Health Care

Google AI looks at your eyes to predict heart disease risk

Google AI looks at your eyes to predict heart disease risk

Google just combined that reality with technology to take the diagnostic potential to another level.

Google parent company Alphabet claims that one of the technology initiatives under its X experimental research divisions can accurately predict heart disease simply by scanning a person's eyes.

Traditionally, medical discoveries are often made through a sophisticated form of guess and test making hypotheses from observations and then designing and running experiments to test the hypotheses. "However, with medical images, observing and quantifying associations can often be hard because of the wide variety of features, patterns, colors, values, and shapes that are present in real data", the researchers wrote.

"Here, we show that deep learning can extract new knowledge from retinal fundus images".

Zainab rape-murder: Girl's father demands suspect be stoned to death
Earlier, police sources confirmed Imran, a neighbour of the girl, had confessed to his crime before an investigation team. He did not say how Imran's execution would be carried out, but many Pakistanis have demanded he be publicly hanged.

In this study, using data from 284,335 patients, the researchers were able to predict cardiovascular risk factors with surprisingly high accuracy.

It brings down the prediction time-frame to 5 years as against 10 years typically associated with the clinical risk predictors now in use. It's now working on an algorithm, which it hopes can predict heart disease by looking into our eyes and deducing data by analyzing scans of the back of a patient's eye.

"To make this useful for patients, we will be seeking to understand the effects of interventions such as lifestyle changes or medications on our risk predictions and we will be generating new hypotheses and theories to test", Peng said.

Using that data, the deep learning system was trained to identify certain health issues and risk factors, such as very high blood pressure or whether the patient is a smoker or non-smoker. Results are most significant when the algorithm was tasked with determining specific risk factors.

Quake felt across Shropshire
Police forces in Wales say they have received "extremely high call volume" reporting tremors. Tremors hit the South West at about 2.30pm with a number of people feeling buildings shake.

The AI algorithms need a good dose of machine learning before they can do this well, which involved analysing a medical dataset of around 300,000 patients and crunching both eye scans and more general medical data. For instance, the algorithm focuses on blood vessels when predicting blood pressure.

Deep learning networks have already been applied to produce algorithms capable of diagnosing diseases like melanoma and blindness caused by diabetes.

Given the retinal image of one patient who later experienced a major cardiovascular event (such as a heart attack) and the image of another patient who did not, the algorithm could pick out the heart patient 70 per cent of the time.

Uber's fourth-quarter loss narrows to $1.1 billion
Google and Uber were friendly rivals in the driverless-car industry, which is expected to grow to billions of dollars a year. The latest financial report shows the company continues to increase its revenue while making progress on cutting its loss.