WNS’s AI-Driven Application Takes Doctors Off the Phone with Payers

Doctors don’t seem flustered by bodily fluids or welts–what they dread is the hour-long calls with insurers, trying to persuade them to cover a test or procedure. There has to be some quality monitoring to prevent fraud and upcoding, but a lot of the time, the doctor just hasn’t coded properly or filled out the fields of the EHR that bolster her claim to need the procedure.

How do we take the doctor off the phone and give back those hours of her life? WNS has an AI-based application they claim can save huge amounts of time. It simply guides the doctor to filling out an EHR accurately and completely. As value-based care becomes more popular, accurate documentation becomes even more important.

WNS has been in the health care field for 15 years, utilizing 4,000 associates to serve 70 clinical institutions. They also have 1,200 associates in pharma or life sciences more generally, where their AI-generated dashboards and reports improve marketing efforts. This article focuses, however, on a clinical application. I had a call recently with Mark Halford, Senior Vice President, Client Services, Life Sciences and Health Care and Vipul Ahuja, Vice President, Client Services.

WNS talks about a “deep customer model.” Essentially, this entails gaining a deeper understanding of members or patients through digital technologies. The process unifies disparate data sources and then gleans actionable insights from data. WNS has found that this model radically transforms patient experience, integrating vital data and making it accessible on any device or channel to drive better clinical and administrative outcomes.

Many new sources of data have come up over the past few years. Patient EHRs have become more open, providing data that can be combined with claims data. By integrating all this information into a data lake, with proper labels and indexes, WNS can offer more personalized service, clinical insight, and administrative efficiency.

Their billing application draws on CMS clinical guidelines and warns the doctor when she is falling outside them. The application also takes the latest treatment protocols recommended by teaching hospitals. An AI-driven bot watches as the doctor fills out the EHR fields–to order an MRI, for instance–and prompts her to fill out everything the record needs to comply with the various guidelines.

Results are dramatic, according to Halford and Ahuja. Their app was adopted by places where 30-35% of requests had to be reviewed by a medical director to resolve disagreements. After deployment of the app, only 1% of requests have need to be reviewed.

Furthermore, the application identifies a whole course of treatment–which can be drawn out and complex, as with many oncology cases–and allows the insurer to grant authorization for the whole course, instead of making the doctor go back and get a new authorization at each step.

Although doctors and insurers clearly benefit from these efficiencies, the information collected on patients by WNS also benefits them, making their EHR information across entire history of treatment more accessible. This comprehensive information is a far cry from the limited views most current clinical portals offer the patient.

Results reported by WNS confirm that data integration is a worthy goal that can make big differences in doctors’ lives and their delivery of treatment. But integration by itself has a limited impact: well-targeted AI can extract more value from the data.

About the author

Andy Oram

Andy is a writer and editor in the computer field. His editorial projects have ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. A correspondent for Healthcare IT Today, Andy also writes often on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM (Brussels), DebConf, and LibrePlanet. Andy participates in the Association for Computing Machinery's policy organization, named USTPC, and is on the editorial board of the Linux Professional Institute.

   

Categories