Related Experiment Videos
Purpose/Objectives:
The intent of this article is to explain predictive modeling-a statistical tool-as it applies to the practice of case management. While actuaries and financial experts focus on the statistical relevance of predictive risk scores, case managers will benefit from knowing what these scores mean and how interpreting and applying them into meaningful action can lead to improved patient outcomes.
Primary Practice Setting(S):
Predictive modeling can be used by physician practice groups, managed care organizations, worksite wellness programs, and any organization desiring to identify the most actionable population for targeted outreach, education, and management.
Findings/Conclusions:
Predictive modeling is a technological tool that functions as an electronic claims canvasser searching for predefined variables of interest. This tool is used to identify high-cost diagnoses that, in turn, provide a risk score indicative of the likelihood to utilize more healthcare resources and dollars than persons of the same age and gender. By targeting specific diagnoses or conditions, clinicians can define precise patient interventions such as appointment reminders, weight checks, and dietary compliance; assess the intended results of prescribed medications, or simply to provide education and support. The validation of predictive modeling's true value lies in the thorough evaluation of the outcomes of these interventions. The success of predictive modeling can be demonstrated only by a combination of specific data and evidence-based intervention leading to improved models of healthcare delivery and improved patient outcomes.
Implications For Case Management Practice:
Using predictive models, case managers will be able to target the most actionable patients who will benefit from targeted outreach and education. Case managers will gain an understanding of how a numerical value can lead to the development of a comprehensive collaborative care plan with the patient and other members of the interdisciplinary team to not only improve the patient's overall health status but to engage the patient in his or her own care, empowering the patient to take responsibility for his or her own health status.
Related Concept Videos
Predicting Reaction Outcomes
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Steps in Outbreak Investigation
Guidelines for Writing Outcome
Patient outcomes reflect the patient's response to the goal rather than what the nurse aims to achieve. Terminology should be observable and measurable to avoid the reader's interpretation. The desired outcome should be realistic and achievable in the designated care timeframe. Expected outcomes should align with adjunctive therapies. The outcome should enhance care evaluation by...
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
The...
Methods of Medium Optimization