Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors.

Journal: Scientific reports
PMID:

Abstract

Hand-foot skin reaction (HFSR) is a common adverse effect of vascular endothelial growth factor receptor (VEGFR) inhibitors that significantly impacts patients' quality of life. Prevention and management of HFSR require individualized approaches, but risk factors remain unclear. This study aimed to develop artificial intelligence (AI) models to predict grade ≥ 2 HFSR using clinical data and foot sole images from 93 instances of VEGFR inhibitor administration in 76 patients. Image-based, clinical information-based, and ensemble AI models achieved areas under the curve of 0.550, 0.693, and 0.699, respectively. At a high-specificity cutoff, the ensemble AI had a positive predictive value of 0.824, suggesting potential clinical utility for identifying high-risk patients. Feature importance analysis revealed heavier weight, good performance status, lack of prior VEGFR inhibitor exposure, and baseline skin toxicity as risk factors. These findings represent the first AI-based HFSR prediction models and provide insights for preventive interventions, but further accuracy improvements are needed.

Authors

  • Taro Yamanaka
    Department of Medical Oncology, Toranomon Hospital, 2-2-2 Toranomon Minato-ku, Tokyo, 105-8470, Japan.
  • Jumpei Ukita
    Mental Health Research Course, Faculty of Medicine, The University of Tokyo, Tokyo, Japan.
  • Dongyi Xue
    M3 Inc., Tokyo, Japan.
  • Chihiro Kondoh
    Department of Medical Oncology, National Cancer Center Hospital East, Kashiwa, Japan.
  • Seiwa Honda
    Nonprofit Organization (NPO) Nagoya Orthopedic Regional Healthcare Support Center, AI Research Division, Meitohonmachi 2-22-1, Meito-ward, Nagoya, Japan.
  • Maiko Noguchi
    Mebix Inc., Tokyo, Japan.
  • Yoshiko Yonejima
    Department of Medical Oncology, Toranomon Hospital, 2-2-2 Toranomon Minato-ku, Tokyo, 105-8470, Japan.
  • Kiyomi Nonogaki
    Department of Medical Oncology, Toranomon Hospital, 2-2-2 Toranomon Minato-ku, Tokyo, 105-8470, Japan.
  • Kohji Takemura
    Department of Medical Oncology, Toranomon Hospital, 2-2-2 Toranomon Minato-ku, Tokyo, 105-8470, Japan.
  • Rika Kizawa
    Department of Medical Oncology, Toranomon Hospital, 2-2-2 Toranomon Minato-ku, Tokyo, 105-8470, Japan.
  • Takeshi Yamaguchi
    Division of Medical Oncology, Japanese Red Cross Musashino Hospital.
  • Yuko Tanabe
    Department of Medical Oncology, Toranomon Hospital, 2-2-2 Toranomon Minato-ku, Tokyo, 105-8470, Japan.
  • Koichi Suyama
    Department of Medical Oncology, Toranomon Hospital, 2-2-2 Toranomon Minato-ku, Tokyo, 105-8470, Japan.
  • Keisuke Ogaki
    M3 Inc, Tokyo, Japan.
  • Yuji Miura
    hhc Data Creation Center, Eisai Co., Ltd., Koishikawa 4-6-10, Bunkyo-ku, Tokyo 112-8088, Japan.