OpenEvidence released an artificial intelligence-powered medical coding feature embedded in its clinical AI assistant.
The new feature, called Coding Intelligence, provides automatic Current Procedural Terminology (CPT) code suggestions, evaluation and management (E/M) level recommendations with supporting medical decision making rationale written directly into the note and ICD-10 diagnoses, according to the company.
The tool, available in OpenEvidence Visits, provides coding derived from the clinical documentation and it automatically applies at the end of every doctor-patient visit, executives said.
“Without any extra work, OpenEvidence is able to generate concise rationale for their CPT + E/M suggestions. It truly captures the complexity of the encounter and saves me hours when I’m at the ER,” said Ania Bilski, M.D., vice president of clinical AI at OpenEvidence.
OpenEvidence, an AI-powered medical search engine, has been growing rapidly, supporting about 18 million clinical consultations from verified physicians in the U.S in December. OpenEvidence is now actively used daily, on average, by more than 40% of physicians in the U.S., spanning more than 10,000 hospitals and medical centers nationwide, according to the company. The company has expanded from clinical search into other clinical workflows that puts it into more direct competition with other healthcare AI companies. In August, the company rolled out its Visits feature, a clinical AI assistant that transcribes patient visits. Last month, OpenEvidence made an AI-integrated doctor dialer feature more widely available, directly taking on Doximity’s core business.
Modern medical billing is complex and time-consuming. With tens of thousands of possible billing codes and multiple ways of coding the same visit, the complexity of billing makes it challenging for physicians to get appropriately reimbursed without pivoting their focus away from patient care, according to OpenEvidence executives.
Most coding solutions today are very ‘old-school.’ In fact, most coding today is still done by either the physicians themselves or their nurses, or outsourced to third-party agencies that employ humans to code,” Zachary Ziegler, co-founder and CTO of OpenEvidence, told Fierce Healthcare.
Many current AI-powered solutions take a simplistic view of the process and enable simple mappings to these common codes.
“In reality, there are now tens of thousands of codes between CPT and ICD-10, and many of these represent complex, nuanced, context-dependent situations. Coding Intelligence is directly integrated into Visits, where it reasons over the entire transcript of the visit and the final clinical note generated to comprehensively understand exactly what was done, what diagnoses were reached and what treatments and labs were ordered. Then, we use the same technology that enables us to find exactly the right evidence when doctors use OpenEvidence, to find exactly the complete set of codes appropriate for the given visit,” Ziegler said.
OpenEvidence’s coding tool is able to report the accurate, complete set of codes that represent the entirety of what was done during the visit for all of the different ways physicians bill, including E/M codes, whether complexity-based using medical decision making or time-based, procedural CPT codes and the supporting ICD-10 diagnosis codes, Ziegler noted.
According to OpenEvidence, Coding Intelligence offers E/M level recommendations with the full medical decision making rationale already written. OpenEvidence generates the breakdown automatically from the clinical note, so whether billing by complexity or by time, the reasoning is already documented and included in the record.
The coding suggestions include uncommon procedure codes that are easily missed for complex cases. OpenEvidence built Coding Intelligence to ensure the right code gets submitted helping physicians minimize time spent in paperwork and lost revenue at the same time, executives said.
The company also designed its coding tool to offer automatic CPT code sequencing to maximize reimbursement. Under Medicare’s Multiple Procedure Payment Reduction policy, every procedure after the first reimburses at roughly 50%. The order in which codes are listed determine how much the practice gets reimbursed. OpenEvidence shows expected RVU values alongside each CPT suggestion so codes can be sequenced correctly before the claim goes out, executives said.
OpenEvidence also applies the CMS Correct Coding Initiative (CCI) rules to validate every code combination before surfacing recommendations, Ziegler said. Submitting incompatible code pairs is one of the most common causes of claim denials and compliance flags in medical billing.
“By running every suggested code set through our CCI rules engine, Coding Intelligence ensures that only valid, billable combinations are ever presented to the physician. This eliminates a whole class of errors that human coders and simpler AI tools routinely make,” he said.
Publisher: Source link
