A non-profit wanted to prove the economics of a procedure it advocated. Trexin's Actionable Analytics Jumpstart answered it in under 30 days, and showed the study should measure survival, not just cost, since untreated patients died too quickly for cost offsets to appear.
As healthcare shifts from fee-for-service to value-based care, a prestigious non-profit wanted to show (quickly and inexpensively) that a procedure it advocated paid for itself: that patients who didn’t undergo it incurred higher long-term complication costs. In short, they wanted the economics of the procedure proven from data.
We applied Trexin’s Actionable Analytics Jumpstart (a 12-step plan coordinating IT, statisticians, subject-matter experts, and a data scientist) over a three-week window, working from five years of claims across two million covered lives. The goal: a rapid prototype to inform a larger CMS study, a unified cost-and-outcome view for Acute Myeloid Leukemia (AML), and a read on the procedure’s economic value, extracting knowledge from the data rather than leaning on clinical literature alone.
The analysis found additional lymphomas in 60% of cases (plus non-cancer co-morbidity), and a five-fold spread in one-year mortality (15% to 77%). Because nearly all treated patients had multiple lymphomas, an AML-only study was an artificial distinction, and we showed a revised study should center on survival, not cost, since untreated patients died too quickly for cost offsets to appear. All in under 30 days.
Data science didn’t just answer the question, it corrected the question, before the Client spent on a larger study aimed the wrong way.
case study
case study
event
Tell us what you're trying to do. A senior practitioner will read it.
Talk to us