Healthcare Industry Using Data Analytics, Machine Learning, AI Innovations to Fight Fraud, Predict Outcomes

The Centers for Medicare & Medicaid Services (CMS) is the nation’s largest insurer, providing health insurance to all Americans over the age of 65 as well as those enrolled in Medicaid and state Children’s Health Insurance Programs. This means over 132 million Americans are covered by the government-run insurance plans.

CMS and their health insurance plans are funded by tax dollars, so the agency is always finding ways to curtail fraud to ensure that no money is wasted. To do that, CMS is turning to new data analytics, machine learning and artificial intelligence (AI) innovations as cybersecurity measures  to predict and mitigate fraud, as well as to improve health outcomes.

Predictive Data Analytics and Machine Learning Detecting and Thwarting Fraud

As reported by Melissa Harris for GovernmentCIO, CMS’ Center for Program Integrity (CPI) is applying predictive analytics in a variety of ways, from more basic “Impossible Day” calculations – where a provider is billing for more services than can literally fit into a day – to more complex calculations comparing peer groups to detect anomalies.

“CMS has been pushing forward with these predictive analytics pursuits by applying machine learning to its models,” shares Harris, referencing a presentation by Data Analytics and Systems Director Raymond Wedgeworth. “This is enabling his team to use unstructured, unsupervised data in predictive analytics models.”

Wedgeworth shared that the results so far have been good, with a high percentage of true positives and not false positives, thereby stopping fraud early in the review process.

“Machine learning is enhancing fraud-detection analytics by allowing Wedgeworth's team to bring back information about the outcomes of investigation leads to models to further improve them,” says Harris.

Wedgeworth is optimistic that as time goes on, the ability to detect even more types of fraud will continue to grow.

AI Innovations Predicting Patient Health Outcomes

CMS is also pursuing solutions that utilize AI. The agency recently announced the winners of their Artificial Intelligence Health Outcomes Challenge.

According to the Challenge website, “The CMS Artificial Intelligence (AI) Health Outcomes Challenge was an opportunity for innovators to demonstrate how AI tools – such as deep learning and neural networks – can be used to accelerate development of AI solutions for predicting patient health outcomes for Medicare beneficiaries for potential use in CMS Innovation Center innovative payment and service delivery models.”

Challenge participants had to go through a multi-stage competition, starting with an initial group of over 300 entrants, to a second phase group of 25, semi-final phase of 7, and finally a winner and runner-up.

At the final stage, “participants further refined the solutions that they developed in the prior stage to help predict unplanned hospital and skilled nursing facility admissions and adverse events, and additionally developed predictive algorithms to identify beneficiaries at risk of mortality in 12 months,” states the press release announcing the winners.

The winner of the challenge was ClosedLoop.ai, with Geisinger named as runner-up. The companies were heralded for their strong performance across the competition and best prediction accuracy results.

Capitol Tech offers bachelor’s, master’s and doctorate degrees in data science . Many courses are available both on campus and online. To learn more about Capitol Tech’s degree programs, contact admissions@captechu.edu.