Now showing 1 - 3 of 3
  • Publication
    Analysis of EHR Free-text Data with Supervised Deep Neural Networks
    In this paper we present an efficient supervised deep neural network architecture to classify patients based solely on free-text notes extracted from their Electronic Health Records (EHRs). In particular, a three-layer Recurrent Neural Network was used in conjunction with the aggregated EHRs of about 127,149 patients from a medical data warehouse. The result forms a key component of an application we name PANNACEA. We evaluated this neural network in the context of competing neural network architectures, comparing the performance of multilayer perceptrons, convolutional neural networks, and recurrent neural networks in relation to the dataset under investigation. We performed evaluation our program to successfully classify the suitability of these patients to the medical service offered based upon a single medical episode.
  • Publication
    Abbreviation and Acronym Identification and Expansion Within Medical Health Records
    (IADIS, 2017-07-22) ;
    Recent years have seen the rapid increase in digitised medical information. In particular, the massive expansion of Electronic Health Records (EHRs), which are designed to document all information that is clinically relevant in a patient's use of a healthcare facility, has introduced unprecedented volumes of relatively unstructured data. This paper intends to determine the extent to which knowledge discovery in relation to both abbreviations and acronyms within heterogeneous data can be achieved. Heterogeneous data such as the narrative-based free-text notes found within patients' EHRs may use inconsistent ways to indicate contractions within the text and may use non-standard definitions for both abbreviations and acronyms. We approached this task through the retrieval and classification of contractions as well as using a novel method of combining multiple publically available repositories. In order to provide better coverage of abbreviations, and also to address the issue of neologisms in general, word embeddings were applied to find semantically similar lexemes.
  • Publication
    Retrieval and Clustering of Medicines Within Healthcare Data Records
    Electronic Health Records (EHRs) are typically designed to electronically document all information that is administratively and clinically relevant in a patient's use of a healthcare facility. This paper intends to improve discoverability of medications which may exist within the narrative-based free-text notes of patients' health care data records. This led us to introduce a context sensitive approach to retrieve candidate pharmaceuticals. Additionally, a combination of contraction promotion and clustering based upon edit distance will be utilised to increase the precision of this process.
      306Scopus© Citations 1