Error message

  • Warning: "continue" targeting switch is equivalent to "break". Did you mean to use "continue 2"? in include_once() (line 1374 of /home/scioha2/public_html/includes/
  • Deprecated function: The each() function is deprecated. This message will be suppressed on further calls in _menu_load_objects() (line 579 of /home/scioha2/public_html/includes/

November 21 2018 | 0 Comments | 145 reads Average Rating: 3.5

Machine Learning: Moving from Talk to Walk?

by Lalithya Yerramilli in Health Analytics

There’s been plenty of talk about the potential of machine learning. Consider the following:

  • According to a report from Deloitte Global, large- and medium-sized enterprises will intensify their use of machine learning in 2018. The number of implementations and pilot projects using the technology will double compared with 2017, and that number will double again by 2020.1
  • Artificial intelligence in healthcare is expected experience a 40% compound annual growth rate (CAGR) between 2017 and 2024, resulting in a $10 billion market according to a Market Study report. Tools, services and platforms related to imaging analytics and diagnostics driven my machine learning are expected to surpass $2.5 billion by the middle of the decade.2

The big question, though: How can healthcare organizations actually walk the machine learning walk? Here are three ways that healthcare organizations can put machine learning to use:

1) Address opioid fraud, waste and abuse (FWA). No doubt, manually identifying FWA is a labor-intensive task. In fact, to go through each patient record manually to determine which are allowable and which are examples of FWA is beyond the capabilities of most healthcare organizations. Machine learning can help. By analyzing hundreds of millions of patient/member records, this approach can discern multiple patterns. Working with clinicians, data scientists can then use this information to develop predictive models that identify potential FWA. For example, such analysis could identify when a patient is traveling a far distance to obtain opioids – a common indicator of drug-seeking behavior.

2) Reduce overbilling of patients. Instead of auditing bills sporadically, machine learning models can be used to review every bill generated. With this analysis, data scientists can then develop predictive models that score every bill prospectively, while continuously iterating and learning from outcomes to minimize false positives. The end result: bills can be analyzed as they are generated and corrected before they are sent.

3) Understand total cost of care by market. The decision to expand into new markets, or expand services in existing markets, is often a difficult one for payers and providers. There are literally hundreds of metrics that must be understood in context with one another, which is beyond the capacity of the human brain. Machine learning can help organizations analyze the data to develop a risk score that acts like a credit score, based on overall parameters such as membership, total spend in the market, provider costs, and member risks. Business experts can then use their experience to determine whether particular markets are worth targeting, and even where clinics should be located to draw the most patients/members.

Want to learn more about machine learning in healthcare? Check out the article that this blog is based on: ‘3 ways machine learning could immediately aid healthcare organizations’, which appeared in the Health Data Management.


1. Deloitte. Machine Learning: Things are Getting Intense.

2. Market Study Report. Healthcare Artificial Intelligence Market Soaring at 40% CAGR During the Period 2017-2024.

Rate this Article:

Average: 3.5 (2 votes)

Lalithya Yerramilli
VP, Healthcare Solutions

Lalithya Yerramilli has 15 years of experience in analytics in insurance, healthcare, and life sciences industries working with customer info-base, transactional, physician level, patient level, claims and longitudinal datasets.

Read full profile and other posts

Log in to post comments



Arun Rangamani
VP, Payment Services Delivery Leader

Ben Steverman
Chief Technology Officer

David Hom
Chief Evangelist

Jodi Siegel, MSHI, BSN, RN (Guest Author)
Director, wellness and care management

John Pagliuca
Vice President, Life Sciences

Lalithya Yerramilli
VP, Healthcare Solutions

Lesli Adams, MPA (Guest Author)
Director of Population Health Strategy, Oracle Corporation

Linda Pantovic (Guest Author)
Director of Compliance & Risk Adjustment, Scripps Health Plan Services

Mark Feeney
Life Sciences Consultant

Monique Pierce
Vice President, Business Optimization

Nayfe Faillace
Chief Compliance & Privacy Officer

Nicole Stec (Guest Author)
Senior Well-Being Manager, Banner Health

Priyanka Rajkumar
VP - SCIOXpert and Solutions, Analytics

Rena Bielinski
SVP, Strategic Accounts

Rodger Smith
SVP, Payment Integrity

Rose Higgins
SVP & GM, Data and Analytics

Subha Vaidyanathan
VP, Technology and Data Management

Taryn Bevilacqua
Compliance Director


Sign up to receive the latest SCIO news & insights, industry updates, event updates and more, right in your inbox.