Enabling online studies of conceptual relationships between medical terms: developing an efficient web platform

Disease surveillance using online news: an extended study of dengue fever in India

BACKGROUND

The study demonstrates the potential in using newspaper information as a proxy for monitoring dengue fever outbreaks in India. Online newspapers are being considered as sources of information on disease surveillance, early outbreak detection, and epidemiology research. Our objective is to understand the complex dengue epidemiology and discover inter-relationships between dengue fever and local social-environmental factors by mining information from local Indian news articles.

RESULTS

We search and extract articles from the newspaper database, LexisNexis. News articles related to dengue fever in India are analyzed together with local environmental, climate, and population data in both temporally and spatially to study disease epidemiology. We also examine the influence of newsworthiness for constructing a disease surveillance system. In terms of temporal aspects, dengue outbreaks follow consistent patterns every year. However, for many areas, this application is frustrated by the relatively small numbers of news articles.

CONCLUSIONS

The study has advanced capabilities in producing approaches that provide for richer interpretations of textual information provided in newspaper articles. Such approaches appear particularly well suited for developing countries with relatively poor medical infrastructures and records.

Fulfilling information needs of patients in online health communities

BACKGROUND

Online health communities (OHCs) experience difficulties in utilising patient reported posts to fulfil the information needs of online patients concerning health related issues.

OBJECTIVES

We aim to propose a comprehensive method that leverages medical domain knowledge to extract useful information from posts to fulfil information needs of online patients.

METHODS

A knowledge representation framework based on authoritative knowledge sources in the medical field for the OHC is proposed. On the basis of the framework, a health related information extraction process for analysing the posts in the OHC is proposed. Then, knowledge support rate (KSR) and effective information rate (EIR) are introduced as metrics to evaluate changes in knowledge extracted from the knowledge sources in terms of fulfilling the information needs of patients in the OHC.

RESULTS

On the basis of a data set with 372 343 posts in an OHC, experimental results indicate that our method effectively extracts relevant knowledge for online patients. Moreover, KSR and EIR are feasible metrics of changes in knowledge in terms of fulfilling the information needs.

CONCLUSIONS

The OHCs effectively fulfil the information needs of patients by utilising authoritative domain knowledge in the medical field. Knowledge based services for online patients facilitate an intelligent OHC in the future.

A Framework for Identifying Genotypic Information from Clinical Records: Exploiting Integrated Ontology Structures to Transfer Annotations between ICD Codes and Gene Ontologies

Although some methods are proposed for automatic ontology generation, none of them address the issue of integrating large-scale heterogeneous biomedical ontologies. We propose a novel approach for integrating various types of ontologies efficiently and apply it to integrate International Classification of Diseases, Ninth Revision, Clinical Modification (ICD9CM), and Gene Ontologies. This approach is one of the early attempts to quantify the associations among clinical terms (e.g., ICD9 codes) based on their corresponding genomic relationships. We reconstructed a merged tree for a partial set of GO and ICD9 codes and measured the performance of this tree in terms of associations' relevance by comparing them with two well-known disease-gene datasets (i.e., MalaCards and Disease Ontology). Furthermore, we compared the genomic-based ICD9 associations to temporal relationships between them from electronic health records. Our analysis shows promising associations supported by both comparisons suggesting a high reliability. We also manually analyzed several significant associations and found promising support from literature.

Knowledge Discovery from Posts in Online Health Communities Using Unified Medical Language System

Patient-reported posts in Online Health Communities (OHCs) contain various valuable information that can help establish knowledge-based online support for online patients. However, utilizing these reports to improve online patient services in the absence of appropriate medical and healthcare expert knowledge is difficult. Thus, we propose a comprehensive knowledge discovery method that is based on the Unified Medical Language System for the analysis of narrative posts in OHCs. First, we propose a domain-knowledge support framework for OHCs to provide a basis for post analysis. Second, we develop a Knowledge-Involved Topic Modeling (KI-TM) method to extract and expand explicit knowledge within the text. We propose four metrics, namely, explicit knowledge rate, latent knowledge rate, knowledge correlation rate, and perplexity, for the evaluation of the KI-TM method. Our experimental results indicate that our proposed method outperforms existing methods in terms of providing knowledge support. Our method enhances knowledge support for online patients and can help develop intelligent OHCs in the future.

