Welcome to the MedMetrics Blog

The MedMetrics blog provides comments and insights regarding the world of Workers’ Compensation, principally, issues that are medically-related. The blog offers viewpoints regarding issues affecting the industry written by persons who have long experience in the industry. Our intent is to offer additional fabric, perspective, and hopefully, inspiration to our readers.

Search The MedMetrics Blog

Monday, November 13, 2017

Predictive Analytics--Winning Through Better Information

by Karen Wolfe

“Predictive analytics, is a way to predict the future using data from the past and helps businesses answer questions about the probabilities of certain events occurring. From recommending additional purchases based on the items that customers place in online shopping carts to pinpointing hospital patients who have a greater risk of readmission, the use of predictive analytics tools and techniques is enabling organizations to tap their collections of data to predict future business outcomes—if the process is managed properly” (emphasis added).[1] A well-managed process means planning, implementing, measuring, and repeating.

“However, many companies are doing analytics to do analytics, and they aren't pursuing analytics that are measurable, purposeful, accountable and understandable.”[2] The idea is to utilize this technology-driven process for analyzing data in order to present actionable information to those responsible for decision-making and to streamline operational processes. That’s why it is so essential to Workers’ Comp employers, payers, and medical management organizations. It is how they can win.

Stated simply, winning for employers and payers in Workers’ Comp means curbing medical costs while improving outcomes for injured workers. Multiple medial cost management initiatives have been implemented over the years in the industry including bill review, nurse case management, utilization review, and peer review to name a few. Yet, managing medical costs while improving outcomes has been elusive. While injury frequency has decreased, severity, both in terms of physical injury and cost has increased.

Enabling an organization to tap its collection of data to predict future business outcomes and managing the process more efficiently requires detailed planning. First, decide what knowledge is needed, how it will be used, and where the supporting data can be found. Integrate the data at the claim level to create a complete view of the claim. That means integrating the data contained in bill review, claims system, and pharmacy at a minimum.

Analyze the collected and integrated data. Identify cost drivers, risk conditions, trends, and outliers. Monitor the data to alert the appropriate persons when those conditions occur going forward. Critical conditions can occur or become known in the data at any point in the claim, not just at the beginning or at planned intervals. Early intervention through better and more timely information will impact cost, duration, and outcome of the claim.

Implementation should emphasize simplicity for the recipients. They should not be required to search for additional information to move forward or enter data in order to reach conclusions. Complete information should be presented to the appropriate persons, including detailed projected costs based on predictive analytics. Knowing the detail of predicted costs serves to guide appropriate initiatives.  Moreover, results of mitigation efforts can be measured.

When untoward conditions occur during the course of the claim, probable ultimate costs for the claim can be projected based on predictive analytics of the historic data. Past is prologue, meaning the costs that occurred in the past in similar situations are likely to repeat. Predicted costs are a powerful knowledge assistant for claims reps in resetting reserves and medical managers targeting the most advantageous approaches to intervention. On case closure, success in mitigating medical costs can be objectively measured compared to projected costs.

A well-managed process always means returning to the beginning to re-evaluate the plan and implementation strategies. Are the results as expected? What additional information is needed or possible? What do the recipients want or need? The process continually improves though execution, learning from the information gained, and how it is best utilized. That’s a win.

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, predictive analytics-informed medical loss management and technical services company. MedMetrics offers intelligent medical management systems that link analytics to operations, thereby making insights actionable and the results measurable. karenwolfe@medmetrics.org


[1] Voorhees, C. Search Business Analytics. Techtarget.com
[2] King, E. The Modeling Agency. Techtarget.com