Combine your Powers of AI-enabled Data Analytics, Machine Learning and Expert Systems for Maximum Return
Written by Justin Schaper, Chief Technology Officer and Megan Bultema, Chief Data Scientist
Artificial Intelligence or AI is revolutionizing healthcare data analytics and changing the way we predict, learn, and act based on insights gained through AI-powered data models. At Empiric Health, we have learned that solving healthcare problems requires multiple types of solutions and technologies. Empiric uses technologies such as AI including Natural Language Processing (NLP), Machine Learning (ML) and Expert Systems to craft solutions for identifying and addressing unwarranted clinical variation in surgery. In some instances, we’ve found that combining technologies into a single solution provides a result more effective than a single technology alone can deliver. By combining our powers of Machine Learning and Expert Systems we can maximize our return.
The Example of Cohorts
Empiric uses a combination of NLP, Expert Systems, and Machine Learning models to create and maintain Cohorts. Cohorts are an Intermountain Healthcare developed method for grouping surgical cases into clinically similar groupings that are more meaningful to surgeons and staff than the traditional groupings based on billing and reimbursement codes, such as DRGs, CPTs, and ICD-10s. To establish these groupings, Intermountain and Empiric clinicians developed a library of cohort definitions using a rules-based approach that looked at both discrete data points and concepts abstracted via NLP from the clinical operative report. These rules and definitions form a knowledge base for an Expert System referred to as the Empiric Cohort Engine. The combination of NLP and Expert System technologies create very refined, clinically meaningful set of high integrity data that enable the quick identification and root cause analysis of unwarranted clinical variance.
Healthcare Data is Complex and Inconsistent
However, healthcare data is not consistent across healthcare systems, hospitals, surgeons, and EMRs. A surgeon may use slightly different language in their operative report than their colleagues. EMRs may capture data points in slightly different ways. Coders may encode billing information in slightly different ways. These sorts of discrepancies can challenge traditional Expert Systems that rely on rules created and defined to expect a static set of possible input values. To maintain the integrity of the Cohorts, Empiric has applied Machine Learning models to work in conjunction with the Cohort Engine.
Combining Machine Learning and Expert Systems
The Machine Learning (ML) models were trained from a broad set of data to recognize patterns and make predictions about likely Cohort placement for a given surgical encounter. These predictions are done independently from the Cohort Engine. By comparing the ML predictions to the Cohort Engine output, Empiric can quickly find where potential Cohort rule specific data anomalies cause invalid Cohort placement. By combining these approaches, Empiric is able to quickly validate and provide ongoing monitoring of client data to ensure that surgical cases are in the appropriate grouping and that the integrity of the unwarranted variance analysis is supported.