New machine learning model to prevent sight loss in humans

Tokyo: Japanese researchers have developed models based on machine learning that predict the risk of visual impairment in patients with high myopia — one of the top three causes of irreversible blindness in many regions of the world.

People with extreme shortsightedness (called high myopia) can clearly see objects that are near to them but cannot focus on objects at a distance.

Contacts, glasses, or surgery can be used to correct their vision, but having high myopia is not just inconvenient; half of the time it leads to a condition called pathologic myopia, and complications from pathologic myopia are the leading causes of blindness.

“We know that machine-learning algorithms work well on tasks such as identifying changes and complications in myopia,” said lead author Yining Wang from Tokyo Medical and Dental University (TMDU) in Japan.

“But in this study, we wanted to investigate something different, namely how good these algorithms are at long-term predictions.”

To do this, the team performed a cohort study and looked at the visual acuity of 967 Japanese patients after 3 and 5 years had passed.

They formed a dataset from 34 variables that are commonly collected during ophthalmic examinations, such as age, current visual acuity, and the diameter of the cornea.

They then tested several popular machine-learning models such as random forests and support vector machines. Of these models, the logistic regression-based model performed the best at predicting visual impairment at 5 years.

However, predicting outcomes is only part of the story.

“It’s also important to present the model’s output in a way that is easy for patients to understand and convenient for making clinical decisions,” said Kyoko Ohno-Matsui, senior author from the varsity.

To do this, the researchers used a nomogram to visualise the classification model. Each variable is assigned a line with a length that indicates how important it is for predicting visual acuity.

These lengths can be converted into points that can be added up to obtain a final score explaining the risk of visual impairment in future.

People who permanently lose their vision often suffer both financially and physically as a result of their loss of independence.

Although the model still has to be evaluated on a wider population, this study has shown that machine-learning models have good potential to help address this increasingly important public health concern, which will benefit both individuals and society as a whole.


Researchers use pollen from Kaziranga National Park to decode climate change

New Delhi: Indian researchers have explored how pollen and non-pollen palynomorphs (NPPs) of Kaziranga National Park (KNP) can help in the interpretation of climate in the region. The KNP in...

Scientists develop tech that can recognise human emotion real time

Seoul: South Korean scientists have developed a groundbreaking technology that can recognise human emotions in real time, an advance poised to revolutionise various industries, including next-generation wearable systems. The multi-modal...

Cryogenic engine of LVM3 rocket completes ground qualification tests: ISRO

Chennai: The Indian space agency, ISRO, on Wednesday said it has achieved a major milestone in the human rating of its CE20 cryogenic engine that will power the LVM3 rocket...

1st human implanted with Neuralink brain chip able to control mouse via thoughts: Musk

New Delhi: Elon Musk has said that the first human implanted with a brain chip from his brain-computer interface company Neuralink seems to have fully recovered and is able to...

AI Tokens see surge after OpenAI’s text-to-video model Sora launch

New Delhi: Following the launch of OpenAI's text-to-video model Sora, a significant growth have been witnessed in the artificial intelligence (AI)-related tokens over the weekend. According to CoinGecko data, sector...

EU opens formal probe against TikTok over safeguarding kids, ad transparency

London: The European Commission on Monday opened formal proceedings to assess whether TikTok may have breached the Digital Services Act (DSA) for protection of minors, advertising transparency, data access for...

AI will create more jobs than it destroys: IBM India

New Delhi: As generative artificial intelligence (AI) begins to threaten certain jobs, Sandip Patel, Managing Director, IBM India/South Asia, has said that AI will actually create more job options that...

India successfully puts into orbit its 3rd Gen Meteorological satellite – INSAT-3DS

Sriharikota (Andhra Pradesh): India successfully put into orbit its third generation meteorological/weather satellite INSAT-3DS on Saturday evening in a copybook style. The 2,274 kg INSAT-3DS was carried by Geosynchronous Satellite...

ISRO again skips ‘unlucky’ 13 while numbering its rocket

Chennai: The Indian Space Research Organisation (ISRO) has done it again. It has skipped the number '13' -- generally considered "unlucky" -- while numbering its Geosynchronous Satellite Launch Vehicle (GSLV)...

59% of domestic firms deployed AI as India on way to become responsible AI hub: IBM

New Delhi: India is on the right path to become a global AI hub with creating a robust AI governance framework, and top factors driving adoption in the country are...

Chikungunya to raise death risk from heart, kidney disease: Lancet

London: People infected with the chikungunya virus (CHIKV) still have an increased risk of death from complications of heart and kidney for up to three months post-infection, according to new...

Scientists identify water molecules on asteroids for 1st time

New York: Scientists have discovered, for the first time, water molecules on the surface of an asteroid. The team from Southwest Research Institute (SwRI) in the US looked at four...

Read Previous

Sensex zooms past 70k after US Fed’s dovish message

Read Next

Power-packed Redmi Note 13 5G to arrive in India on Jan 4

Leave a Reply

Your email address will not be published.

WP2Social Auto Publish Powered By :