Savvy health systems are using AI and physician education to bolster their CDI teams — Join them with these 6 best practices
Many health system leaders see their organizations as locked in an adversarial contest with payers over reimbursement. Claims are often denied based on clinical indicators or the fact that complications or comorbidities were only documented once. These coding issues can lead to inadequate reimbursement, as payers will downgrade reimbursement if the claim lacks specificity.
At Becker’s 8th Annual CEO & CFO Roundtable in Chicago in November, Ensemble Health Partners hosted an executive roundtable to explore how clinical documentation improvement (CDI) best practices and physician education, as well as technologies like artificial intelligence, can enhance reimbursements. Ensemble Health Partners’ Jenna Jordan, senior vice president of health information, and Pieter Schouten, chief analytics officer, facilitated a wide-ranging discussion with session participants.
CDI and coding pitfalls are leading to reductions in hospital reimbursements
Many CDI professionals and medical coders are trained to only look for complications and comorbidities in a patient’s medical record, and then they stop. This is problematic for several reasons. If a complication is only documented once in the discharge summary, payers often will deny the claim. They want to see documentation of diagnosis and treatment throughout the patient’s stay.
Ms. Jordan explained, “Your CDI teams and coders must look at the entire medical record. If they don’t do this, you will fail on value-based outcomes and population health information. Once a payer sees one [major complication or comorbidity], you’re done with the reimbursement. But what about those additional diagnosis codes that show how sick the patient is?”
Organizations that do well on their Medicare Star ratings and risk-adjusted coding have CDI professionals that go beyond complications and look at potential patient safety events.
Another challenge is that payers often use clinical indicators that haven’t been adopted by hospitals. For Medicare, most health systems use sepsis-2 criteria for claims. Yet, Medicare Advantage and other commercial payers will deny those claims because they use sepsis-3 criteria. As a result, the healthcare organization receives an even lower payment even though the patient was treated for sepsis.
“Payers are denying claims just because you don’t meet what they consider to be their clinical indicators,” Ms. Jordan said. “It’s very important that your [health information management team] and CDI departments work together. If the clinical indicators aren’t there, you won’t get paid,”.
Physician education and involvement can help
Physicians must be educated about coding rules, documentation and variations in payers’ clinical guidelines. Ms. Jordan noted, “You won’t connect with doctors by telling them the hospital is seeking more revenue. You have to show them clinically what’s wrong with the patient charts.”
CDI queries to physicians must include clinical evidence. If a large number of queries comes back with “undetermined” responses, that’s a sign that the organization needs a physician education program.
“A CDI professional can tell you they are querying 35 percent of patients, but if they aren’t getting a response from the physicians, those queries are irrelevant,” Ms. Jordan said. “Who are the top doctors you are querying and why? How are they responding? This information will help you identify the financial impact of a physician education program.”
Including a physician advisor on the denials team can also help. Often physician-to-physician calls are more effective than inquiries from the CDI staff. Foreign physicians who aren’t licensed to practice in the United States can make good CDI physician advisors. They must be trained, however, on current clinical indicators and documentation guidelines.
Artificial intelligence can identify claims-related errors
Over the last year, Ensemble Health Partners has been applying technology to identify anomalies and errors in medical claims. Initially, the team took a rules-based approach. Now it is using artificial intelligence and applying it directly to areas like claims validation.
“If you use a rules-based system, it’s basically static. It looks for issues that resemble problems found in the past,” Mr. Schouten said. “Artificial intelligence is more advanced. You can explore completely new problems. We use a machine learning approach called the multi-armed bandit to find errors, particularly with DRG validation.”
6 best practices for bolstering CDI and increasing reimbursements
Ms. Jordan shared six best practices health systems can use to strengthen CDI departments:
- Confirm whether the CDI program is reviewing all inpatients. Many CDI initiatives exclude pediatrics and maternity cases. Ms. Jordan has worked with health systems where pregnancy complications are a major source of denials, yet the CDI team doesn’t review maternity patient cases.
- Require CDI teams to work on the weekend. Hospitals serve patients seven days a week. Unfortunately claims may never be reviewed for patients who come in on Friday and leave before Monday, if the CDI team only works Monday to Friday.
- Make sure the CDI team is on the floor, rounding and communicating with physicians. There is no sense in having CDI onsite if they never leave the office. CDI team members should be out on the floor.
- Consider a hybrid onsite/remote CDI model. It’s a good idea to always have a CDI professional onsite. One option is to rotate shifts. CDI team members can alternate between working onsite one week and then working from home the next. “When people work from home, they should have high levels of productivity. When they work onsite, they should focus on interacting with physicians or PAs,” Ms. Jordan said.
- Get a list of the top five denials for diagnosis-related group downgrades and the top five findings for code audits. This information allows organizations to develop prompts for physicians within the EHR.
- Take CDI to the next level beyond the financial impact. The CDI team should work with quality and focus on patient safety measures.
Dealing with payers is tougher than ever. It’s critical CDI specialists understand the coding rules and review the entire medical record clinically. Even if coders don’t have a clinical background, they can learn clinical indicators. Technology can also give healthcare organizations a leg up, as they strive to minimize denials.
As Ms. Jordan explained, “When you get denials, you have to fight them. You provided the services to patients and you deserve to get paid for them. Fight for every one of those denials, otherwise the payer will see you as an easy target.”