Step towards Improving the Voluntary Interruption of Pregnancy by Means of Business Intelligence

Introduction

The use of Information and Communication Technologies (ICT) are increasingly, occupying an important place in society. The health sector is no exception, as these among other things, can provide complete and reliable information for healthcare professionals, allowing to support their clinical and administrative decisions and consequently decreasing medical errors associated to these decisions (Pinto, 2009).

Besides, ICT have a high potential to facilitate information sharing, communication and collaboration between health professionals, increasing the quality and efficiency of the health system as well as the use of Electronic Health Records (EHR) (Abelha et al., 2007; Khodambashi, 2013; Portela et al., 2010) is one of the goals.

In recent times, Business Intelligence (BI) technologies have been the target of interest to health professionals and to the Information Technology (IT) professionals, due to its applicability in EHR (Bonney, 2013). BI is a process that encompasses several methodologies, applications and technologies for collecting, storing, manipulating, analysing and providing access to data in order to help enterprise users making better and faster business decisions. Thus BI has the ability to operationalize the repository content of EHR in supporting evidence-based practice and improving the quality of healthcare delivery (Bonney, 2013; Mettler & Vimarlund, 2009; Portela et al., 2010).

In the case of healthcare organizations, the majority of clinical data documenting their daily activities are stored in a Relational Database Management System (RDBMS). Because of the extensive amount of information, this information is stored in different ways and therefore highly heterogeneous with each other. On the other hand, a decision-making process, where it is necessary to integrate multiple data provided by clinical, medical, financial and administrative systems and where the sources are quite heterogeneous, large and complex becomes extremely important to meet the data quality that directly interferes in the success of the Knowledge Discovery Database (KDD) process (Mettler & Vimarlund, 2009; Raquel & Oliveira, 2012). So, with this increasing amount of information there is also a corresponding need to apply Data Mining (DM) technologies to extract knowledge from information / data stored in databases and providing real-time decisions (Bonney, 2013). Most clinical data are not structured and the DM techniques work well with structured data. It is inferred another advantage to using BI as a decision support technology since it allows the combination of structured and unstructured data (Bonney, 2013).

Furthermore, it can be stated that the Information Systems interoperability in an institution is one of the key factors in the decision-making process. Interoperability (Cardoso, Marins, Portela, Santos, et al., 2014) ensures systems standardization and allows passing all the inherent complexity of the different data sources ensuring data quality.

Thus, this chapter is focused on presenting the architecture of a global BI platform that can be used in Maternity Care Institution, taking as a case study the Centro Materno Infantil do Norte (CMIN) in Porto, Portugal. It was planned apply BI and DM techniques in order to develop a platform where it is possible generate useful Key Performance Indicators (KPIs) (clinical and management) for healthcare professionals in the context of the Voluntary Interruption of Pregnancy (VIP) module. For the development of this platform, one Data Warehouse (DW) was built using the star schema and a set of DM models were induced. For better accuracy of the solution and validity of information generated, all the work has been pleading with clinicians and specialists.

The solution in development is a pervasive real-time web-based BI application and due to their characteristics allows it to be accessed anywhere and anytime.