It’s absolutely vital that primary care physicians are equipped with the right tools to optimize their limited time with patients.
Health care today is not set up to allow physicians to spend nearly enough time with their patients.
In fact, a popular study published in the Journal of the American Board of Family Medicine found that in order to provide adequate care for the standard panel size of about 2,500 patients, primary care physicians would need to work more than 21 hours a day.
It’s clear that physicians don’t have the tools they need to manage their patient loads effectively. And because of that, patient care is suffering and providers and their staff are experiencing burnout at high rates — as high as 62.8%, according to a 2021 study from the American Medical Association.
If we want to see health care outcomes improve, it’s absolutely vital that primary care physicians are equipped with the right tools to optimize their limited time with patients. And one way to achieve that is by making pre-encounter medical record retrieval and analysis the norm for primary care — especially for at-risk providers.
Current Medical Record Processes are Setting Providers Up to Fail
Providers often walk into a clinical encounter with limited-to-no understanding of the patient’s medical history. They then have to spend valuable time playing catch-up to understand a patient’s current needs, or risk missing out on important insights.
This isn’t the providers’ fault, it’s the result of a broken system for retrieving and interpreting medical records.
Even with the implementation of EHRs, 78% of hospitals are still “often or sometimes” using mail and fax to receive medical records, according to a 2021 report from the Office of the National Coordinator for Health Information Technology. And when (or if) those records arrive, they’re often incomplete, illegible or contain far too many pages for a provider to read and analyze before the clinical encounter.
EHRs have done little to solve this problem, as they still require providers to search through pages of records to find key clinical insights. Typically, up to 70% of clinical value is contained in progress or SOAP notes, which are unstructured and thus difficult to extract information from.
We have to find a new solution that makes it easier for providers to gather and analyze the information they need — faster and more effectively.
The Benefits of Pre-Encounter Medical Record Analysis
Imagine how much more effective clinical encounters would be if providers were empowered with a complete understanding of the patients’ medical histories.
For example, a provider could walk into a clinical encounter with a list of diagnoses, current medications, and previous test results — rather than needing to get this information from a patient or spend time after the appointment sending out records requests.
A shift to pre-encounter medical record analysis could have enormous benefits for patients, payers, and providers. Patients would receive better quality care, HCC coding and other risk adjustment processes would improve, and providers could spend more time with patients and less time tracking down medical records.
Can Artificial Intelligence Offer a Solution?
If pre-encounter medical record analysis is the goal, then artificial intelligence and machine learning models are uniquely equipped to help create the solution we need.
Rather than expecting providers to sift through every document from a patient’s lifetime to look for potential diagnoses, recent advances in large language models could complement the work of manual risk adjusters, summarizing key information and pulling out diagnostic codes.
There’s also enormous potential for AI to help coders extract value from the unstructured progress or SOAP notes, including diagnoses, prescriptions, and even specific treatment plan details.
Medicare Advantage Rule Changes Make Risk Adjustment a Pressing Issue
All providers could benefit from changing our medical records process, but this problem is especially pressing for Medicare Advantage providers.
CMS recently announced a plan to remove more than 2,000 diagnosis codes from the current risk adjustment model, requiring providers to get much more precise with their diagnoses or risk missing out on premiums.
Unfortunately, traditional systems for medical record retrieval, storage, and analysis are not sophisticated enough to adequately meet providers’ needs under these new rules.
When a provider incorrectly diagnoses a patient — or presents a diagnosis without a treatment plan — it puts them at risk of payment retraction or fines for any discrepancies found during a Risk Adjustment Data Validation audit. On the other hand, when a provider misses a diagnosis, it lowers the patient’s RAF score and decreases the payment the provider receives from CMS for that patient’s care.
These consequences were already a significant source of concern for at-risk provider groups. But now that the list of HCC codes is shrinking, it’s more important than ever to code accurately and to catch all diagnoses.
While the pace of change in health care is often slow, it’s clear that action is desperately needed. Every time a provider has to spend valuable time chasing down medical records or quizzing a patient about their history, it directly impacts the quality of care for patients and the overall costs for the health system.
About the Author: Carm Huntress is the founder and CEO of Credo, a leader in value-based care solutions. Credo is working to radically simplify and automate the current medical record retrieval and risk adjustment processes. In doing so, Credo is enabling providers to take better overall care of their patients, improve staff productivity, and drive accuracy and compliance.