McKinsey and BeyondCore conducted a hypothesis-free analysis of 30M+ commercial claims lives to predict which patients are most likely to experience extreme increases in their total annual medical expenses. The most interesting predictors of such increases are typically multi-variable ones such as: patients who have been diagnosed with depression, who have not been refilling their prescription medications, and have recently been discharged for a PTCA heart procedure are most likely to see a 100%+ rise in their healthcare costs in the next year. In other words: if I’m a hospital who has started to take on risk for my population (e.g. through an ACO), when I see a patient leave my hospital with that particular patient profile, I should invest to intervene with coordinated care to manage their health and manage down their total medical costs. The results of this analysis provide health systems with a prioritized set of such rules that allow them to generate the greatest value from the investments they make in care coordination.
From an analytical perspective, due to the large number of potential variable combinations, it is impossible to preconceive of and evaluate all of the potential hypotheses. Moreover, even when a statistically-significant pattern is detected, care must be taken to adjust for the confounding effects of all other variables. The amount of analytical effort to conduct such an analysis for a dataset spanning demographics, diagnoses, treatments, preexisting conditions, medication usage, etc. is not manually tractable. Consequently, to make the analysis tractable, analysts tend to cherry-pick variables relevant for specific hypotheses. This however prevents a comprehensive review of the overall context. You see a series of snapshots rather than the complete movie. Using the power of Big Data analytics, the consultancy Objective Health, a McKinsey & Company solution for healthcare providers, reversed the traditional approach, first using BeyondCore to automatically evaluate a million variable combinations to detect statistically significant patterns and then using experts to form and test hypotheses that might explain the identified patterns. Actionable insights detected by this project may be used by healthcare payers and providers to target wellness programs and other remediation efforts at the populations most likely to see the greatest cost increase absent such intervention. ACOs may also use such approaches to detect populations who are most likely to respond to efforts to reduce their healthcare expenses. In this session we will explain the methodology used, share several actionable patterns and engage the audience in an open discussion of what the analysis revealed about our healthcare costs and how we can most effectively manage them at a patient-specific level.
Tim Darling leads Research and Product Development at Objective Health. Objective Health is the branch of McKinsey & Company’s healthcare practice charged with serving community hospitals and health systems. He is responsible for building the platform of tools and analytics solutions that power Objective Health’s products and client service efforts. Tim is an expert on leveraging big data and cutting edge analytics to bring strategic and financial insights to US hospitals and health systems. Prior to joining McKinsey in 2010, Tim led the development of enterprise web applications at the University of Maryland. He has an MBA from the Carnegie Mellon’s Tepper School of Business and BS in both Mathematics and Computer Science from the University of Maryland, College Park.
Arijit Sengupta is the CEO of BeyondCore and the Chair of the Big Data and Advanced Analytics SIG at the Service Research and Innovation Institute (SRII). BeyondCore received awards such as Gartner Cool Vendor in Business Process Services 2012, GigaOm Structure Launchpad 2011 and the UP2010 Overall Most Innovative Cloud Provider. Arijit has guest lectured at Stanford and other universities; spoken at conferences in a dozen countries; and was written about in The World Is Flat release 3.0, the New York Times, San Jose Mercury News, and other leading publications. Arijit held leadership positions at several eBusiness initiatives and previously worked at Oracle, Microsoft, and Yankee Group. He has been granted eight patents in the domains of advanced analytics, business process improvement, operational risk, privacy and information security. Arijit holds an MBA with Distinction from the Harvard Business School and Bachelor degrees with Distinction in Computer Science and Economics from Stanford University.
For exhibition and sponsorship opportunities at Strata Rx conference, contact Sharon Pierce at (203) 304-9476 or firstname.lastname@example.org
For information on trade opportunities with O'Reilly conferences email mediapartners
View a complete list of Strata Rx 2013 contacts