AI Insights

There was a lot of excitement when we debuted CertHLM at HIMSS26, as it is the first language model built specifically for healthcare intelligence and decision support.

Today, AI is rapidly becoming the go-to solution for organizations across the healthcare continuum seeking meaningful, impactful improvements.

These days, it seems like AI is being positioned as the answer to almost every problem in healthcare analytics—promising faster decisions, streamlined workflows, and smarter outcomes.

Deep learning will eventually replace most of the regression models so widely used for risk prediction in the healthcare industry today. We describe here a history of deep learning findings at Certilytics—culminating in our latest innovations in the GenAI space—using choice examples spanning eight years of research, development, and operational experience. These proofs of concept (POCs) turned models, turned products, share in common a three step approach to adapting cutting edge machine learning techniques to healthcare:

Deep learning has opened new possibilities for healthcare predictive modeling, enabling us to expand our clinical risk prediction library from dozens of models to over 1,000. Our deep learning approach has vastly expanded the universe of target functions that can be modeled, meaning we can train a single model that predicts hundreds of variables representing every aspect of a member’s health profile, all integrated in a unified risk framework. This model, which we call the All CORE Condition (ACC) Model, provides deeper insight into member and population health than ever possible before—while also making model training and deployment faster and more reliable. We can now train and deploy whole model suites as single model objects, obviating the need to manage hundreds or thousands of model SKUs.