|
Activity Number:
|
115
- Advances in Clustering and Classification
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 8, 2022 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
|
Abstract #322461
|
|
|
Title:
|
Application of Machine Learning for Predicting Outcomes in a Random Effect Clustered Bivariate Model
|
|
Author(s):
|
Edmund Essah Ameyaw* and Seth Akonor Adjei and John Kwagyan
|
|
Companies:
|
Howard University and Northern Kentucky University and Howard University
|
|
Keywords:
|
Machine Learning;
Predictive Models;
Random Effect Models;
Clustered Bivariate Outcomes
|
|
Abstract:
|
Random effect model is routinely used in the analyses of clustered data. However, the use of clustered bivariate models for prediction is very limited. We report the development and application of a random effect (logistic-Gaussian) model for clustered bivariate binary outcomes. We use a Gauss Hermite Quadrature approach for the approximation of the marginal likelihood function. We then use a series of machine learning approaches to investigate the predictive performance of the model. We apply the approach to predict vision loss data due to diabetic retinopathy patients, viewing the pair of eyes as a bivariate outcome and discuss it performance using measures of sensitivity and specificity, and report the area under the Receiver Operator Curve (ROC) curve (AUC).
|
Authors who are presenting talks have a * after their name.
