Identification of Risk Factors in Clinical Texts through Association Rules

• DOI: 10.26615/978-954-452-044-1_009
• Publication Date: 2017-12-23T21:42:31Z
• Authors: Svetla Boytcheva; Ivelina Nikolova; ; Galia Angelova; ; Zhivko Angelov
• Keywords: Identification; Medical record

We describe a method which extracts Association Rules from texts in order to recognise verbalisations of risk factors.Usually some basic vocabulary about factors is known but medical conditions are expressed clinical narratives with much higher variety.We propose an approach for data-driven learning specialised which, once collected, enables early alerting potentially affected patients.The illustrated by experimens records patients Chronic Obstructive Pulmonary Disease (COPD) and comorbidity CORD, Diabetes Melitus Schizophrenia.Our input data come the Bulgarian Diabetic Register, built using pseudonymised collection outpatient 500,000 diabetic generated CORD analysed context demographic, gender, age information.Valuable anounts meaningful words, signalling factors, discovered high precision confidence.