Evaluating service quality dimensions as antecedents to outpatient satisfaction using back propagation neural network

Abstract

Nowadays the ability to provide outpatient services with exceptional quality is paramount to long-term survival of hospitals, as the revenues from outpatient services are predicted to equal or exceed inpatient revenues in the near future. Identifying the relative weight of different dimensions of healthcare quality service which concur together to determine outpatients satisfaction is very important, as it can help healthcare managers to allocate resources more efficiently and identify managerial actions able to guarantee higher levels of patients' satisfaction. This study proposes the use of Artificial Neural Network (ANN) as a knowledge discovery technique for identifying the service quality factors that are important to outpatient. An ANN model is developed on data from a panel of outpatients of public healthcare services.

Design of a Patient-Centered Appointment Scheduling with Artificial Neural Network and Discrete Event Simulation

“…In this study, we constructed an ANN model to predict an individual patient's treatment duration for an appropriately appointment. Back-propagation artificial neural network (BP-ANN) is one of the most representative and most common used model among the artificial neural networks [16] [17]. In general, the architecture of a BP-ANN involves three layers, the first layer represents the input vector that receives information, the last layer is the output that calculates results, and the hidden layer processes information (demonstrate in Figure 2).…”

“…To construct the prediction model of an individual's treatment durations, a standard back-propagation algorithm for feed-forward neural networks was applied due to its relative simplicity and stability [17]. The BP-ANN predictive model were established by using the validated data which excluded the collected data with missing value(s).…”

“…, where I and O is the number of neurons in the input and output layers respectively; c is a constant ranging from 0 to 10 [17]. We changed the number of hidden neurons from three to twelve, increased 0.05 of the learning rate from 0.1 to 0.5.…”

Preventive Healthcare: A Neural Network Analysis of Behavioral Habits and Chronic Diseases

“…These networks have the ability to learn from experience, generalize from previous examples, and abstract relevant features from irrelevant data inputs [24]. Neural network applications in the domain of chronic disease management include automatic prediction of exacerbations in Chronic Obstructive Pulmonary Disorder [25]; diagnosing myocardial infarction [26,27,28,29], coronary artery disease [30,31,32], chronic heart failure [33]; predicting heart diseases [34]; classifying other types of heart disease [35]; diagnosing diabetes on small mobile devices [36]; and identifying behavioral health problems of patients who are at high risk for hospital admission [37]. In most chronic diseases, early detection is beneficial for effective management of the conditions.…”

Combined medical quality assessment using the evidential reasoning approach

“…The public craves highquality healthcare services, and people choose appropriate hospitals on the basis of medical quality information they can collect about target hospitals (Dijs-Elsinga et al, 2010;Glazer, McGuire, Cao, & Zaslavsky, 2008;Marang-van de Mheen et al, 2011). Meanwhile, hospital managers seek to improve medical quality, as quality is the key factor for attracting public or private funding and healthcare service consumers (Campbell, Roland, & Buetow, 2000;Carlucci, Renna, & Schiuma, 2013;Glazer et al, 2008;Normand et al, 2008). In developed countries such as the US, healthcare researchers have conducted systematical medical quality research since the 1960s (Donabedian, 1966;Donabedian, 1968;Feinstein, 2002;Mcqueen, Mittman, & Demakis, 2004).…”