Application of Probabilistic Techniques for the Development of a Prognosis Model of Stroke Using Epidemiological Studies

Introduction

Medical informatics is the discipline dedicated to the systematic processing of data, information and knowledge in medicine and healthcare (Shortliffe & Cimino, 2006). As has been mentioned previously (Haux, 2010), there is a need for introducing and exploring new theories, concepts or methods that significantly contribute to efficient, high-quality healthcare, improvements in quality of life and/or to the progress of biomedicine and the computer, health and information sciences. The growing rate of chronic diseases such as diabetes, hypertension, lower back pain, heart disease, and cardiovascular disease accounts for more than half of the overall growth of healthcare costs. For this reason, healthy living is an essential topic in the health field. In recent years, the Internet has been a mean to increase individual participation in disease prevention and health promotion. A study (Lemire, Paré, Sicotte, & Harvey, 2008) confirms the importance of the credibility of information on the frequency of Internet use, as a preferred source of information on personal health. It also shows the potentially influential role of the Internet in the development of personal knowledge of health issues. With the use of Internet, the development of Medical Differential Diagnosis and Therapy systems using computational intelligence, has gained momentum over the last years (Zhao, Yanxiang, & Hui, 2005). Sciences, biology and medicine are considered (Cohen, 2004) to have been among the most progressive scientific fields during the twentieth century, and such advancements are expected to have a tremendous impact on the information technology (IT) application domain landscape. However, leveraging the potential of knowledge-intensive applications in medical differential diagnosis is a critical issue to be tackled, in order to rely on the accuracy and efficiency of diagnosis or therapy systems.

This work presents the design of a prognosis model for the prevention of suffering stroke. Stroke is a cerebrovascular disease characterized by an abrupt interruption of blood supply to the brain, which triggers a set of symptoms that can be variable, depending on the brain area affected (80% of strokes are ischemic and the rest hemorrhagic). Stroke and heart attacks are the most common cardiovascular diseases and the leading cause of mortality in developed countries, there are many risk factors involved of suffering this pathology (i.e. such as overweight and smoking among other factors that can be decreased or even stopped with a correct approach). In this sense, the development of tools which can warn of the risk of suffering an illness like a stroke is crucial, where part of their risk factors are related with healthy living.

The paper is organized as follows: Methods section outlines relevant literature in the area and the core of the approach presenting a deep analysis of the epidemiology of the stroke risk factors and the proposed probabilistic model, based on the independance of the risk factors. Also a very deep explanation of the probabilistic calculus that had been done to estimate the final probability is presented. In Results’ section we present a specific example of use given the data provided by the epidemiological sources and it includes the evaluation (design and results) performed to assess the quality of the proposed model. Conclusions and future work are discussed in the Discussion section.