Reforming pre-authorization with AI and machine learning
Healthcare providers are increasingly comfortable using AI-powered software to improve patient care, from medical imaging analysis to chronic disease management. While health plans have been slower to adopt AI and machine learning (ML), many are beginning to rely on these technologies in administrative areas such as claims management, and 62% of payers consider improving their AI/ML capabilities as an extremely high priority.
The process by which health plans manage the cost of member benefits is particularly ripe for technological innovation. Health plans often require providers to obtain prior approval, or prior authorization (PA), for a wide range of procedures, services, and medications. The heavily manual PA process results in unnecessary resource costs and delays in care, which can lead to serious adverse events for patients.
In recent years, the focus has been on reducing the administrative burden of PAs through digitalization. Some health plans are going beyond automation by leveraging AI and ML technologies to redefine the care experience, helping their members receive high-value, evidence-based care as quickly as possible. These technologies are able to streamline PA administrative tasks while continually refining personalized, patient-specific care pathways to achieve better outcomes, reduce provider friction, and accelerate patient access.
Provide clinical context for PA requests
Traditionally, PA requests are one-time transactions, disconnected from the patient’s longitudinal history. Physicians enter the requested clinical information, which is already captured in the electronic health record (EHR), into the health plan’s PA portal and await approval or denial. Although FHIR standards have provided new interoperability for exchanging clinical data, these integrations are rarely sufficient to meet a PA request, as most of the relevant information resides in unstructured clinical notes.
Using natural language processing, ML models can automatically extract this patient-specific data from the EHR, providing the health plan with a more complete patient record. By using ML and interoperability to study the patient’s unique clinical history, health plans can better contextualize PA requests in light of the patient’s past and current treatment.
Anticipate the entire episode of care
An AI-based authorization process can also identify episode-based care pathways based on patient diagnosis, suggesting additional services that might be appropriate for bulk authorization. Instead of submitting separate PAs for the same patient, physicians can submit a consolidated authorization for multiple services during a single episode of care, receiving pre-approval.
The extracted clinical data can also help health plans develop more accurate adjudication rules for these episode-based care pathways. Health plans can create subpopulations of patients who share clinical characteristics, allowing direct comparison of patient cohorts in various treatment settings. As patient data is collected, applied ML algorithms can identify the best outcomes for specific clinical scenarios. Over time, an intelligent authorization platform can aggregate real-world data to test and refine condition-specific care pathways for a wide range of patient populations.
Influencing Care Choices to Improve Outcomes
Health plans can also use AI to encourage physicians to make the most clinically appropriate and high-value care decisions. When an AP request is entered, ML models can assess both the completeness and relevance of the information provided in real time. For example, an ML model can detect that a physician failed to provide imaging records in clinical notes, triggering an automated prompt for that data.
An ML model can also detect when the provider’s PA request deviates from best practice, triggering a recommendation for an alternative care choice. For example, a smart authorization platform can suggest that a doctor select an outpatient environment instead of a hospital environment based on the type of procedure and clinical evidence. By using AI to help physicians build a more clinically appropriate case, health plans can reduce denials and reduce unnecessary medical expenses, while improving patient outcomes.
Of course, for these clinical recommendations to be accepted by physicians, health insurance plans must provide greater transparency in the criteria they use. While 98% of health plans say they use peer-reviewed, evidence-based criteria to assess PA claims, 30% of physicians think PA criteria are “rarely or never” proven on evidence. To earn the trust of physicians, health plans that use technology to provide automatically generated care recommendations must also provide full transparency about the evidence behind their medical necessity criteria.
Case prioritization for faster clinical review
Finally, applying advanced analytics and ML can help health plans improve PA self-determination rates by identifying which claims require clinical review and which do not. This technology can also help case managers prioritize their caseload, as it allows flagging of high-impact cases as well as cases that are less likely to impact patient outcomes or medical expenses.
Using specific health plan policy guidelines, a smart authorization platform can use ML and natural language processing to detect evidence that criteria have been met, linking relevant text in clinical notes to plan policy documentation. Reviewers can quickly identify the correct area of interest in the case, speeding up their review.
Applying AI and ML to the onerous PA process can relieve both physicians and health plans of the repetitive manual administrative work involved in submitting and reviewing these applications. More importantly, these smart technologies are transforming PA from a largely bureaucratic exercise to one that can ensure patients receive the highest quality care as quickly and painlessly as possible.
About the Author
Niall O’Connor is Chief Technology Officer at Cohere Healtha utilization management technology company that aligns patients, physicians and health plans with evidence-based treatment plans at the time of diagnosis.
Sign up for the free insideBIGDATA newsletter.
Join us on Twitter: @InsideBigData1 – https://twitter.com/InsideBigData1