Feature Engineered Relation Extraction – Medical Documents Setting

Purpose

Improving healthcare services by developing assistive technologies includes both the health aid devices and the analysis of the data collected by them. The acquired data modeled as a knowledge base give more insight into each patient’s health status and needs. Therefore, the ultimate goal of a health-care system is obtaining recommendations provided by an assistive decision support system using such knowledge base, benefiting the patients, the physicians and the healthcare industry. This paper aims to define the knowledge flow for a medical assistive decision support system by structuring raw medical data and leveraging the knowledge contained in the data proposing solutions for efficient data search, medical investigation or diagnosis and medication prediction and relationship identification.

Design/methodology/approach

The solution this paper proposes for implementing a medical assistive decision support system can analyze any type of unstructured medical documents which are processed by applying Natural Language Processing (NLP) tasks followed by semantic analysis, leading to the medical concept identification, thus imposing a structure on the input documents. The structured information is filtered and classified such that custom decisions regarding patients’ health status can be made. The current research focuses on identifying the relationships between medical concepts as defined by the REMed (Relation Extraction from Medical documents) solution that aims at finding the patterns that lead to the classification of concept pairs into concept-to-concept relations.

Findings

This paper proposed the REMed solution expressed as a multi-class classification problem tackled using the support vector machine classifier. Experimentally, this paper determined the most appropriate setup for the multi-class classification problem which is a combination of lexical, context, syntactic and grammatical features, as each feature category is good at representing particular relations, but not all. The best results we obtained are expressed as F1-measure of 74.9 per cent which is 1.4 per cent better than the results reported by similar systems.

Research limitations/implications

The difficulty to discriminate between TrIP and TrAP relations revolves around the hierarchical relationship between the two classes as TrIP is a particular type (an instance) of TrAP. The intuition behind this behavior was that the classifier cannot discern the correct relations because of the bias toward the majority classes. The analysis was conducted by using only sentences from electronic health record that contain at least two medical concepts. This limitation was introduced by the availability of the annotated data with reported results, as relations were defined at sentence level.

Originality/value

The originality of the proposed solution lies in the methodology to extract valuable information from the medical records via semantic searches; concept-to-concept relation identification; and recommendations for diagnosis, treatment and further investigations. The REMed solution introduces a learning-based approach for the automatic discovery of relations between medical concepts. We propose an original list of features: lexical – 3, context – 6, grammatical – 4 and syntactic – 4. The similarity feature introduced in this paper has a significant influence on the classification, and, to the best of the authors’ knowledge, it has not been used as feature in similar solutions.

Building Integrated Ontological Knowledge Structures with Efficient Approximation Algorithms

The integration of ontologies builds knowledge structures which brings new understanding on existing terminologies and their associations. With the steady increase in the number of ontologies, automatic integration of ontologies is preferable over manual solutions in many applications. However, available works on ontology integration are largely heuristic without guarantees on the quality of the integration results. In this work, we focus on the integration of ontologies with hierarchical structures. We identified optimal structures in this problem and proposed optimal and efficient approximation algorithms for integrating a pair of ontologies. Furthermore, we extend the basic problem to address the integration of a large number of ontologies, and correspondingly we proposed an efficient approximation algorithm for integrating multiple ontologies. The empirical study on both real ontologies and synthetic data demonstrates the effectiveness of our proposed approaches. In addition, the results of integration between gene ontology and National Drug File Reference Terminology suggest that our method provides a novel way to perform association studies between biomedical terms.