Aug 16, 2024

Cerebral has decreased time spent on audits by 78% and has seen an even bigger improvement in meeting critical insurance criteria. The technology offers precise data feedback that could be missed in manual auditing, an exec says. Photo: Julia Dolan Cerebral is a virtual mental healthcare provider with a mission to democratize access to high-quality care to all. With several full-service monthly subscription plans to choose from, members receive online access to therapists and prescribing providers. Visits are done via video chat, and members can message their care team directly. Members can receive medications delivered straight to their door. THE PROBLEM Unfortunately, Cerebral's chart auditing process was entirely manual, time intensive and costly. The manual internal auditing and monitoring processes required hundreds of hours every month from a team of clinical auditors responsible for individually identifying notes to audit. To do this, they would work through a process of creating a selected sample of clinicians to review and issues or topics to review for adherence or compliance, and assure prior audit findings were not repeating in the environment. "In order to gain a relevant selected sample, the manual monthly build entailed reviewing hundreds of clinicians' calendars and appointments to identify and copy medical record links into the EHR in order to locate actual session notes for review," said Julia Dolan, associate director of behavioral operations at Cerebral. "Results and observations were then recorded separately in another document, analyzed and summarized into a report for management and the individual clinician, and finally separately synthesized for senior leadership and executive leadership within the company," she continued. In addition to being time-consuming, the process also was prone to human error. The successful completion and scoring of providers' audit results relied on the auditor's meticulous attention to detail. "They were required to type the clinician's name and the medical record number into a scoring template used to document feedback," Dolan explained. "This naturally posed typical audit hazards like name mismatches, incorrect links, or omissions of applying an audit component to a chart. "Remaining committed to continuous improvement and iteration to ensure high-quality audit feedback, we recognized gaps in the manual process and remained diligent and proactive with the resources we had available – not an insignificant task for clinical management," she added. PROPOSAL Vendor Brellium offered an AI-powered chart review technology designed to simplify the management of unstructured clinical notes by leveraging artificial intelligence to perform comprehensive and real-time audits. This technology aimed to address a major pain point in healthcare administration: the inefficiencies and errors in clinical documentation due to manual processing. "The core functionality of the system was to pre-screen all unstructured clinical notes for various types of errors and inconsistencies that could potentially impact quality patient care and/or insurance billing, such as client mood, successes and successors, evidenced based interventions, and determining if treatment goals are measurable and time-bound," Dolan explained. "Specifically, the AI was trained to identify clinical errors and spot note trends that might require attention," she continued. "This preemptive analysis also seeks to ensure that billing and/or coding errors could be identified and corrected before insurance claims submission, thus significantly reducing the risk of claims denials and the need for costly rework." Moreover, by automating the review process, the technology promised to decrease the time healthcare providers spent on manual auditing by 98%, she added. Where traditional methods typically allowed for only a small fraction of patient visits to be thoroughly reviewed, this AI-driven approach enabled Cerebral to extend the percentage of notes it reviews, increasing the coverage of reviews while also enabling a dramatic reduction in the labor-intensive task of manual screening – with a 78% reduction in time spent, she said. "This significant improvement in efficiency freed up significant resources, allowing healthcare providers to reallocate their time and efforts to more client-focused activities and other administrative areas," she noted. MEETING THE CHALLENGE In December 2023, Cerebral started using the automated chart review process within its behavioral care division. Facing the challenge of processing thousands of therapy session notes each month, Cerebral needed a scalable system to ensure compliance with its internal quality control and compliance requirements as well as insurance mandates – without the unsustainable burden of manual reviews. "Our clinical team worked directly with the vendor to deliver a tailored AI system that integrates the unique formats of Cerebral's session notes, service timings and specific audit requirements of insurance partners," Dolan explained. "After building out individualized question sets and parameters for each note template type, Brellium's system automatically screens session notes from Cerebral's EHR and highlights necessary adjustments, significantly reducing the resources devoted to administrative audits and allowing more time for patient care, while also mitigating the risk of financial loss from insurance clawbacks," she said. RESULTS Within six months of deploying the AI technology, Cerebral has seen a dramatic 81% improvement in meeting critical insurance criteria, and has decreased the time spent on chart audits by 78%, demonstrating significant advancements in operational efficiency. In addition, from March to June 2024, Cerebral has seen clinicians' average audit scores improve by 8%. ADVICE FOR OTHERS "AI-powered chart auditing has allowed us to expand our documentation auditing in an objective and operationally efficient way," Dolan stated. "It has enabled Cerebral to more efficiently review trends and error patterns via precise data feedback that could be missed in manual auditing. "In turn, we have been able to more easily identify areas of improvement and better implement additional education across our clinician teams in a meaningful and impactful way to drive continuous improvement," she continued. AI-powered chart auditing has enabled meaningful efficiency in Cerebral's workflows and enhanced note documentation quality, she concluded. Follow Bill's HIT coverage on LinkedIn: Bill Siwicki