer major HP Inc. on Wednesday announced its partnership with educational content provider Gamooz in India to...

Can Facebook become Amazon of the world with Reliance Jio?

New Delhi, April 23 (IANS) Mark Zuckerberg-run Facebook has interestingly chosen India to begin its global ecommerce journey with investing $5.7 billion (approx. Rs...

More Articles Like This