Home » News » Will Artificial Intellignece Be Able to Truly Save Lives?
Artificial Intelligence Health

Will Artificial Intellignece Be Able to Truly Save Lives?

Robots and computers will probably never totally replace doctors and nurses, but they’re still having a grand impact on healthcare. Machine learning is improving diagnostics, predicting outcomes and ushering in a new era of personalised medicine.

As artificial intelligence and bots become more and more sophisticated, the question that remains: will AI be able to truly save lives?

Robo-miracles

For those at risk of heart disease, the answer may well be yes. Researched published by a team at the London Institute of Medical Services has shown that an artificial intelligence system can accurately predict when patient’s hearts will give out. The team trained the system to analyse blood tests and complex 3D models of beating hearts to look for signs of heart failure.

The system tracks the movement of more than 30,000 points on a patient’s heart to construct a realistic 3D model of the organ. Combining these with healthcare records, the system taught itself to recognise signals of impending death, making predictions for 5 years into the future.

The AI predicted with 80% accuracy, which patients will die in the next year. Doctor’s only average around 60% accuracy.

“The AI really allows you to tailor the individual treatment,” Dr. Declan O’Regan, one on the researchers, told BBC News. “So it takes the results of dozens of different tests including imaging, to predict what’s going to happen to individual patients very accurately. So we can tailor getting absolutely the right intensive treatment to those who will benefit the most.”

A taste of whats to come

This isn’t the only case of an AI making such sure diagnoses. In August 2016, IBM’s Watson (perhaps the world’s most famous AI) helped save a woman’s life by detecting her rare form of leukaemia. The University of Tokyo’s Institute of Medical Science, hadn’t detected the disease using conventional methods, but it took Watson just less than 10 minutes.

By comparing the patient’s genetic information with 20 million clinical oncology studies, Watson relatively quickly made the correct diagnoses and an AI-recommended course of treatment was successful.

Satoru Miyano, a Professor at the University of Tokyo’s Institute of Medical Science, notes that this is proof positive of the potential that AI has in the coming years, “to change the world.”  Seiji Yamada, of the National Institute of Informatics and chairman of the Japanese Society for Artificial Intelligence, adds that this is the nation’s first case of an AI saving someone’s life, asserting that this is “the most practical application in the field of medical and health care for artificial intelligence.”

These developments show just how useful AIs can be in preventing disease and death. AIs can analyse millions of bits of data in next to no time at all, which is something even the most adept of medical professionals just cannot compete with.

Still a way to go

However, we must also acknowledge that AIs are not a ready made replacement for doctors – yet. For example, human pathologists can diagnose breast cancer from biopsy samples with 96% accuracy. A trained AI system – a joint effort by the Harvard Medical School (HMS) and Beth Israel Deaconess Medical Center (BIDMC) – could only make diagnoses with 92% accuracy.

So you may think that, why bother developing an AI system that is actually worse than humans? Well, when the researchers combined the diagnostic capabilities of the AI with additional human pathologists, they identified breast cancers with 99.5% accuracy.

“We think AI has tremendous potential to improve health care, by enabling the construction of diagnostic tools to make diagnoses that are more accurate, more reproducible, and more predictive,” study co-author Andrew Beck of BIDMC told Digital Trends. “We hope these tools enable physicians to more effectively match patients to the right therapies.”

The future of medicine is based in data and analytics. This isn’t to say doctors and nurses are likely to go obsolete – a human touch is part of any healthcare system. But with advances in artificial intelligence, human and robots working together will have the capacity to save more lives than ever before.

About the author

Saqib Rana

Technohead living in Berlin. Experience in biosciences, banking and finance, blockchain.

Add Comment

Click here to post a comment