• Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer

Center for Artificial Intelligence and Cybersecurity – AIRI

  • Home
  • About Us
    • Vision, Mission and Goals
    • Center Activities
    • Center Faculty
    • Steering Committee
    • Press
  • Research
    • Scientific Projects
    • Research Papers
  • Laboratories
    • Machine Learning
    • Natural Speech & Language Processing
    • Blockchain Technology
    • Information Processing & Pattern Recognition
    • AI in Medicine
    • Data Mining
    • Computer Vision
    • Complex Networks
    • Human-Computer Interaction
    • Maritime Cybersecurity
    • Autonomous Navigation
    • AI in Mechatronics
    • AI in Education
    • Hybrid Computational Methods
    • Drug Design
    • Legal Aspects of AI
    • Ethically Aligned AI
    • Cultural Complexity
  • Collaboration
    • Industry Collaboration
    • Industry Projects
    • International Collaboration
  • News
  • Contact

Automatic Annotation of Narrative Radiology Reports

01.04.2020

Narrative texts in electronic health records can be efficiently utilized for building decision support systems in the clinic, only if they are correctly interpreted automatically in accordance with a specified standard. This paper tackles the problem of developing an automated method of labeling free-form radiology reports, as a precursor for building query-capable report databases in hospitals. The analyzed dataset consists of 1295 radiology reports concerning the condition of a knee, retrospectively gathered at the Clinical Hospital Centre Rijeka, Croatia. Reports were manually labeled with one or more labels from a set of 10 most commonly occurring clinical conditions. After primary preprocessing of the texts, two sets of text classification methods were compared: (1) traditional classification models—Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), and Random Forests (RF)—coupled with Bag-of-Words (BoW) features (i.e., symbolic text representation) and (2) Convolutional Neural Network (CNN) coupled with dense word vectors (i.e., word embeddings as a semantic text representation) as input features. We resorted to nested 10-fold cross-validation to evaluate the performance of competing methods using accuracy, precision, recall, and F1 score. The CNN with semantic word representations as input yielded the overall best performance, having a micro-averaged F1 score of 86.7%. The CNN classifier yielded particularly encouraging results for the most represented conditions: degenerative disease (95.9%), arthrosis (93.3%), and injury (89.2%). As a data-hungry deep learning model, the CNN, however, performed notably worse than the competing models on underrepresented classes with fewer training instances such as multicausal disease or metabolic disease. LR, RF, and SVM performed comparably well, with the obtained micro-averaged F1 scores of 84.6%, 82.2%, and 82.1%, respectively.

Authors:
Ivan Krsnik, Goran Glavaš, Marina Krsnik, Damir Miletić, Ivan Štajduhar
Journal:
Diagnostics
Publishing date:
01.04.2020
View original article

Primary Sidebar

Latest Projects

ABsistemDCiCloud

Machine Learning for Knowledge Transfer in Medical Radiology

Estimating River Discharges in Highly Stratified Estuaries

Multilayer Framework for the Information Spreading Characterization in Social Media during the COVID-19 Crisis (InfoCoV)

European Network for assuring food integrity using non-destructive spectral sensors

Latest Research Papers

Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning

Entropy-Based Concentration and Instantaneous Frequency of TFDs from Cohen’s, Affine, and Reassigned Classes

Coupled encoding methods for antimicrobial peptide prediction: How sensitive is a highly accurate model?

The Choice of Time–Frequency Representations of Non-Stationary Signals Affects Machine Learning Model Accuracy: A Case Study on Earthquake Detection from LEN-DB Data

Improved Parametrized Multiple Window Spectrogram with Application in Ship Navigation Systems

Latest News

Assoc. prof. Jonatan Lerga received the Croatian Academy of Sciences and Arts award

Dr. Sc. Nikola Lopac successfully defended his doctoral dissertation

Presentation at the conference “Digital Innovation and Technology for People”

Assoc. prof. dr. sc. Jonatan Lerga presented AIRI Center at the IEEE Rijeka : Computer Society Congress 2021

Prof. dr. sc. Ana Mestrovic participated at the Panel on perspectives and real-life applications of AI organized by IEEE Technology and Engineering Management Society

We provide the expertise for solving real world problems using AI

If your company wants to implement artificial intelligence in your products or services, or increase your level of cybersecurity, our multidisciplinary team of scientists is your ideal partner.

Contact us

Footer

Center for Artificial Intelligence and Cybersecurity
  • jlerga@airi.uniri.hr
  • +385 51 406 500

University of Rijeka

University of Rijeka

About the Center

  • About Us
  • News
  • Privacy Policy
  • Contact

Center Activities

  • Laboratories
  • Scientific Projects
  • Industry Projects
  • Research Papers
  • Industry Collaboration
  • International Collaboration

Footer bottom left

© 2020 Center for Artificial Intelligence and Cybersecurity, all rights reserved.

Designed & developed by Nela Dunato Art & Design