Nursing Home Leader Holds Favorable View of AI-Enhanced EHR

Technology has become increasingly prominent across all types of healthcare facilities in recent years. This increase has helped meet the challenges of today, whether they are related to the pandemic or shortages in healthcare staffing.

There are few better examples than the use of electronic health records (EHRs), which has ramped up considerably over the last two decades. However, EHRs have also had some unintended consequences, such as an increase in a physician’s administrative responsibilities and a decrease in patient experience.

Rather than interacting with a patient, physicians too often find themselves staring at a computer screen. One study showed that 62 percent of the time clinicians spend with patients is devoted to reviewing EHRs. Another indicated that those same physicians spend nearly two hours a day simply inputting data.

Needless to say, these are unsustainable workloads, a point that has been further driven home during the pandemic. Four of every five physicians responding to a survey by the website Medical Economics said they are burned out, and the primary reason for that is “too much paperwork and regulations.”

While pre-pandemic studies (i.e., the American Medical Association in 2019) put the burnout rate at 44 percent, those studies also indicate that administrative burden is the main culprit.

The solution? More technology, perhaps. Specifically, it has been suggested that artificial intelligence can ease clinicians’ burdens and enable them to devote themselves more to patient care.

That is the belief of Joel Landau, chairman and founder of The Allure Group, a network of six New York City-based nursing homes. Landau has always tried to remain on the cutting edge of technology to meet the needs of each of Allure’s 1,400 residents and believes other facilities and organizations would do well to take a similar approach.

Consider Providence Health and Services in Renton, Wash., which according to the website EHRIntelligence is one of the largest healthcare systems in the nation, with 51 hospitals and 1,085 clinics. B.J. Moore, Providence’s Chief Information Officer and Vice President, told EHRIntelligence that EHR documentation is “probably the single biggest burnout issue for our clinicians,” and noted the trickle-down effect on those seeking care:

“Not only does it burn out our clinicians, but it also impacts the quality of patient interaction. Instead of having face-to-face interaction with the patient, a lot of times the caregiver is on a keyboard looking over their shoulder as they enter this information in the medical record.”

As a result, Providence has implemented a speech-to-text solution that records physician-patient conversations and incorporates medical data into the patient’s EHR. According to EHRIntelligence, the clinician need not even push a “record” button, as the AI-based technology begins to do so on its own, ignoring casual conversation and honing in on health-based exchanges.

Researchers at MIT and Boston’s Beth Israel Deaconess Medical Center have also developed a system called MedKnowts, which uses machine learning to simplify data collection and retrieval. An autocomplete system recognizes specific medical terms as they are entered by clinicians, enabling them to search more easily for information about any given condition, which is stored on bits of interactive text known as chips.

David Karger, Professor of Computer Science in MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and senior author of the study, said in a university news release that the idea behind this technology is to “smooth the pathway for physicians and let them accelerate.”

In other words, physicians are freed up to focus on the patient. As Karger also said in the release, EHRs have to this point proven more beneficial to researchers and government bodies than physicians:

“I think a lot of clinicians feel they have had this burden of EHRs put on them for the benefit of bureaucracies and scientists and accountants. We came into this project asking how EHRs might actually benefit clinicians.”

Researchers at Stanford University similarly developed an AI-based system that would enable clinicians to organize and retrieve patient records. When 12 gastroenterologists tested it, all but one found it superior to previous EHR iterations, and it saved them 18 percent of the time it would normally take to sort out data.

Despite these developments and AI’s potential to not only streamline workflows but also enhance interoperability and limit data overload, the technology is largely “absent” from healthcare facilities. That’s according to a November 2021 blog post on the website Insidebigdata.com by David Sellars, Principal of Product Innovation at DrFirst, Inc., a Rockville, Md.-based provider of healthcare solutions and services.

He did note one surprising exception -- Galva (Ill.) Pharmacy, which in April 2021 became the first U.S. pharmacy to incorporate an AI solution into its workflow, and as a result decreased its data-entry time by 45 percent.

Other healthcare organizations will inevitably follow. The benefits -- to physicians and ultimately to patients -- are too great to proceed otherwise. Leaders like Joel Landau have come to understand that, and many others are following suit.