Free EMR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to EMR and EHR for FREE!

AI-Based Tech Could Speed Patient Documentation Process

Posted on August 27, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

A researcher with a Google AI team, Google Brain, has published a paper describing how AI could help physicians complete patient documentation more quickly. The author, software engineer Peter Lui, contends that AI technology can speed up patient documentation considerably by predicting its content.

On my initial reading of the paper, it wasn’t clear to me what advantage this has over pre-filling templates or even allowing physicians to cut-and-paste text from previous patient encounters. Still, judge for yourself as I outline what author Liu has to say, and by all means, check out the write-up.

In its introduction, the paper notes that physicians spend a great deal of time and energy entering patient notes into EHRs, a process which is not only taxing but also demoralizing for many physicians. Choosing from just one of countless data points underscoring this conclusion, Liu cites a 2016 study noting that physicians spend almost 2 hours of administrative work for every hour of patient contact.

However, it might be possible to reduce the number of hours doctors spend on this dreary task. Google Brain has been working on technologies which can speed up the process of documentation, including a new medical language modeling approach. Liu and his colleagues are also looking at how to represent an EHR’s mix of structured and unstructured text data.

The net of all of this? Google Brain has been able to create a set of systems which, by drawing on previous patient records can predict most of the content a physician will use next time they see that patient.

The heart of this effort is the MIMIC-III dataset, which contains the de-identified electronic health records of 39,597 patients from the ICU of a large tertiary care hospital. The dataset includes patient demographic data, medications, lab results, and notes written by providers. The system includes AI capabilities which are “trained” to predict the text physicians will use in their latest patient note.

In addition to making predictions, the Google Brain AI seems to have been able to pick out some forms of errors in existing notes, including patient ages and drug names, as well as providing autocorrect options for corrupted words.

By way of caveats, the paper warns that the research used only data generated within 24 hours of the current note content. Liu points out that while this may be a wide enough range of information for ICU notes, as things happen fast there, it would be better to draw on data representing larger windows of time for non-ICU patients. In addition, Liu concedes that it won’t always be possible to predict the content of notes even if the system has absorbed all existing documentation.

However, none of these problems are insurmountable, and Liu understandably describes these results as “encouraging,” but that’s also a way of conceding that this is only an experimental conclusion. In other words, these predictive capabilities are not a done deal by any means. That being said, it seems likely that his approach could be valuable.

I am left with at least one question, though. If the Google Brain technology can predict physician notes with great fidelity, how does that differ than having the physician cut-and-paste previous notes on their own?  I may be missing something here, because I’m not a software engineer, but I’d still like to know how these predictions improve on existing workarounds.

Mercy Shares De-Identified Data With Medtronic

Posted on October 20, 2017 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

Medtronic has always performed controlled clinical trials to check out the safety and performance of its medical devices. But this time, it’s doing something more.

Dublin-based Medtronic has signed a data-sharing agreement with Mercy, the fifth largest Catholic health system in the U.S.  Under the terms of the agreement, the two are establishing a new data sharing and analysis network intended to help gather clinical evidence for medical device innovation, the company said.

Working with Mercy Technology Services, Medtronic will capture de-identified data from about 80,000 Mercy patients with heart failure. The device maker will use that data to explore real-world factors governing their response to Cardiac Resynchronization Therapy, a heart failure treatment option which helps some patients.

Medtronic believes that the de-identified patient data Mercy supplies could help improve device performance, according to Dr. Rick Kuntz, senior vice president of strategic scientific operations with Medtronic. “Having the ability to study patient care pathways and conditions before and after exposure to a medical device is crucial to understanding how those devices perform outside of controlled clinical trial setting,” said Kuntz in a prepared statement.

Mercy’s agreement with Medtronic is not unique. In fact, academic medical centers, pharmaceutical companies, health insurers and increasingly, broad-based technology giants are getting into the health data sharing game.

For example, earlier this year Google announced that it was expanding its partnerships with three high-profile academic medical centers under which they work to better analyze clinical data. According to Healthcare IT News, the partners will examine how machine learning can be used in clinical settings to sift through EMR data and find ways to improve outcomes.

“Advanced machine learning is mature enough to start accurately predicting medical events – such as whether patients will be hospitalized, how long they will stay, and whether the health is deteriorating despite treatment for conditions such as urinary tract infections, pneumonia, or heart failure,” said Google Brain Team researcher Katherine Chou in a blog post.

As with Mercy, the academic medical centers are sharing de-identified data. Chou says that offers plenty of information. “Machine learning can discover patterns in de-identified medical records to predict what is likely to happen next, and thus, anticipate the needs of the patients before they arise,” she wrote.

It’s worth pointing out that “de-identification” refers to a group of techniques for patient data protection which, according to NIST, include suppression of personal identifiers, replacing personal identifiers with an average value for the entire group of data, reporting personal identifiers as being within a given range, exchanging personal identifiers other information and swapping data between records.

It may someday become an issue when someone mixes up de-identification (which makes it quite difficult to define specific patients) and anonymization, a subcategory of de-identification whereby data can never be re-identified. Such confusion would, in short, be bad, as the difference between “de-identified” and “anonymized” matters.

In the meantime, though, de-identified data seems likely to help a wide variety of healthcare organizations do better work. As long as patient data stays private, much good can come of partnerships like the one underway at Mercy.