The VA and DeepMind machine learning model was able to predict over 90 percent of the most severe kidney disease cases.
The Department of Veterans Affairs (VA) and DeepMind Health, a Google-backed research company, have developed a machine learning tool that can forecast acute kidney injury in patients up to 48 hours in advance.
Acute kidney injury (AKI), a potentially life-threatening condition, is often difficult for providers to detect. Once it occurs, patients often deteriorate very quickly.
In a study published in Nature, researchers showed how their machine learning model accurately predicted AKI in patients. Using a dataset of EHRs that cover diverse clinical environments, the tool was able to predict over 90 percent of the most severe AKI cases 48 hours sooner than with usual care.
Dig Deeper
- VA Enlists Watson for Big Data Analytics, Decision Support
- Machine Learning Tools Help Predict Clinical Trial Outcomes
- Machine Learning, Risk Scores Help Predict Hospital Readmissions
Want to publish your own articles on DistilINFO Publications?
Send us an email, we will get in touch with you.
Early detection can help improve medical care and reduce patients’ progression to serious consequences, such as the need for dialysis.
The study builds on the partnership between VA and DeepMind to use machine learning as the foundation for developing predictive analytics tools. Announced in February 2018, the partnership is initially focused on spotting the health risks that indicate patient deterioration.
Patient deterioration while in the hospital accounts for 11 percent of patient deaths around the world, according to the VA.
“Medicine is more than treating patients’ problems,” former VA Secretary David J. Shulkin said at the time. “Clinicians need to be able to identify risks to help prevent disease. This collaboration is an opportunity to advance the quality of care for our nation’s Veterans by predicting deterioration and applying interventions early.”
The partnership with the VA also adds to DeepMind’s efforts to improve disease detection and diagnosis. The artificial intelligence company has previously developed a clinical decision support product that can accurately identify more than 50 eye diseases and provide treatment recommendations for patients.
“Currently, eye care professionals use optical coherence tomography (OCT) scans to help diagnose eye conditions. These 3D images provide a detailed map of the back of the eye, but they are hard to read and need expert analysis to interpret,” said DeepMind when it developed the product.
“The time it takes to analyze these scans, combined with the sheer number of scans that healthcare professionals have to go through can lead to lengthy delays between scan and treatment – even when someone needs urgent care. If they develop a sudden problem, such as a bleed at the back of the eye, these delays could even cost patients their sight.”
By teaming up with the VA, DeepMind will expand its research and enable better care for veterans.
“We are proud to partner with the Department of Veterans Affairs on this important challenge,” Mustafa Suleyman, co-founder of DeepMind, said when the partnership was announced.
“This project has great potential intelligently to detect and prevent deterioration before patients show serious signs of illness. Speed is vital when a patient is deteriorating: the sooner the right information reaches the right clinician, the sooner the patient can be given the right care.”
Going forward, the VA Palo Alto Health Care System in California will be exploring ways to bring the AKI machine learning model into clinical settings. Researchers will work to build and integrate a user-friendly platform that will assist clinicians with treatment decisions.
The VA expects that leveraging the latest advancements in artificial intelligence will help improve the health and lives of veterans.
“These are exciting times for research and innovation at VA,” said VA Secretary Robert Wilkie. “Studies like this can have a significant effect in not only the Veteran community, but people throughout the nation.”
Date: August 07, 2019
Source: HealthITAnalytics
