Home // eTELEMED 2013, The Fifth International Conference on eHealth, Telemedicine, and Social Medicine // View article

Evaluation of e-Health by PSM (Propensity Score Matching) Method

Authors:
Yuji Akematsu
Masatsugu Tsuji

Keywords: propensity score matching; sample selection bias; inpatient; outpatient; medical expenditure

Abstract:
The authors have been conducting successive estimations on the effect of e-Health on medical expenditures and outpatient treatment days for chronic diseases using survey data from Nishi-aizu Town, Fukushima Prefecture, Japan. The reason why this town was chosen is that it has been implementing e-Health more than 15 years and is one of the most successful examples. This paper uses several other outcome variables such as medical expenditures and treatment days of outpatient and inpatient, and compares those outcomes among two groups such as 199 treatment (users) of e-Health and 209 control (non-users) selected from residents. In this paper, the propensity score matching (PSM) method, a rigorous analytical method is used to overcome sample selection bias which is contained in data in the process which samples were selected. PSM is a method to choose subjects from two groups with exact similar characteristics except for their use or non-use of e-Health. After eliminating biases, the effect of e-Health on medical expenditures and treatment days was estimated. To obtain robust results, two different matching methods were applied, that is, caliper matching, and Epanechnikov kernel matching. The results demonstrated that the treatment group has lower medical expenditures for chronic diseases than the control group. Using other outcomes enables international comparison of e-Health projects with the same standard. Such comparisons are also presented.

Pages: 102 to 107

Copyright: Copyright (c) IARIA, 2013

Publication date: February 24, 2013

Published in: conference

ISSN: 2308-4359

ISBN: 978-1-61208-252-3

Location: Nice, France

Dates: from February 24, 2013 to March 1, 2013