Unsupervised machine learning-assisted multimodal characterization of cardiomyocytes on a thin-film-transistor microelectrode array (TFT-MEA)
Biomedical Physics & Engineering Express · 2026
DOI: 10.1088/2057-1976/ae87aa ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, 2026. Verfasst von Xingzhuo Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Industrial Science, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8505, Tokyo, Japan. Hauptthemen laut MEDLINE: Myocytes, Cardiac, Unsupervised Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Murata Science Promotion and Education Foundation 2024, Institute of Industrial Science -UTokyo, Spring GX.
Abstract (Originalsprache)
Microelectrode arrays (MEAs) provide powerful platforms for large-scale in vitro cardiac tissue analysis. We present a machine learning (ML)-assisted framework for multimodal characterization of cardiomyocyte activity recorded using a transparent thin-film-transistor MEA, allowing simultaneous acquisition of electrophysiological and optical data. The features of both modalities were integrated, and unsupervised learning identified contraction patterns without prior labels. Reliability was assessed with supervised models and SHapley Additive Explanations to confirm feature importance and label consistency. Pharmacological validation with isoprenaline showed the expected increase in beating frequency, detected automatically by our pipeline. Multimodal feature correlations with emergent labels demonstrated that interpretable ML can extract biologically meaningful insights from complex datasets. While isoprenaline served as a proof-of-concept, the framework is applicable for detecting diverse drug- or disease-induced cardiac network changes. This approach enables scalable, label-free and automated assessment of cardiomyocytes networks for drug discovery, toxicity screening, and mechanistic studies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute of Industrial Science, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8505, Tokyo, Japan.
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo, Hongo, Bunkyo-ku, Tokyo 113-8655, Tokyo, Japan.
- Department of Advanced Cardiology, Graduate School of Medicine, The University of Tokyo, Hongo, Bunkyo-ku, Tokyo 113-8655, Tokyo, Japan.
- Department of Integrative Physiology, Institute of Science Tokyo, Bunka, Sumida-ku, Tokyo 112-8519, Tokyo, Japan.
ORCID-Profile: Xingzhuo Hu, Junichi Sugita, Agnès Tixier-Mita
Förderung
- Murata Science Promotion and Education Foundation 2024
- Institute of Industrial Science -UTokyo
- Spring GX
- Japan Science and Technology Agency Support
- Japan Society for the Promotion of Science
- Japan Agency for Medical Research and Development
- Japan Science and Technology Agency
- Nanken-Kyoten, Science Tokyo
Zitieren
APA
Hu, X., Sugita, J., Fujiu, K., Tixier-Mita, A., & Toshiyoshi, H. (2026). Unsupervised machine learning-assisted multimodal characterization of cardiomyocytes on a thin-film-transistor microelectrode array (TFT-MEA). Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ae87aa
Vancouver
Hu X, Sugita J, Fujiu K, Tixier-Mita A, Toshiyoshi H. Unsupervised machine learning-assisted multimodal characterization of cardiomyocytes on a thin-film-transistor microelectrode array (TFT-MEA). Biomedical Physics & Engineering Express. 2026. doi:10.1088/2057-1976/ae87aa
BibTeX
@article{Hu2026,
author = {Hu, Xingzhuo and Sugita, Junichi and Fujiu, Katsuhito and Tixier-Mita, Agnès and Toshiyoshi, Hiroshi},
title = {Unsupervised machine learning-assisted multimodal characterization of cardiomyocytes on a thin-film-transistor microelectrode array (TFT-MEA)},
journal = {Biomedical Physics & Engineering Express},
year = {2026},
doi = {10.1088/2057-1976/ae87aa}
}
EUVIMED