In-Hospital Cancer Mortality Prediction by Multimodal Learning of Non-English Clinical Texts.

Journal: Studies in health technology and informatics
PMID: 37203505

Abstract

Predicting important outcomes in patients with complex medical conditions using multimodal electronic medical records remains challenge. We trained a machine learning model to predict the inpatient prognosis of cancer patients using EMR data with Japanese clinical text records, which has been considered difficult due to its high context. We confirmed high accuracy of the mortality prediction model using clinical text in addition to other clinical data, suggesting applicability of this method to cancer.

Authors

  • Shintaro Oyama
    Innovative Research Center for Preventive Medical Engineering, Nagoya University, Nagoya, Japan.
  • Taiki Furukawa
    Nagoya University Hospital Medical IT Center, Nagoya University, Nagoya, Japan.
  • Shotaro Misawa
    FUJIFILM Corporation, Tokyo, Japan.
  • Ryuji Kano
    FUJIFILM Corporation, Tokyo, Japan.
  • Hirokazu Yarimizu
    FUJIFILM Corporation, Tokyo, Japan.
  • Tomoki Taniguchi
    FUJIFILM Corporation, Tokyo, Japan.
  • Kohei Onoda
    FUJIFILM Corporation, Tokyo, Japan.
  • Kikue Sato
    Nagoya University Hospital Medical IT Center, Nagoya University, Nagoya, Japan.
  • Yoshimune Shiratori
    Nagoya University Hospital Medical IT Center, Nagoya University, Nagoya, Japan.

Keywords

External Resources

Popular Topics
Recent Journals