Three Approaches to Predictive Analytics in Healthcare
When it comes to predictive analytics, the message is clear: it’s the intervention that matters most. Crunching all the big data in the world and using fancy machine learning math won’t improve patient care unless the data is tied directly to making appropriate and timely decisions.
For predictive analytics to be successful in healthcare, it must have three characteristics: timely, role-specific, and actionable. And like a three-legged stool falling over when it’s missing one of its legs, missing any of these three requirements significantly increases the chance of failure and waste during clinical implementation.
Health Catalyst uses three types of predictive analytics that directly support clinical decision making and inform administrative priorities and actions:
- Risk stratification (risk scores)
- Simulation (what-if scenarios)
- Mapping (geo-spatial analysis)
Approach #1: Risk Stratification
Risk stratification scoring can help health systems prioritize clinical workflow, reduce system waste, and create financially efficient population management programs. Established risk stratification scores of low-risk, high-risk, and rising-risk populations can play key roles in several healthcare scenarios. For example, a calculated risk score can help reduce system waste by setting workflow priorities for patient follow-up in heart failure patient populations. Based on this predictive risk score ranking, care managers are prompted to focus on those patients at highest risk and preemptively intervene with medication reconciliation, home visits, or follow-up appointments.
Other methods to calculate population risk include the CMS-HCC (Centers for Medicare and Medicaid Hierarchical Condition Categories) approach or population comorbidity algorithms, such as Elixhauser or Charlson-Deyo, which score to approximate the expected disease burden of a given geographic area. Patient-facing surveys, such as SF – 12® and SF – 36® are other approaches to approximating risk.
Approach #2: Simulation
Another type of predictive approach Health Catalyst uses with its partners is simulation (what-if scenarios), which are invaluable when decision makers want to ask simple “what if” questions about a given clinical area or administrative function.
For example, as variation is reduced in a specific clinical care process, Health Catalyst’s Key Process Analysis (KPA) application calculates the amount of opportunity dollars available to capture. The sum of these care process opportunity dollars across an entire health system can be substantial. The KPA tool also helps prioritize which clinical areas to target, initially, using the Pareto 80/20 rule.
A more clinically focused example from the advanced analytics application for the appendectomy population module features a length-of-stay simulation, which demonstrates the financial impact (dollars saved) and improved patient satisfaction of shorter patient stays in the hospital. Predictive analytics used in a simulation environment gives clinicians and administrators a glimpse into “what if” scenarios and the likely outcomes of a given combination of events.
Approach #3: Mapping
Geographic information systems (GIS) and geo-spatial analysis is a well-developed industry, having passed its 50th anniversary mark. Despite those five decades, the obvious overlap to leveraging GIS tools with healthcare and geomedicine is just now coming into focus. Only recently have large sets of national claims and payment data been made public. Additionally, private and non-profit institutions have large amounts of operational and patient data that could be mapped.
Mapping layers and predictive analytics are routinely used to forecast weather, optimize supply chains, and support military deployment. A natural extension of these established approaches is to leverage GIS mapping of healthcare facilities, patient disease burden, and accountable care populations. Mapping is an effective visual approach to analytics and decision making.
Appropriate Intervention: What Matters Most in Healthcare Predictive Analytics
ROI does not reside in data itself, but in the timely interpretation of that data followed by appropriate intervention. When a calculated metric is timely, role specific, and actionable, the return on dollars and quality follow.
All the predictive bells and whistles in the world will not improve healthcare one iota without thoughtful, meaningful intervention and clinical leaders willing to base that intervention on proven predictive data.
- Machine Learning in Healthcare: How it Supports Clinician Decisions—and Why Clinicians are Still in Charge
- 3 Reasons Why Comparative Analytics, Predictive Analytics, and NLP Won’t Solve Healthcare’s Problems
- The Top Three Recommendations for Successfully Deploying Predictive Analytics in Healthcare
- Understanding Risk Stratification, Comorbidities, and the Future of Healthcare
- Top Five Elements of an Effective Readmission Risk Score
Would you like to use or share these concepts? Download this Predictive Analytics in Healthcare presentation highlighting the key main points.