What predictive modeling capabilities do you have?
Response: Data modeling and algorithm development are performed using industry-leading tools for data mining and supervised machine learning. Catalyst has recently hired a research director to oversee our predictive algorithm development and incorporation into key data marts.
Ongoing efforts include decision tree and regression models for a generalized predictor of hospital readmissions using variables such as length of stay, age at admit, APR-DRG severity of illness, discharge day, discharge time, total number of admissions, etc. Specific models are planned for patient populations such as heart failure, pneumonia, and acute myocardial infarction.
Importantly, we have internal access to millions of de-identified hospital records in both the inpatient and outpatient settings and both adult and pediatric populations. This training data is key to addressing the predictive analytics demands of clients and site customization. So when your request comes—whether it involves classification, clustering, or attribute selection—Health Catalyst has the tools, the data, and the expertise to successfully deliver top-performing predictive analytics.