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.

Capturing Unstructured Data for Better Patient Care

Posted on October 9, 2014 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

The following is a guest blog post by Dr. Chris Tackaberry, CEO of Clinithink.
Clinithink_Chris Tackaberry_CEO and Founder
There is a veritable gold mine of high value data locked inside the free text fields of all EHR systems, as well as in the free text of other sources of clinical documentation such as progress notes, discharge summaries, consult requests and diagnostic reports. In all of these sources, rich, actionable patient data is trapped in unstructured text—stored side by side with more easily accessible structured data.

Take echocardiography reports, for example. The data contained within them—specifically ejection fraction, for instance—are crucial to the management of heart failure as outlined within NQMC core measures for this serious chronic condition. Yet seldom is an ejection fraction captured as structured data. Instead, it is usually documented as free text.

Since narrative has been an inherent part of clinical workflow for many years, HIT software vendors have reasonably added free text fields to their applications. While there is clearly value in driving insights from structured data captured in such systems, the unstructured piece in free text fields remains untapped. This represents a source of potentially significant additional value that can be gleaned from EHR and other clinical documentation sources. However, conventional structured data tools do not support the ability to exploit it for use in clinical decision making.

Unlocking the clinical value in unstructured data

In the days of paper charts, highly experienced physicians were able to quickly scan large charts to find information such as allergies, medications, family history, past and current symptoms, social history, and other background detail that provided the context so critically important to any clinical encounter. This information was usually summarized in documents (discharge summaries, referrals, etc.). Ironically, such information is now more difficult to find when stored electronically.

If the existence of unstructured narrative data were known, discoverable, searchable and actionable for every patient—across any EMR or other health IT systems—the currently hidden additional diagnostic and clinical data could further increase the efficiency and quality of care. Clinical Natural Language Processing (CNLP) is a technology that enables access to unstructured narrative data which can be used to unlock this additional value. Using narrative data found in reports, web pages, transcribed output, EMRs, and other electronic sources of free text at the point of care can expand our knowledge of the patient beyond the information obtained from structured data.

Recently, the AMA issued a report in conjunction with the RAND Corporation on the need for EHR vendors to improve the software solutions they are delivering to better meet the needs of physicians. Utilizing CNLP technology to access the clinical value inherent in unstructured EHR data would allow vendors to begin addressing some of the potential improvements.

As we move from a world in which healthcare is delivered on an episodic basis retrospectively to one where care is delivered almost continuously and prospectively, CNLP increases the opportunity to deliver rich, actionable and meaningful clinical content to help improve decision-making for more accurate, evidence-based and effective care.

Dr. Chris Tackaberry is the CEO of Clinithink.