Friday, 21 September 2018
Latest news
Main » Google builds AI that can predict heart disease

Google builds AI that can predict heart disease

20 February 2018

The results of this study show that, until now, the predictions made by AI can not outperform specialized medical diagnostic methods, such as blood tests. The role of AI and machine learning in making human lives easier is conventional, but using the advanced technology tools to have a lasting impact on human health is certainly a breakthrough.

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.

The programme then combines the information in order to evaluate the patient's risk of suffering a major cardiac event such as a heart attack, The Verge reports.

The algorithm makes it quicker for doctors to analyse cardiovascular risk and it doesn't require a blood test.

Red Sox agree to five-year, $110 million deal with JD Martinez
In just 62 games in Arizona , he hit 29 homers, drove in 65 runs and propelled the Diamondbacks into the NL Division Series. Martinez became the 18th player in Major League Baseball history (and 16th of the modern era) to hit four homers in a game.

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.

Google researchers fed images scanned from the retinas of more than 280,000 patients across the United States and United Kingdom into its intricate pattern-recognizing algorithms, known as neural networks.

"In summary, we have provided evidence that deep learning may uncover additional signals in retinal images that will allow for better cardiovascular risk stratification". Google just combined that reality with technology to take the diagnostic potential to another level. In addition, this technique could help generate hypotheses for future scientific investigations into CV risk and the retina.

By predicting cardiovascular risks early, Google and Verily are not trying to replace doctors.

Russia says five of its citizens killed by US strike in Syria
The Kremlin does not exclude the presence of Russian citizens in Syria , who are not affiliated with the Russian Armed Forces. Two of the Russians told Bloomberg that more than 200 mercenaries, mostly Russian, were killed in the strike.

Despite the proof that machine learning can be accurate for interpreting risk factors based on medical images, one of the greatest challenges for wider adoption of machine learning in medicine is showing how these algorithms arrive at their conclusions.

"In other words, it's not yet ready for clinical testing, but it's a promising start for non-invasive evaluation of cardiovascular health", Engadget concludes.

The researchers concluded: "The opportunity to one day readily understand the health of a patient's blood vessels, key to cardiovascular health, with a simple retinal image could lower the barrier to engage in critical conversations on preventive measures to protect against a cardiovascular event". By studying their appearance with camera and microscope, doctors can infer things like an individual's blood pressure, age, and whether or not they smoke, all of which are crucial indicators of cardiovascular health.

ANC to vote Zuma out in ParliamentThursday
Malema admitted he felt robbed by the fact that he would not be leading a motion of no confidence against Zuma. A more than willing Julius Malema held a press briefing to respond to Zuma's question: What did I do wrong?

Google builds AI that can predict heart disease