The adoption of electronic health records (EHRs) was supposed to expedite these administrative tasks. In reality, it’s just created more roadblocks.
BY CHRIS RIOPELLE 3 MINUTE READ
The feasibility of AI and machine learning (ML) tools in healthcare settings is up for debate. ChatGPT made headlines after a recent experiment proved it could pass all three parts of the United States Medical Licensing Exam (USMLE). At the same time, experts continue to raise concerns about the tool’s limitations in real-life healthcare situations, as well as its proclivity for inaccuracies and bias.
While clinicians and other medical experts continue to debate ML’s effectiveness for treating patients, they’re neglecting a much more dependable and equally impactful use case: administrative work. ML has tremendous potential to streamline tedious administrative tasks and free up valuable time for clinicians, which ultimately leads to better patient outcomes. However, the effectiveness of AI in reducing administrative workloads hinges on providers’ ability to properly incorporate these tools into their work routines.
ADMINISTRATIVE BURDENS COST THE U.S. HEALTH SYSTEM $1 TRILLION A YEAR
The U.S. spends nearly $4 trillion on healthcare annually, and administrative costs account for a quarter of this figure. For those not in the medical field, it can be difficult to grasp how much time clinicians spend each day on administrative work. Patient record-keeping, insurance billing, prescription management, and countless other tasks pile up, reducing the amount of time providers can dedicate to their patients.
The adoption of electronic health records (EHRs) was supposed to expedite these administrative tasks. In reality, it’s just created more roadblocks. Fifty-seven percent of providers say that excessive EHR documentation is contributing to burnout. And while a majority of providers say exchanging data within their EHR network is easy, far fewer (24%) say the same for out-of-network EHRs.
Administrative restraints also affect patients. Think back to your most recent doctor’s visit. How much of the visit was spent filling out paperwork or waiting patiently while a physician or nurse practitioner typed away at their computer? This time would be better spent having a more substantive discussion about new health issues and treatment options. These administrative burdens don’t just come at the expense of providers and staff—they take time away from the quality of care patients receive.
MACHINE LEARNING CAN REDUCE ADMINISTRATIVE ROADBLOCKS
ML has significant potential for helping providers streamline their administrative responsibilities and, as a result, foster better and more fulfilling patient experiences.
One potential use case involves AI-powered scribing solutions, which a number of startups are beginning to roll out. These solutions take detailed notes of a patient and provider’s conversation, which helps streamline and better capture the visit, allowing for a more productive appointment.
Another trending use case is prior authorizations, or PAs. PAs occur when a healthcare payor requires a provider to secure approval to carry out a specific procedure or prescribe a medication. Physicians and their staff spend almost two full business days each week on PAs, and they can be a major source of contention between payors and providers. ML can quickly compile relevant patient information from EHRs and provide data-backed recommendations about the benefits of various treatment options. While providers still review the information and make the final call, ML can help reduce the time it takes to complete each PA.
In this example, ML acts as a supplemental tool for providers rather than the primary source of truth. This distinction is crucial. When using ML tools, providers will still have to use their best judgment for decision-making. But a reduced focus on administrative work coupled with a more comprehensive picture of a patient’s health history will make these judgments easier.
ADMINISTRATION PRESENTS AN OPPORTUNITY FOR EXPERIMENTATION
Concerns about bias and the feasibility of using ML and AI solutions are not without merit. Obviously, tools like ChatGPT have limitations, and it’s important to fully consider all the factors that could impact patient outcomes.
But using these tools for administrative purposes offers providers a much lower-stakes path to realize their benefits. Ultimately, by streamlining administrative tasks, providers become better equipped to offer their patients more comprehensive care.
Chris Riopelle is the CEO and co-founder of Strive Health.
You must be logged in to post a comment.