The algorithm claims to have a 90 percent accuracy. LogitBoost was trained on data from 950 chest pain patients –  from the data, 85 variables are calculated.

Each of the patients have known outcomes after six years. Combined, this algorithm was able to identify patterns which indicates a higher chance of a heart attack or cardiac-related death.

Study author Dr Luis Eduardo Juarez-Orozco, said these advances go beyond medicine.

He said: “These advances are far beyond what has been done in medicine, where we need to be cautious about how we evaluate risk and outcomes.

“We have the data but we are not using it to its full potential yet.”

The findings were presented yesterday at the International Conference on Nuclear Cardiology and Cardiac CT (ICNC) in Lisbon, Portugal.

Dr Juarez-Orozco said: “Humans have a very hard time thinking further than three dimensions or four dimensions.

“The moment we jump into the fifth dimension we’re lost.

“Our study shows that very high dimensional patterns are more useful than single dimensional patterns to predict outcomes in individuals and for that we need machine learning.”

deepgeniusai.com/">AI & Big Data Expo events with upcoming shows in Silicon Valley, London, and Amsterdam to learn more. Co-located with the IoT Tech Expo, , & .

The post ML algorithm predicts heart attacks with 90% accuracy appeared first on AI News.

Corti has partnered with the European Emergency Number Association (EENA) to expand its service to four additional cities. The startup, based in Copenhagen, will select which cities it will expand its pilot to next in June.

The pilot in Copenhagen has been a resounding success measured by the analysis released today. Based on more than 2,000 cardiac arrest emergency calls in 2014, Corti was 93 percent accurate. While the ideal scenario would be 100 percent, it’s already a marked improvement over the 73 percent success rate for human operators.

Corti’s system analyses emergency calls to learn words and characteristics associated with those used in cardiac arrest calls and applies them to a neural network.

When emergency calls are placed, Corti acts like a digital assistant to the human operator and listens in for things such as breathing patterns which may indicate an emergency vehicle needs to be prioritised and dispatched quickly.

Cardiac arrests represent the biggest killer around the world. Here in the UK, the British Heart Foundation says a cardiovascular (heart and circulatory) disease causes more than a quarter (26 percent) of all deaths in the UK — an average of 420 people each day, or one death every three minutes. There are over seven million people in the UK living with a cardiovascular disease.

Corti has chosen a great place to start their AI detection system as many of us will have been impacted by a cardiovascular problem, either directly or indirectly. Going forward, it’s an exciting demonstration of the benefits AI can have in healthcare and could be expanded to help quickly diagnose other conditions.

Update: An earlier version of this article mistakingly said Corti’s AI detected heart attacks rather than cardiac arrests. To learn about the differences, see here.

What are your thoughts on the use of AI to detect health problems?

The post Cardiac arrest-detecting AI will expand to further European cities appeared first on AI News.