Association Patterns of Ontological Features Signify Electronic Health Records in Liver Cancer

Abstract

Electronic Health Record (EHR) system enables clinical decision support. In this study, a set of 112 abdominal computed tomography imaging examination reports, consisting of 59 cases of hepatocellular carcinoma (HCC) or liver metastases (so-called HCC group for simplicity) and 53 cases with no abnormality detected (NAD group), were collected from four hospitals in Hong Kong. We extracted terms related to liver cancer from the reports and mapped them to ontological features using Systematized Nomenclature of Medicine (SNOMED) Clinical Terms (CT). The primary predictor panel was formed by these ontological features. Association levels between every two features in the HCC and NAD groups were quantified using Pearson's correlation coefficient. The HCC group reveals a distinct association pattern that signifies liver cancer and provides clinical decision support for suspected cases, motivating the inclusion of new features to form the augmented predictor panel. Logistic regression analysis with stepwise forward procedure was applied to the primary and augmented predictor sets, respectively. The obtained model with the new features attained 84.7% sensitivity and 88.4% overall accuracy in distinguishing HCC from NAD cases, which were significantly improved when compared with that without the new features.

Ontology-Based Approach for Liver Cancer Diagnosis and Treatment

“…They aim to improve knowledge engineering achievements in medical purposes. They include ontologies for medical image interpretation such as [24,26,35,39,40]. These works focus basically on medical image features and finding.…”

“…Also, a great deal of effort has been devoted to studying biomedical ontologies. Chan et al [24] propose an EHR (electronic health record)-based approach, allowing the examination of medical data such as clinical reports. This system is not only dedicated to offer information about patients but also provides a clinical decision support by distinguishing HCC diseases from those reports.…”

Ontologies for Liver Diseases Representation: A Systematic Literature Review

“…To validate these approaches, there exist several followed techniques to improve the proposed work efficiency. Some works try to use standard measurements such as recall and accuracy percentages, techniques used by [35] and [12]. Other works test their approaches with real data extracted mainly from clinical and medical sources.…”

“…Modeling HCC reports via semantic representation is the objective of this section. In this context, [35][36] and [37] presented ontological approaches to analyze medical reports. For [35], it proposed an Electronic Health Record (EHR) based system dedicated to deal with medical data.…”

“…In this context, [35][36] and [37] presented ontological approaches to analyze medical reports. For [35], it proposed an Electronic Health Record (EHR) based system dedicated to deal with medical data. Three phases in this approach (1) collecting real radiological reports tacked randomly (2) extracting information from the treated cases and (3) clinical terms were extracted according to SNOMED CT vocabulary.…”