For some time now, humans as a species have been intrigued by the possibility of creating machines that could mimic the human brain.
From the eponymous spare-parts monster in Mary Shelley’s Frankenstein, published in 1818, to more modern-day plots like Tron or Her, we continue to be fascinated with artificial intelligence (AI).
While the emergence of AI appears both innovative and recent, the concept was introduced by a generation of scientists in the 1940s and 1950s. The term, “artificial intelligence,” was coined in 1955 by cognitive scientist and computer scientist, John McCarty, PhD in 1956 at the “Dartmouth Summer Research Project on Artificial Intelligence.”1 From this humble beginning, machine learning, deep learning, and predictive analytics were born and gave rise to a whole new field of study: data science.
Data science made advances towards AI for years, which encouraged scientists to believe the dream of a machine “thinking” could be a reality. Yet, the advancement of AI was slow and ultimately, held back by the limits of data processing.
Interestingly, the same developments in data science which underpin AI are likely to have the greatest impact on your revenue cycle. Today, the ability to source, harness, and leverage data ⎯ rather than artificial intelligence ⎯ is leading the way in increasing dollars collected by providers and health systems.
Big Data and Revenue Cycle Management
According to Rockwell Anyoha of Harvard University’s Graduate School of Arts and Sciences, “We now live in the age of ‘big data,’ an age in which we have the capacity to collect huge sums of information too cumbersome for a person to process.”2 It is that very data that offers rich gains for healthcare providers and surgery centers in their efforts to optimize reimbursement, reduce administrative burden and positively impact the patient experience.
In pre-billing, innovations around the patients’ unique financial characteristics (data) are making a significant impact. It is data that is ultimately submitted to the payers when seeking reimbursement. A clean claim must reflect the best data associate with the patient – their name, gender, date of birth, social security or MBI number and address. Errors in that data and in the patient’s insurance profile result in costly denials, increased days to collect, and rising labor costs within the RCM process.
Dynamic AR Optimization Technology
Ambulatory surgery centers today have access to extremely effective tools that mine big data to return the most accurate, complete patient information available in 30 seconds or less. By utilizing a demographic verification technology, providers can eliminate the patient profile errors and missing information before submitting a claim.
Nationally, 60% of claims submitted on average contain incorrect patient information.3 Best-in-class AR optimization solutions take the patient information collected during the encounter and enhance it by dynamically searching big data to return the most accurate and actionable data for your claim.
The same tools verify insurance information provided by the patient at the time of service and can even seek out additional, billable coverage that may have been previously hidden. Recent data from ZOLL Data Systems reveals that for every 1,000 claims previously identified as self-pay at the time of service, 344 have active commercial or governmental insurance coverage. Using an insurance discovery tool to harness big data and locate coverage for these claims nets huge wins for providers in their average collection per visit, without increasing administrative burden or cost.
Patient Financial Characteristics, Reimbursement, and Relationship Management
Big data is also creating significant gains as the patients out of pocket responsibility continues to rise. The title of Jonathan Wiik’s book, “The Patient is the New Payer,” captures this conundrum well. As a revenue cycle professional, you are faced with the difficult task of not only delivering bad news to the patient about what his policy does not cover, but also having to ask for payment. All too often this results in the erosion of both the patient relationship and the provider’s profitability.
According to James Zadoorian of ARxChange, technological innovations in self-pay analyzer tools are leading to as much as an 83% increase in collections from uninsured patients and a 22% increase in collections from insured patients. Self-pay analyzer tools mine big data to analyze the patient’s medical debt score, available credit, federal poverty level, and likelihood to pay in order to provide insights to providers who can then determine the best strategy for working with patients to collect payments due. Additionally, the data fulfills the government’s regulatory requirements for compliantly discounting the patient’s portion of the bill. What has previously been an uncomfortable and cumbersome task to determine a patient’s eligibility is now accessible in real time.
While AI is still in development, the best and most innovative technology available to RCM professionals today leverages big data and has much to offer anyone looking for ways to reduce claim denials, capture more revenue, and reduce administrative burden.
This article is a collaborative effort with ZOLL Data Systems.
1 A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence, J. McCarthy et al, August 31, 1955, http://raysolomonoff.com/dartmouth/boxa/dart564props.pdf
2 The History of Artificial Intelligence, Rockwell Anyoha, Harvard University Graduate School of Arts and Sciences “Science in the News” https://sitn.hms.harvard.edu/flash/2017/history-artificial-intelligence/, August 28, 2017
3 If only the claims were clean: Payers, providers lose big on inaccuracies, poor workflows, Susan Morse, March 22, 2016, “Healthcare Finance” https://www.healthcarefinancenews.com/news/if-only-claims-were-clean-payers-providers-lose-big-inaccuracies-poor-workflows