Machine learning-based reproducible prediction of type 2 diabetes subtypes.

Journal: Diabetologia
Published Date: Aug 21, 2024

Abstract

AIMS/HYPOTHESIS: Clustering-based subclassification of type 2 diabetes, which reflects pathophysiology and genetic predisposition, is a promising approach for providing personalised and effective therapeutic strategies. Ahlqvist's classification is currently the most vigorously validated method because of its superior ability to predict diabetes complications but it does not have strong consistency over time and requires HOMA2 indices, which are not routinely available in clinical practice and standard cohort studies. We developed a machine learning (ML) model to classify individuals with type 2 diabetes into Ahlqvist's subtypes consistently over time.

Authors

  • Hayato Tanabe
    Department of Diabetes, Endocrinology, and Metabolism, Fukushima Medical University School of Medicine, Fukushima, Japan.
  • Masahiro Sato
    Department of Electrical Engineering and Information Systems, The University of Tokyo, Hongo 7-3-1, Bunkyo-ku, Tokyo 113-8656, Japan.
  • Akimitsu Miyake
    Department of AI and Innovative Medicine, Tohoku University School of Medicine, Miyagi, Japan.
  • Yoshinori Shimajiri
    Shimajiri Kinsermae Diabetes Care Clinic, Okinawa, Japan.
  • Takafumi Ojima
    Department of AI and Innovative Medicine, Tohoku University School of Medicine, Miyagi, Japan.
  • Akira Narita
    Tohoku Medical Megabank Organization, Tohoku University, Sendai, Japan.
  • Haruka Saito
    Department of Diabetes, Endocrinology, and Metabolism, Fukushima Medical University School of Medicine, Fukushima, Japan.
  • Kenichi Tanaka
    Division of Gastrointestinal Surgery, Department of Surgery, Graduate School of Medicine, Kobe University, Kobe, Japan. tanakake@med.kobe-u.ac.jp.
  • Hiroaki Masuzaki
    Division of Endocrinology and Metabolism, Second Department of Internal Medicine, University of the Ryukyus Graduate School of Medicine, Okinawa, Japan.
  • Junichiro J Kazama
    Department of Nephrology and Hypertension, Fukushima Medical University School of Medicine, Fukushima, Japan.
  • Hideki Katagiri
    Department of Diabetes, Metabolism and Endocrinology, Tohoku University Graduate School of Medicine, Miyagi, Japan.
  • Gen Tamiya
    Tohoku Medical Megabank Organization (ToMMo), Tohoku University, Sendai, Miyagi, Japan.
  • Eiryo Kawakami
    Medical Sciences Innovation Hub Program, RIKEN, Yokohama, Kanagawa, Japan.
  • Michio Shimabukuro
    Department of Diabetes, Endocrinology, and Metabolism, Fukushima Medical University School of Medicine, Fukushima, Japan. mshimabukuro-ur@umin.ac.jp.

Keywords

External Resources

Popular Topics
Recent Journals