Browsing by Subject "decision models"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Evaluating Methods for Identifying Cancer in Free-Text Pathology Reports Using Various Machine Learning and Data Preprocessing Approaches
    (IOS, 2015) Kasthurirathne, Suranga Nath; Dixon, Brian E.; Grannis, Shaun J.; Department of BioHealth Informatics, School of Informatics and Computing
    Automated detection methods can address delays and incompleteness in cancer case reporting. Existing automated efforts are largely dependent on complex dictionaries and coded data. Using a gold standard of manually reviewed pathology reports, we evaluated the performance of alternative input formats and decision models on a convenience sample of free-text pathology reports. Results showed that the input format significantly impacted performance, and specific algorithms yielded better results for presicion, recall and accuracy. We conclude that our approach is sufficiently accurate for practical purposes and represents a generalized process.
  • Thumbnail Image
    Item
    Toward better public health reporting using existing off the shelf approaches: The value of medical dictionaries in automated cancer detection using plaintext medical data
    (Elsevier, 2017-05) Kasthurirathne, Suranga N.; Dixon, Brian E.; Gichoya, Judy; Xu, Huiping; Xia, Yuni; Mamlin, Burke; Grannis, Shaun J.; Department of Epidemiology, Richard M. Fairbanks School of Public Health
    Objectives Existing approaches to derive decision models from plaintext clinical data frequently depend on medical dictionaries as the sources of potential features. Prior research suggests that decision models developed using non-dictionary based feature sourcing approaches and “off the shelf” tools could predict cancer with performance metrics between 80% and 90%. We sought to compare non-dictionary based models to models built using features derived from medical dictionaries. Materials and methods We evaluated the detection of cancer cases from free text pathology reports using decision models built with combinations of dictionary or non-dictionary based feature sourcing approaches, 4 feature subset sizes, and 5 classification algorithms. Each decision model was evaluated using the following performance metrics: sensitivity, specificity, accuracy, positive predictive value, and area under the receiver operating characteristics (ROC) curve. Results Decision models parameterized using dictionary and non-dictionary feature sourcing approaches produced performance metrics between 70 and 90%. The source of features and feature subset size had no impact on the performance of a decision model. Conclusion Our study suggests there is little value in leveraging medical dictionaries for extracting features for decision model building. Decision models built using features extracted from the plaintext reports themselves achieve comparable results to those built using medical dictionaries. Overall, this suggests that existing “off the shelf” approaches can be leveraged to perform accurate cancer detection using less complex Named Entity Recognition (NER) based feature extraction, automated feature selection and modeling approaches.