AI and Predictive Analytics in Healthcare

DZone 's Guide to

AI and Predictive Analytics in Healthcare

Researchers are using artificial intelligence and predictive analytics in myriad ways to predict, prevent, and treat myriad health issues.

· AI Zone ·
Free Resource

A few years ago, I wrote about a fascinating Italian project to use mobile phone data to predict the onset of bipolar disorder. The notion was that the sensors built into the average smartphone are ideal for picking up on the mood changes users undergo as they occur.

For instance, the manic stage of the condition is typified by hyperactivity, which can manifest itself in rapid speech, high levels of movement, and excessive phone usage. People in depressive states, by contrast, tend to show similar behaviors, albeit at the other end of the spectrum.

It isn’t the only work utilizing AI to help those with bipolar disorder, as a recent paper from the University of Cincinnati outlined an approach to accurately predict treatment outcomes by using AI.

“In psychiatry, treatment of bipolar disorder is as much an art as a science,” the authors say. “Patients are fluctuating between periods of mania and depression. Treatments will change during those periods. It’s really difficult to treat them appropriately during stages of the illness.”

The authors suggest that existing models of treatment predict the response to lithium treatment with an accuracy of no more than 75%. It’s an approach they believe needs to be improved, and indeed their AI-based approach was found to deliver a stunning 100% accuracy. What’s more, the model was also capable of predicting the reduction in symptoms resulting from the treatment with 92% accuracy.

The work is part of a cohort of projects that are looking to use AI to make medical treatments both earlier but also more effective.

For instance, an EU-led project is working on HIV. The work is being done under an EU project called EuResist, which began several years ago to work on optimizing treatments, including that of AIDS. The tool is offered freely throughout the EU and taps into data from across both Europe and Africa to find the right combination of drugs to provide resistance for the maximum amount of time. Crucially, it can also provide doctors with a good idea of when the drugs may cease being effective.

You’ve also got the novel project that is using AI to ensure organ transplants are more successful.  The Australian research team used the kind of AI algorithms that underpin many modern dating sites to try and improve organ acceptance and ensure a more accurate connection between organ donors and recipients.

“It’s a specially designed machine learning algorithm using multiple donor and recipient features to predict the outcome,” the team says.

A team from Mount Sinai Health System has used a similar machine learning-based approach to predict whether blood cancer patients will accept bone marrow or develop complications as a result.

We’re still at a very early stage of the application of AI in healthcare, but the early signs are positive enough to suggest that its impact will be very positive indeed.

ai, machine learning, medical, predictive analytics

Published at DZone with permission of Adi Gaskell , DZone MVB. See the original article here.

Opinions expressed by DZone contributors are their own.

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

{{ parent.tldr }}

{{ parent.urlSource.name }}