NOVEL DATA MINING ALGORITHMS FOR ANALYSIS OF ELECTRONIC HEALTH RECORDS

Abstract

Medical health providers use electronic health records (EHRs) to store information about patient treatment to support patient care management and securely share health information among healthcare organizations. EHRs have also been used in healthcare research in problems such as patient phenotyping, health risk prediction, and medical entity extraction. In this thesis, we focus on several important issues: (1) how to convert natural text from medical notes to vector representations suitable for deep learning algorithms, (2) how to help healthcare researchers select a patient cohort from EHRs, and (3) how to use EHRs to identify patient diagnoses and treatments. In the first part of the thesis, we present a new method for learning vector representations of medical terms. Learning vector representations of words is an important pre-processing step in many natural language processing applications. For example, EHRs contain clinical notes that describe patient health conditions and course of treatment in a narrative style. The notes contain specialized medical terminology and many abbreviations. Learning good vector representations of specialized medical terms can improve the quality of downstream data analysis tasks on EHR data. However, the traditional approaches struggle to learn vector representations of rarely used medical terms. To overcome this problem, we developed a neural network-based approach, called definition2vec, that uses external knowledge contained in medical vocabularies. We performed quantitative and qualitative analysis to measure the usefulness of the learned representations. The results demonstrate that definition2vec is superior to the state-of-the-art algorithms. In the second part of the thesis, we describe a new visual interface that helps healthcare researchers select patient cohorts from EHR data. Process of identifying patients of interest for observational studies from EHR data is known as cohort selection, a challenging research problem. We considered a problem of cohort selection from medical claim data, which requires identifying a set of medical codes for selection. However, there are tens of thousands of unique medical codes, and it becomes very difficult for any human to decide which codes identify patients of interest. To help users in defining a set of codes for cohort identification, we developed an interactive system, called Medical Claim Visualization system (MedCV), which visualizes medical code representations. MedCV analyzes a medical claim database and allows users to reason about medical code relationships and define inclusion rules for the selection by visualizing medical codes, claims, and patient timelines. Evaluation of our system through a user study indicates that MedCV enables domain experts to define inclusion rules efficiently and with high quality. The third part of the thesis is a study of the definition of acute kidney injury (AKI), which is a condition where kidneys suddenly cannot filter waste from the blood. AKI is a major cause of patient death in intensive care units (ICU) and it is critical to detect it early. Recently published KDIGO medical guideline proposed a clinical definition of AKI using blood serum creatinine and urine output. The KDIGO definition was developed based on the expert knowledge, but very little is known about how well it matches the medical practice. In this study, we investigated publicly available EHR data from 47,499 ICU admissions to determine the concordance between the KDIGO definition and AKI determination by the medical provider. We show that it is possible to find a formula using machine learning with much higher concordance with the medical provider AKI coding than KDIGO and discuss the medical relevance of this finding.