
Who We Are
We are a team of high-performing data scientists, software engineers, and business strategists focused on delivering measurable business and clinical value through the implementation of practical AI.
New Analytical Breakthroughs and Data Sources Lead to Better Decision Making
Curia was built to help healthcare companies facing increasing costs of care optimize patient, member and clinician interventions focused on a wide range of chronic conditions. While risk modeling has long guided targeting and resource allocation decisions, much less analytical rigor has been applied to determining who is most likely to respond favorably to a given intervention.
New mathematical methods and advances in computing power have unlocked this ‘impactability scoring’ capability, which Curia combines with state-of-the-art risk scoring to drive significant gains in engagement programs targeted to members, patients and/or clinicians.
Curia’s Modular Architecture
integrates a wide variety of data sources and uses a combination of risk + impactability modeling to drive truly optimized decision-making

Illustrative Business and Clinical Applications
Reducing Inappropriate ED Utilization
Unnecessary ED visits account for significant added cost in the system and are not an optimal health pathway. Curia identifies the most influential outreach method per individual, allowing for successful prevention and alternative care re-routing.
Driving Course of Treatment Adherence
To achieve crucial value-based outcomes, individuals in post-acute and care management paths must receive engagement and diagnostic interventions that are most likely to drive intended behaviors.
Encouraging Preventative Care Actions
Optimizing Commercial Programs
Driving the highest percentage of member / patient population to enroll in needed dietary programs, get their flu shots or schedule overdue cancer screenings requires allocating resources to the most effective intervention type per individual.
Carefully analyzing which patients are most likely to respond to various interventions using modern ML causal intervention models can dramatically improve ROI on programs ranging from detailing digital outreach to pull-through to adherence.
Understanding who is at greatest risk for chronic condition complications or readmission is a crucial component of prevention. But, measuring the causal effect of planned interventions on the likelihood of more positive health / financial results is essential for decision makers to deliver impactful targeting at the individual level, and maximized resource allocation on aggregate.
Decreasing Avoidable Chronic Hospitalizations and Readmission