The guiding principle that primes machine learning to reduce readmissions

As healthcare datasets become ever larger, a new paradigm is emerging in healthcare risk modeling. Specifically, machine learning algorithms are leveraging historical relationships and trends in these datasets to develop risk models that identify which patients are most vulnerable to readmission. Hospitals that want to successfully use such models to reduce their own readmissions are advised to follow a guiding principle of machine learning. 

In brief, this principle asserts that hospitals should strive to provide the right information to the right audience, at the right granularity, at the right time, in the right visualization/modality. Let's dive a little more deeply into each component. 

#1: The right information
In the context of reducing readmissions, machine learning can identify patients with the highest risk and ultimately guide clinicians as to which interventions are likely to have the broadest impact on the population. In other words, a strong ML model can provide the right information needed for patient-centered decision making in a timely manner.

#2: The right audience
These are the people directly involved in front-line interventions of patients with the highest risk. Likewise, their involvement in developing the model is critical to assure strong adoption and trust in the underlying variables, logic, and decisions. 

#3: The right granularity
Healthcare data is recorded and stored in many different sources and levels of granularity. The data can relate to the individual patient, visit, or specific event (e.g., lab test). Machine learning considers how all the different variables interact with one another and contribute to an increased risk of readmission. 

#4: The right time
There are multiple opportunities to intervene with a patient to reduce their risk of readmission (e.g., hospital admission, discharge, after discharge, etc.). The type and amount of information available for a readmission risk model to leverage is different at each of these varying points in time.

#5: The right visualization and modality
By deploying a readmission risk model such that the output is embedded in existing workflow at the point of care, the clinician can evaluate and act on information at their fingertips. Pairing best practice interventions and potential health outcomes with an alert on a patient's chart in the EHR, for example, or a daily worklist can help validate a clinician's intuition and result in better and more consistent care. 

Conclusion

Traditionally, healthcare risk models have been treated as a type of "locked box" in which only a select few have access to variables and logic contributing to the risk calculation and output. Machine learning has the potential to transform this norm by drawing from the entire EHR and other data sources, at all granularities, and applying insight towards all patients. As more clinicians and data professionals use machine learning, this insight will become more broadly gained—and used to reduce readmissions at hospitals around the country. 

About the author: Levi Thatcher, Ph.D. is Director of Data Science for Health Catalyst, a leader in healthcare data warehousing, analytics and outcomes improvement.