With a mission to help employers save money on healthcare by improving their members’ health, CareATC was the first in its sector to implement rules-based predictive analytics for member costs and health risks at an individual level. To further improve predictive accuracy and the efficiency of its outreach programs, CareATC decided to explore artificial intelligence/machine learning (AI/ML) as an alternative to rules-based risk stratification.

‍

Impact Summary

• 75% of individuals for whom ClosedLoop’s predicted costs were more accurate than a rules-based system
• 30% of unplanned hospital admissions correctly predicted by ClosedLoop in the top 5% by risk
• 2.3X increase in identification of unplanned hospital admissions vs. baseline
  
  Read the case study to learn more.

‍