# A Systematic Approach to Detect Hierarchical Healthcare Cost Drivers and Interpretable Change Patterns

## TL;DR

This paper introduces a systematic, hierarchical method using enhanced SPC algorithms to identify and interpret key healthcare cost drivers and change patterns, aiding early intervention and cost management.

## Contribution

It presents a novel hierarchical and multi-resolution approach with enhanced SPC algorithms for detecting interpretable healthcare cost change patterns.

## Key findings

- Effective identification of high-impact cost drivers
- Interpretable change patterns linked to demographic and clinical factors
- Quantification of cost impacts due to utilization changes

## Abstract

There is strong interest among payers to identify emerging healthcare cost drivers to support early intervention. However, many challenges arise in analyzing large, high dimensional, and noisy healthcare data. In this paper, we propose a systematic approach that utilizes hierarchical and multi-resolution search strategies using enhanced statistical process control (SPC) algorithms to surface high impact cost drivers. Our approach aims to provide interpretable, detailed, and actionable insights of detected change patterns attributing to multiple demographic and clinical factors. We also proposed an algorithm to identify comparable treatment offsets at the population level and quantify the cost impact on their utilization changes.