Text Mining of Medical Records for Radiodiagnostic Decision-Making

  title={Text Mining of Medical Records for Radiodiagnostic Decision-Making},
  author={William Claster and Subana Shanmuganathan and Nader Ghotbi},
  journal={J. Comput.},
The rapid growth of digitalized medical records presents new opportunities for mining terra bytes of data that may provide new information & knowledge. [] Key Method We employed Self Organizing Maps (SOM), an unsupervised neural network based text-mining technique for the analysis. This approach led to the identification of keywords with a significance value within the narratives of the medical records that could predict & thereby lower the number of unnecessary CT requests by clinicians. This is important…

Figures and Tables from this paper

Machine Learning for Medical Examination Report Processing

This article presents a name entity recognition system, MD_NER_NCL, and a text document classification system, C_IME_RPT, and an in-depth empirical study on the effectiveness of parameters associated with the SOM learning process and text mining, and their effects on classification results.

Use of natural language processing to improve predictive models for imaging utilization in children presenting to the emergency department

Predictive models combining structured and unstructured variables available at triage performed better than models using structured or un Structured variables alone, suggesting the potential for use of NLP in determining resource utilization.

Knowledge Extraction From Radiology Report Using Text Mining

The aim of this project to extract the information and used that information in radiology report and the system is consisting of three main modules: the medical finding extractor, report retriever, and image retriever.

Prediction of Emergency Department Hospital Admission Based on Natural Language Processing and Neural Networks.

The predictive accuracy of hospital admission or transfer for patients who presented to ED triage overall was good, and was improved with the inclusion of free text data from a patient's reason for visit regardless of modeling approach.

DISEArch - A Strategy for Searching Electronic Medical Health Records

The objective of DISEArch is to enhance research activities on disease analysis allowing researchers to describe the disease they are interested on, and providing them the EHRs that best match their description.

Clustering of 27,525,663 Death Records from the United States Based on Health Conditions Associated with Death: An Example of Big Health Data Exploration

The prevalence of multiple health conditions at death requires a shift from disease-oriented towards person-centred palliative care at the end of life, including timely advance care planning, according to the National Vital Statistics System between 2006 and 2016.

Prediction of acute appendicitis among patients with undifferentiated abdominal pain at emergency department

Predictive models that can predict the AA diagnosis for adult and pediatric ED patients are developed, and the predictive accuracy was improved with the inclusion of NLP elements and approaches.

Automatic Text categorization and summarization using rule reduction

  • C. DevasenaM. Hemalatha
  • Computer Science
    IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM -2012)
  • 2012
A text analyzer is developed to derive the structure of the input text using rule reduction technique in three stages namely, Token Creation, Feature Identification and Categorization and Summarization.

Applied bibliometrics and information visualization for decision-making processes in higher education institutions

Evidence that a bibliometric approach in conjunction with data visualization can be a valuable complement to in-depth literature reviews for the decision-making process is provided.

A Parallel Implementation of the Self Organising Map using OpenCL

A parallel version of the classical algorithm using OpenCL that is suited for use on parallel processor architectures, and the use of the Manhattan distance metric is explored as a replacement for the traditional Euclidean distance in an attempt to decrease run times.



The clinician's perspective on electronic health records and how they can affect patient care

Important lessons learned from previous attempts to get clinicians to use computers in health care are examined; how clinicians actually work are discussed; recommendations on designing or selecting clinical computer systems are made; and how the use of electronic health records might affect patient care is explored.

Doctors' knowledge of radiation exposure: questionnaire study

The level of knowledge doctors have concerning radiation doses received by patients when they undergo commonly requested radiological investigations is investigated.

Evidence-based Guidelines Needed on the Use of CT Scanning in Japan

More work is needed to establish good practice principles by the medical community through determination of more reasonable indications to request CT scanning, to help limit and control the amount of radiation doses the Japanese population is being exposed to through medical diagnostic imaging technologies.

Computed tomography and radiation risks: what pediatric health care providers should know.

The issues with CT patterns of use and radiation risk are summarized, dose reduction strategies pertinent to pediatric health care providers are provided, and a variety of strategies to limit radiation dose are offered.

Pediatric CT scan usage in Japan: results of a hospital survey

PurposeThe aim of this study was to examine the usage parameters of diagnostic computed tomography (CT) in children because of concerns of possible overuse in Japanese hospitals, including the

Estimated risks of radiation-induced fatal cancer from pediatric CT.

It is suggested that pediatric CT will result in significantly increased lifetime radiation risk over adult CT, both because of the increased dose per milliampere-second, and the increased lifetime risk per unit dose.

Risk and benefit in paediatric radiology

  • D. Roebuck
  • Medicine, Physics
    Pediatric Radiology
  • 1999
Abstract An investigation requiring the use of ionising radiation can be justified by showing that its benefits are likely to exceed its risks. The risks can be estimated from the effective dose by

Radiation exposures to patients from CT: reality, public perception, and policy.

Figure 4 Tabbed version of C5.0 decision tree .1 indicates the predication of a necessary scan and 2 indicates the prediction of an unnecessary scan

  • Figure 4 Tabbed version of C5.0 decision tree .1 indicates the predication of a necessary scan and 2 indicates the prediction of an unnecessary scan