Applying AI to healthcare's biggest opportunity: Clinical variation

Mercy and Intermountain, two of the largest and most innovative hospital systems in the United States, have recently applied AI to tackle clinical variation within their systems. Todd Steward and Lonny Northrup discuss the application of machine intelligence for optimizing care and provide valuable insights into practice variation for improving clinical pathways.

How do we use our records of the past to inform us about how we should treat patients in the future? This question is simple to ask but surprisingly difficult to answer. Current approaches are difficult to implement, due to both the amount and the complexity of medical data. Mercy and Intermountain, two of the largest and most innovative hospital systems in the United States, have recently applied AI to tackle clinical variation within their systems. Todd Steward and Lonny Northrup discuss the application of machine intelligence for optimizing care and provide valuable insights into practice variation for improving clinical pathways. By constructing topological summaries of the space of treatments for a medical procedure, it is possible to get a handle on EMR data that has tens of thousands of features that vary over time. This compressed representation of the data allows accurate identification of groups of treatments in the past that lead to good clinical outcomes. Grouping medical treatments—highly complex series of events—was a previously unsolved problem. Mercy was able to tackle it by blending state-of-the-art techniques from genomics with expertise in topological mathematics. Once the data has been segmented in this fashion, it is possible to adapt other methods from biology and signals processing to the problem of determining optimal outcomes. The approach also links predictive machine learning methods like regression and classification to perform real-time carepath editing. What this means is that any proposed carepath can immediately optimized further based on the current situation as determined by the physician. In this manner, algorithmic approaches can effectively side-step the problem of data complexity and size, letting care givers work hands-on with their data, receiving decision support backed by hundreds of thousands of impartial records instead of their own human experiences and biases. More generally speaking, this framework can be thought of in terms of process optimization: given some process containing a series of complex actions and records of previous processes, how can we find the optimal actions? It need not be restricted to standards construction: if one is halfway through a series of steps, the method could be extended to suggest the next most appropriate action. The applications to healthcare are multifarous and also extend to any domain where longitudinal records of any business process are kept (banking, retail, manufacturing, etc.).