Impact of Size, Location, Symptomatic-Nature and Gender on the Rupture of Saccular Intracranial Aneurysms.

Ruptured intracranial aneurysms are associated with a high rate of mortality and disability due to the difficulty in predicting the rupture and complexity of the condition itself. Clinical narratives such as progress summaries and radiological reports, etc. contain key biomarkers, medical signs, and symptoms. By applying ontology-based information extraction on clinical narratives to extract important evidences and subsequently using machine learning can help to make decision support tools for complex decision making such as prediction of aneurysm rupture. According to best of our knowledge, there doesn't exist any work to extract clinical features from clinical narratives to predict the rupture of intracranial/Brain aneurysms (BA). While no single factor individually contributes to the risk of rupture of a BA, it is important to consider the combined impact of these aspects to understand the rupture probability of the aneurysm. In this paper, we explore the impact of size as a relative factor in saccular aneurysms with respect to location, gender and symptomatic/asymptomatic aspects of BA. Our study involves descriptive and inferential statistical data analysis on features extracted from retrospective electronic health records (EHRs) using natural language processing (NLP) and ontology-based information extraction techniques. Our analysis shows that size alone is not the sole contributor for rupture but the combination of size, location and patient's gender can influence aneurysm ruptures. Our results also show interesting insight that on same vasculature location, the average size of ruptured aneurysms for females is always smaller than that of males.