The Empiric Analytics Suite – Opportunity Identification
Empiric’s Opportunity Identification component utilizes automation and machine learning to not only identify and size variation opportunities but also to recommend substitutions or clinical practice changes based on clinically meaningful comparisons.
Empiric’s automated opportunity identification platform rapidly identifies and quantifies opportunity from the Empiric Opportunity Playbook across the system, facility or surgeon.
Empiric’s dynamic data playground to explore supply variation opportunities by visualizing opportunities more clearly, maximizing the value of the Empiric Clinical Supply Categorization and telling a fluid clinical story.
In development, Empiric’s machine learning based engine for analyzing complex surgical case and claims data, identify variation, and make item substitution recommendations based on best practice within the data.
Empiric’s algorithmic variance analysis evaluates differences between physicians on a like procedure basis through the analysis of cleaned Doctor Procedure Cards and supply utilization.
*Module in Development
Comparable Supply Categories – Empiric has created clinical supply categories using a combination of Empiricist and Supply Chain expert knowledge and machine learning. These categories make it easier to find a low cost alternative to high cost items by categorizing items how and when they are used in a surgical case.
Empiric Opportunity Playbook – Empiric’s proprietary compendium of Service Line specific opportunities based on Empiric’s work to-date. The Playbook enables faster identification and implementation of opportunities at new clients. The database includes supply items, evidence-based research, and example presentations to surgeons.
Implant Analytics – Empiric’s deep dive analysis into variation opportunity specific to implants and Physician Preference Items (PPI). Client specific pricing and the use of constructs are taken into account with cohorts serving to provide a level playing field of clinically similar patients.