Search results

The objective of this work is twofold: firstly, to develop a model for assessing healthcare service quality (HSQ), and secondly, to evaluate the effectiveness of machine learning algorithms in predicting the quality of healthcare services.

In this study, a comprehensive literature review has been performed to identify key quality dimensions in the healthcare services domain. Delphi’s method has been used to confirm the criticality of these dimensions based on experts’ opinions and proposed a novel CIRMQUAL model. Factor analysis techniques have been used to further validate the CIRMQUAL model. Using the data collected through a questionnaire survey, a number of machine learning models have been developed to predict the customer satisfaction level based on the service quality (SQ) performance of a healthcare unit on different dimensions of the CIRMQUAL model.

The study developed a CIRMQUAL model with 14 dimensions (quality of care, safety and security, skill and conduct, staff attitude, tangibles, quality of the atmosphere, patient rights, follow-up, communication, cost of treatment, availability of resources, accessibility, waiting time and services), and these dimensions have been clubbed into four major dimensions, i.e. clinical quality, infrastructural quality, relationship and managerial quality. Furthermore, the application of machine learning algorithms has demonstrated significant accuracy in predicting SQ, highlighting its ability to improve healthcare services and the satisfaction level of patients.

Managers of healthcare units work hard to identify and address the pain points of the patients and improve the working of the healthcare units being managed by them. The availability of many scales with numerous dimensions adds to their confusion in selecting a suitable scale. The current work addresses this confusion and provides four clear areas for assessing the quality of healthcare units. By using this scale, managers can assess the quality of services provided by them, identify the dimensions of low performance, plan and take suitable corrective actions to improve the performance of their healthcare units.

A comprehensive SQ model, i.e. CIRMQUAL has been proposed as a new scale to assess SQ in healthcare units. The model has been developed after analyzing the dimensions used by many researchers available in the literature. This model can be used by future researchers to assess the SQ in healthcare units. Moreover, an attempt has been made to use artificial intelligence-based techniques for predicting customer satisfaction. Such attempts are in the initial stage for healthcare sector. Future researchers can take this concept forward and test the applicability of different machine learning techniques in different functional areas of healthcare.

Good health is of utmost importance for all human beings. In spite of the expenditure of substantial time and efforts by various stakeholders, the service delivery doesn’t match the expectations of patients. Many times, the service providers are not aware of this dissatisfaction and specific aspects of service delivery that need to be improved to reduce dissatisfaction. The model proposed will help the service providers in this regard and the service providers will be able to take focused steps. Such initiatives will definitely improve patient’s satisfaction and their social well-being.

This work is unique because it uses a novel technique to redefine the quality of services in healthcare by using a dual methodology. The research presents a model that includes various factors and it is specially developed to evaluate the quality of services in healthcare settings. This study advances the area’s progress by implementing computational tools for accurate evaluation of HSQ. The healthcare decision-makers may use this novel perspective to evaluate and enhance the quality of service.