AI plays a role during the patient intake process

Patient intake and associated manual tasks that precede a medical visit represent a key component of a healthcare system’s operational efficiency and clinical quality.

As a result, some hospitals and primary care clinics are experimenting with artificial intelligence and large language models to focus on note-taking and writing.

With physicians burned out from spending more and more time in the electronic health record (EHR), can this technology be applied to other departments outside the exam room?

Dr. Josh Reischer is CEO of Health Note, a provider of a platform that can automate pre-visit documentation and help optimize time spent in the exam room by reducing EHR time. We spoke with him about the role of AI in the patient intake process and other efforts to improve workflow.

Q. You’re working on ways to automate patient intake and the manual tasks that precede a medical visit. Why is this area important to the overall performance of a health system?

A. Pre-appointment interactions set the tone for the entire healthcare experience. When done well, patients and physicians have a better encounter, administrators can be more efficient, and organizations are best prepared to get paid for the care they provide. When done poorly, you get the system we have today.

You wouldn’t go into an interview unprepared, but for doctors that’s the norm and patients notice it when they have to re-share the exact information they entered at home or in the waiting room. Doctors don’t have much choice in this regard and the demands placed on them are overwhelming.

The goal should be to increase efficiency for patients, staff and physicians. This means that everyone is freed from telephone calls, paper surveys, repeated questionnaires and other unnecessary medical details. Furthermore, visits can be improved if physicians are well informed about their patients. They can ask prescriptive, non-redundant questions that put the patient at ease and lead to a better diagnosis.

We see that doctors spend more time in the EPD. This is made worse by the Endless notes and “pajama time” that I struggled with late at night as physicians had to code and summarize patient interactions in the EHR.

Only one in five doctors say they have enough time to document the diagnosisIn the same survey, 42% said they have little control over their workload, and more than one in two spend an excessive amount of time at home creating documentation.

Revenue integrity and compliance are another group within healthcare systems that can benefit from a streamlined, automated intake and outtake process. Depending on the billing, there are different documentation requirements and patient reported outcomes that must be collected for each.

The solution is to collect the appropriate patient-reported outcomes before the appointment begins. That way, a doctor has the reminder to confirm and doesn’t have to worry about forgetting to add them. Traditionally, updates like this require training and are delayed. However, automating the workflow can help integrate these updates to all their doctors and patients at once.

Q. Health systems are increasingly experimenting with AI and large language models for note-taking and writing. Can this technology also be used in places outside the exam room or is it a one-trick pony?

A. Generative AI is an incredible technology because it is so adaptable. I think AI will uproot several parts of our industry, but I don’t believe it should displace humans in the loop. Most importantly, AI will help healthcare become more human than it is today.

It almost feels like healthcare technology is in its awkward teens – still figuring out what its purpose is. Today’s healthcare technology is clunky and silly, and doesn’t always do what’s expected of you. Generative AI feels like the beginning of the next phase of maturity.

Scribes are a great first step for generative AI, but there are a number of use cases throughout the patient and physician journey that could be improved with the technology beyond the visit. Yes, it starts with simple manual tasks and chores that are outdated and unnecessary in today’s healthcare, but I’m excited about how healthcare could be better for everyone.

When AI is applied to the front-end experience of healthcare, there are some significant benefits. For example, during intake, a chatbot or intelligent engine could work with a patient to discern pain levels, previous medical history, social determinants that trigger previous conditions, or simply recall a previous medical visit.

Generative AI can communicate in many different languages, translate medical shorthand and empathize with a patient’s condition. This is a huge win for organizations serving diverse and underserved populations.

Even in my career as a medical professional, I have seen the industry move from paper templates and keyboards to buttons and touchscreens. I believe AI will unlock new, more intuitive ways to interact with each other and the technology that supports us.

Q. Physicians are spending more time working in the EHR, and this is contributing to physician burnout. What are some ways technology can be improved to help physicians be more efficient and prescriptive with their time?

A. It has been noted that The time clinicians spend on EHRs increased by 28 minutes between 2019 and 2023. That simply can’t happen, especially at a time when more and more medical professionals are indicating they want to leave the industry. Technology makes the everyday better and enables doctors to deliver top performance.

As cliché as that sounds, it’s true. Today’s tools would have encouraged me to stay in patient care. In 2018, I left internal medicine to co-found Health Note. We all want to see the eradication of paper notes; we rehash every minute of our patient interactions—the good, the bad, and the ugly—for accountability and an outdated billing model.

Artificial intelligence is already changing thatwith documentation companies that handle that part. We need to extend this to the intake process and other areas so that doctors can spend more time with patients and sleep better at night. In short, physicians can rely on technology to increase personalization and get to know patients before interactions in the exam room.

Q. Are there other ways in which health IT design has failed? If so, how can these things be fixed?

A. In this first wave of innovation, doctors, nurses and physicians have been completely left out of the design phase. I have seen a lot of incompatibility and misunderstandings about the use of technology. That is why I believe that there are now more doctors like me who are developing much more practical tools.

We’re going to have to interface with the EHR in the near future, but it can evolve. Point solutions are going to go away in the near future. It’s now about enterprise platforms that can cross multiple care locations and specialties, from urology to musculoskeletal. Healthcare has so many layers and you can’t just design with one use case in mind.

It must be versatile enough to be applicable to this wide range of environments and populations, from Rural Appalachia to New York City. As we prepare for the Silver Tsunami of an aging generation of Boomers, where 10,000 people turn 65 every daywe all expect healthcare utilization to increase, so it is imperative that we build a sustainable workflow for the physician and enable an experience that is personalized to meet volume pressures.

The HIMSS AI in Healthcare Forum will take place September 5 and 6 in Boston. More information and registration.

Follow Bill’s HIT reporting on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a publication of HIMSS Media.