Image: New research suggests machine learning can enhance digital healthcare tools by aiding routine processes and helping physicians to assess patient risk (Photo courtesy of iStock).
A number of studies presented at the 67th Annual Scientific Session of the American College of Cardiology (Washington, DC, USA) demonstrated how machine learning can be used to accurately predict clinical outcomes in patients with known or potential heart problems. The findings of these studies indicate that machine learning can usher in a new era in digital health care tools capable of enhancing healthcare delivery by aiding routine processes and helping physicians to assess the patients’ risk.
Clinical scoring systems and algorithms have been used in medical practice since a long time now, although there has recently been a visible increase in the application of machine learning to improve these tools. While traditional algorithms require all calculations to be pre-programmed, machine-learning algorithms deduce the optimal set of calculations by searching for patterns in large collections of patient data. New studies presented at ACC.18, which took place on March 10-12 in Orlando, USA, demonstrated how machine learning can be used to predict outcomes such as diagnosis, death or hospital readmission; improve upon standard risk assessment tools; elucidate factors that contribute to disease progression; or to advance personalized medicine by predicting a patient’s response to treatment.
For instance, in one study, researchers used machine learning to predict which patients would eventually be diagnosed with a heart attack after visiting a hospital emergency department for chest pain. Although chest pain is among the most common complaints in patients visiting the emergency department, only a fraction of such patients are ultimately diagnosed with a heart attack. In a pilot test, the algorithm was able to accurately predict a heart attack diagnosis 94% of the time in the validation data set. Researchers also ran the validation data through a standard clinical model (the hsTnT model, which incorporates only a patient’s age, sex and high-sensitivity troponin levels), which showed an accuracy of 88%. These results suggest that machine learning can offer a substantial improvement over current decision support tools.
“In a broad sense, machine-
learning methods have been around for quite some time, but it’s just in the last few years that we have gained the large data sets and computational capabilities to use them for clinical applications,” said Daniel Lindholm, MD, PhD, postdoctoral research fellow at Uppsala University in Sweden and the study’s lead author. “I think that we will see more and more decision support systems based on machine learning. But even as machine learning can enhance medical practice, I do not think these algorithms will ultimately replace physicians but, rather, provide decision support based on the data at hand. Other things, such as empathy, human judgment and the patient-doctor relationship are crucial.”
American College of Cardiology