The adoption of artificial intelligence solutions by many industries continues apace. According to the McKinsey Global Institute, about 70% of companies worldwide will embrace at least one form of AI by the year 2030.
One sector currently experiencing a surge in the development of AI tools and research into their utility is health and medicine.
A new study has found that AI can predict the risk of death in patients with heart disease better than existing models designed by medical experts.
The study (Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease) was published in PLOS One.
The researchers’ model was designed using healthcare data of more than 80,000 patients and the algorithms trained themselves to pick the most relevant variables for coronary heart disease from a set of 600.
Coronary heart disease is a leading cause of death in many developed countries and it’s caused by fatty deposits blocking the blood vessels that supply the heart with oxygen and nutrients.
Among the 600 variables were whether a person smoked and if they had received home visits from a doctor.
Proof of Principle
The AI model was compared with an expert-constructed prognostic model that made predictions based on 27 variables – and did a much better job. This was a proof of principle to compare the two and even though the AI model came out on top it could be a while before it’s used in the clinic. But that’s where researchers hope we are heading.
According to Andrew Steele the first author of the paper, “It won’t be long before doctors are routinely using these sorts of tools in the clinic to make better diagnoses and prognoses, which can help them decide the best ways to care for their patients.”