Abstract Details
Activity Number:
|
504
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 6, 2014 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Health Policy Statistics Section
|
Abstract #313650
|
|
Title:
|
Particle Swarm Optimization for Diagnosis Code Variable Selection
|
Author(s):
|
Gregory Watson*+
|
Companies:
|
|
Keywords:
|
Particle Swarm ;
Variable Selection ;
Diagnosis Code ;
Medical Claims
|
Abstract:
|
Predicting patient health outcomes from medical claim diagnosis codes offers the opportunity for health plans or accountable care organizations to identify patients at high risk for negative outcomes and target them for early intervention. Substantial variation in health outcomes and the large number of diagnosis codes make this a challenging task; in particular, the development of an effective model depends upon successfully discerning the subset of codes important for prediction. Particle swarm optimization is a population-based optimization technique that has been shown to be an effective tool for solving many types of optimization problems, including variable selection. This paper employs a modified particle swarm optimizer to identify diagnosis codes most important for predicting particular health events. The algorithm is demonstrated on Medicaid claims collected over a two year period on 3,917 HIV positive Medicaid beneficiaries in Southern California.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.