Predictive Analytics

Predictive Healthcare Analytics: Improving the Revenue Cycle

By Sriram Parthasarathy
Share on LinkedIn Tweet about this on Twitter Share on Facebook

Efficiency in the revenue cycle is a critical component for healthcare providers. A failure in even one area can lead to difficulties receiving payments from insurance carriers and patients—resulting in critical revenue loss for the organization.

In 2017, healthcare organizations suffered a net revenue loss of 17.5 percent, according to a survey conducted by AMGA Medical Group—a 10 percent increase compared to the year before. Now more than ever, finding a path to better revenue cycle efficiency is critical to the financial health of these organizations.

The Cost of Inefficiency

Problematic claim submissions make up a significant portion of revenue loss for healthcare providers. The most common reasons for claim rejections include:

  • Missing or inaccurate patient information
  • Lack of proper authorization indicated on the claim
  • Submitting claims outside of an authorization period
  • Incorrect ICD-10 codes
  • Late claim submission

Ninety percent of these claim denials could be prevented through better process improvements. Though various automation tools could speed up the pace of claims submissions, this doesn’t address the data and timing issues that cause payers and plans to deny claims. What physicians really need is a more accurate method of identifying potential claim errors before they end up costing valuable revenue.

Enter Predictive Analytics

By implementing predictive analytics solutions throughout the revenue cycle, providers can identify and correct mistakes while developing strategies for minimizing future errors. The most critical portions of the revenue cycle include the registration process for patients, verifying insurance coverage, recording information from patient consultations, and submitting accurate claims for payment.

Providers can implement predictive analytics solutions to:

  1. Identify Missing Information. Providers can build models with rules identifying the pieces of data that cause most claims rejections. They can also forecast how much money may end up lost due to incorrect birth dates, member numbers, or other information critical to claims payment.
  2. Validate Coding. Payers frequently reject claims that contain codes that do not appear to tie back to a claim diagnosis. Building models around data from successful past claim submissions can identify the information that must be present to ensure payment. Providers can use the information to make improvements in manual and automatic claim creation workflows.
  3. Verify Authorizations. Analytics can be used to help providers improve the process of obtaining proper authorizations and referrals for medical procedures. The data from the models can also help providers create better validation procedures to prevent payment delays while improving the patient experience.
  4. Manage Charge Entry. Providers can reduce their rate of claims rejection by creating models verifying the accuracy of fee schedules. Other models can audit the accuracy of past charges and put strict auditing controls around charge entry to reduce the chances of submitting incorrectly billed charges.
  5. Follow Up with Insurance. Data models can be used to identify gaps in following up with carriers for payment, timely entry of claim denials, and collection actions taken by an organization’s staff. Providers can also forecast improvement trends based on any corrective actions taken to improve the entire payment collection process.

In all of these ways and more, analytics can give providers a 360-degree view of the efficiency of their current revenue cycle. They can also use the resulting insights to make critical improvements throughout the process and inform investments in automation and other technological tools.

Closing Revenue Cycle Leaks

Predictive analytics can be invaluable in helping healthcare providers to fill the costliest gaps in their revenue cycles. The entire process can be reviewed to forecast how various decisions can lead to improvements in the sequence and better financial health of a practice or organization.

Originally published September 9, 2019; updated on March 29th, 2021

About the Author

Sriram Parthasarathy is the Senior Director of Predictive Analytics at Logi Analytics. Prior to working at Logi, Sriram was a practicing data scientist, implementing and advising companies in healthcare and financial services for their use of Predictive Analytics. Prior to that, Sriram was with MicroStrategy for over a decade, where he led and launched several product modules/offerings to the market.