Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Using AI to Improve Diagnoses and Prognoses of Diseases

DZone 's Guide to

Using AI to Improve Diagnoses and Prognoses of Diseases

A team from Cardiff University believes that artificial intelligence can play a big role in improving the medical world.

· AI Zone ·
Free Resource

Smarter diagnosis and prognosis of a disease has obvious benefits to patients and healthcare providers alike. A team from Cardiff University believes that artificial intelligence can play a big role in doing just that. In a recently published study, the team describes how AI can help improve risk assessments for patients with cardiovascular disease in an efficient manner that requires neither expertise or human interaction.

"If we can refine these methods, they will allow us to determine much earlier those people who require preventative measures. This will extend people's lives and conserve NHS resources," the researchers explain.

Image title

Evidence-Based Medicine

Traditional approaches to risk assessment have taken a mathematical approach to the task, but the researchers believe that AI can help uncover complex associations in the data that are very hard to uncover manually.

The researchers utilized genetic programming to try and uncover some of these complex associations so that they can be made more readily available to clinicians at the point of care without requiring them to remove themselves from the patient.

They tested the system on cardiovascular patients to identify the risk of future events, including stroke, myocardial infarction, and even death. The system was trained on data from nearly 4,000 patients over a 10-year period, with around 25 predictors used, such as age, sex, BMI, and blood pressure.

The results revealed that the algorithm was able to perform at least as well as traditional methods when determining the risk for each individual patient, suggesting that the system has definite merits to further explore.

"The ability to interpret solutions offered by machine learning has so far held the technology back in terms of integration into clinical practice," the researchers conclude. "However, in light of the recent resurgence of neural networks, it is important not to sideline other machine learning methods, especially those that offer transparency such as genetic programming or decision trees. After all, we are looking to use artificial intelligence to aid human experts and not to take them out of the equation altogether."

Topics:
ai ,artificial intelligence ,ai in healthcare ,ai news ,ai study

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}