Hospital leverages predictive analytics to improve treatment

Hospital leverages predictive analytics to improve treatment

on Oct 24, 14 • by Chris Bubinas • with No Comments

Massachusetts General Hospital now utilizes predictive analytics technology to make better clinical decisions, leading to more efficient and effective patient care...

Home » Analytics and Data Mining » Hospital leverages predictive analytics to improve treatment

Predictive analytics have proven themselves to be an invaluable resource for countless organizations in many fields. By leveraging this technology, firms can gain better insight that leads to improved decision-making and, consequently, superior results.

The most recent example of the power of predictive analytics surrounds health care. Massachusetts General Hospital now utilizes this technology to make better clinical decisions, leading to more efficient and effective patient care.

Identifying risk
MGH is widely acknowledged as one of the nation's leading centers for health care. Frequently, patients are referred to the hospital by doctors who simply don't have the means or experience to effectively treat these individuals themselves. This means that MGH surgeons and clinicians frequently face some of the most challenging, high-risk health care challenges out there.

Speaking to HealthITAnalytics, Dr. David Ting, associate medical director for information systems at the Massachusetts General Physicians Organization, explained that the organization now applies predictive analytics technology to its Queriable Patient Interface Dossier in order to better assess individual patients' risks.

Previously, according to Ting, MGH surgeons would have limited insight into the risks involved in a given operation. They would typically work with referred patients, and therefore did not have a robust, one-on-one experience with those individuals.

"How do you know whether something's appropriate or not when this is a patient that comes to you and you have 15 minutes to go through the chart or talk to the patient?" said Ting, the news source reported. "Well, that's how we use QPID."

The doctor went on to explain that the QPID system delivers insight into the surgical risks of a particular procedure when performed on a patient with a specific set of circumstances and conditions. The system takes into account the entirety of a patient's electronic health record, delivering comprehensive predictive insight concerning the risks of the intended operation.

"The system automates those searches using national guidelines, and then it essentially shows the results in a dashboard with a red, yellow or green risk indicator for the surgeon or proceduralist to see," Ting said, according to HealthITAnalytics.

He went on to note that surgeons can then have much more informed, productive conversations with patients. Rather than relying on guesswork or general trends – for example, the average percentage of people who experience complications from an operation – doctors can offer data-based evidence that a particular procedure has a high risk for a specific patient, based on his or her unique history, and that an alternative approach may be the better option.

Not only does this help to cut down on unwise surgical procedures, but it also empowers patients to make more informed decisions in regard to their own treatment.

Integration issues
In order for this and other health care-related predictive analytics to yield positive results, though, hospitals and other care providers must overcome a number of hurdles. One of the most significant of these is the need to fully integrate with EHR systems. The MGH predictive analytics solution relies entirely on EHRs to accurately gauge the risk for an individual patient, as opposed to the average dangers posed by the operation. The same will likely be true of any organization's health care predictive analytics efforts.

Additionally, care providers must utilize high-quality algorithms to ensure the effectiveness of their predictive analytics systems. Without embeddable, high-performance algorithms that integrate with all relevant apps, organizations are unlikely to optimize the accuracy or usability of their predictive analytics tools. For a health care provider, such shortcomings may not only be frustrating, but actually dangerous. 

Related Posts

Leave a Reply

Your email address will not be published. Required fields are marked *

Scroll to top