A generalized semiparametric mixed model for analysis of multivariate health care utilization data

Zhuokai Li, Hai Liu, Wanzhu Tu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Health care utilization is an outcome of interest in health services research. Two frequently studied forms of utilization are counts of emergency department (ED) visits and hospital admissions. These counts collectively convey a sense of disease exacerbation and cost escalation. Different types of event counts from the same patient form a vector of correlated outcomes. Traditional analysis typically model such outcomes one at a time, ignoring the natural correlations between different events, and thus failing to provide a full picture of patient care utilization. In this research, we propose a multivariate semiparametric modeling framework for the analysis of multiple health care events following the exponential family of distributions in a longitudinal setting. Bivariate nonparametric functions are incorporated to assess the concurrent nonlinear influences of independent variables as well as their interaction effects on the outcomes. The smooth functions are estimated using the thin plate regression splines. A maximum penalized likelihood method is used for parameter estimation. The performance of the proposed method was evaluated through simulation studies. To illustrate the method, we analyzed data from a clinical trial in which ED visits and hospital admissions were considered as bivariate outcomes.

Original languageEnglish (US)
Pages (from-to)2909-2918
Number of pages10
JournalStatistical Methods in Medical Research
Volume26
Issue number6
DOIs
StatePublished - Dec 1 2017

Fingerprint

Patient Acceptance of Health Care
Semiparametric Model
Mixed Model
Healthcare
Multivariate Analysis
Hospital Emergency Service
Count
Cost of Illness
Emergency
Health Services Research
Disease Progression
Patient Care
Regression Splines
Thin-plate Spline
Clinical Trials
Health Services
Interaction Effects
Likelihood Methods
Delivery of Health Care
Exponential Family

Keywords

  • Bivariate splines
  • exponential family
  • health care utilization
  • multivariate longitudinal data
  • semiparametric regression

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability
  • Health Information Management

Cite this

A generalized semiparametric mixed model for analysis of multivariate health care utilization data. / Li, Zhuokai; Liu, Hai; Tu, Wanzhu.

In: Statistical Methods in Medical Research, Vol. 26, No. 6, 01.12.2017, p. 2909-2918.

Research output: Contribution to journalArticle

@article{8c7a5f50f53844908a28550dca4fcd7f,
title = "A generalized semiparametric mixed model for analysis of multivariate health care utilization data",
abstract = "Health care utilization is an outcome of interest in health services research. Two frequently studied forms of utilization are counts of emergency department (ED) visits and hospital admissions. These counts collectively convey a sense of disease exacerbation and cost escalation. Different types of event counts from the same patient form a vector of correlated outcomes. Traditional analysis typically model such outcomes one at a time, ignoring the natural correlations between different events, and thus failing to provide a full picture of patient care utilization. In this research, we propose a multivariate semiparametric modeling framework for the analysis of multiple health care events following the exponential family of distributions in a longitudinal setting. Bivariate nonparametric functions are incorporated to assess the concurrent nonlinear influences of independent variables as well as their interaction effects on the outcomes. The smooth functions are estimated using the thin plate regression splines. A maximum penalized likelihood method is used for parameter estimation. The performance of the proposed method was evaluated through simulation studies. To illustrate the method, we analyzed data from a clinical trial in which ED visits and hospital admissions were considered as bivariate outcomes.",
keywords = "Bivariate splines, exponential family, health care utilization, multivariate longitudinal data, semiparametric regression",
author = "Zhuokai Li and Hai Liu and Wanzhu Tu",
year = "2017",
month = "12",
day = "1",
doi = "10.1177/0962280215615159",
language = "English (US)",
volume = "26",
pages = "2909--2918",
journal = "Statistical Methods in Medical Research",
issn = "0962-2802",
publisher = "SAGE Publications Ltd",
number = "6",

}

TY - JOUR

T1 - A generalized semiparametric mixed model for analysis of multivariate health care utilization data

AU - Li, Zhuokai

AU - Liu, Hai

AU - Tu, Wanzhu

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Health care utilization is an outcome of interest in health services research. Two frequently studied forms of utilization are counts of emergency department (ED) visits and hospital admissions. These counts collectively convey a sense of disease exacerbation and cost escalation. Different types of event counts from the same patient form a vector of correlated outcomes. Traditional analysis typically model such outcomes one at a time, ignoring the natural correlations between different events, and thus failing to provide a full picture of patient care utilization. In this research, we propose a multivariate semiparametric modeling framework for the analysis of multiple health care events following the exponential family of distributions in a longitudinal setting. Bivariate nonparametric functions are incorporated to assess the concurrent nonlinear influences of independent variables as well as their interaction effects on the outcomes. The smooth functions are estimated using the thin plate regression splines. A maximum penalized likelihood method is used for parameter estimation. The performance of the proposed method was evaluated through simulation studies. To illustrate the method, we analyzed data from a clinical trial in which ED visits and hospital admissions were considered as bivariate outcomes.

AB - Health care utilization is an outcome of interest in health services research. Two frequently studied forms of utilization are counts of emergency department (ED) visits and hospital admissions. These counts collectively convey a sense of disease exacerbation and cost escalation. Different types of event counts from the same patient form a vector of correlated outcomes. Traditional analysis typically model such outcomes one at a time, ignoring the natural correlations between different events, and thus failing to provide a full picture of patient care utilization. In this research, we propose a multivariate semiparametric modeling framework for the analysis of multiple health care events following the exponential family of distributions in a longitudinal setting. Bivariate nonparametric functions are incorporated to assess the concurrent nonlinear influences of independent variables as well as their interaction effects on the outcomes. The smooth functions are estimated using the thin plate regression splines. A maximum penalized likelihood method is used for parameter estimation. The performance of the proposed method was evaluated through simulation studies. To illustrate the method, we analyzed data from a clinical trial in which ED visits and hospital admissions were considered as bivariate outcomes.

KW - Bivariate splines

KW - exponential family

KW - health care utilization

KW - multivariate longitudinal data

KW - semiparametric regression

UR - http://www.scopus.com/inward/record.url?scp=85038826440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038826440&partnerID=8YFLogxK

U2 - 10.1177/0962280215615159

DO - 10.1177/0962280215615159

M3 - Article

VL - 26

SP - 2909

EP - 2918

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

IS - 6

ER -