EUVIMEDEUVIMED entdecken
Crossref

Generative AI Enables Rapid Point-of-Care Diagnostics via Signal Prediction in Pre-equilibrium Immunoassays

Weiqi Zhao, Dingyang Xie, Ting Xiao, Xiaohu Niu, Huanhuan Li, Yunlei Xianyu, Zhaoqin Wang, Long Wu, Liping Pan, Zhenghao Wang, Yiping Chen

Analytical Chemistry · 16.11.2026

DOI: 10.1021/acs.analchem.6c06586 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 16.11.2026. Verfasst von Weiqi Zhao und 10 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Liaoning Province ?Xingliao Talent Plan? Leading Talent Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional immunoassays typically operate under equilibrium conditions and require several hours for accurate quantification, which limits their suitability for point-of-care testing (POCT). Here, we report a portable pre-equilibrium immunoassay that employs a microfluidic chip as a physical information interface to encode immunoreaction states, enabling artificial intelligence (AI)-based inference of equilibrium-referenced quantitative estimates from early-stage signal dynamics. Instead of waiting for equilibrium, transient target binding-induced motion trajectories of magnetic nanoparticle−loaded microbeads are monitored in a compact self-driven microfluidic system. The smartphone-integrated model predicts signal transduction outcomes from immunoreaction dynamics at individual time points, and quantitative analysis is achieved by jointly evaluating these time-resolved predictions, with an adversarial framework enhancing robustness. Using this approach, reliable quantification of real samples is achieved within 4 min, representing more than a 30-fold reduction in assay time compared with conventional enzyme-linked immunosorbent assay, while maintaining comparable sensitivity. By exploiting the kinetic information embedded within non-continuous, pre-equilibrium observations, this work provides a general strategy with broad potential to accelerate decentralized diagnostics.

Förderung

  • National Natural Science Foundation of China
  • Liaoning Province ?Xingliao Talent Plan? Leading Talent Project

Zitieren

APA

Zhao, W., Xie, D., Xiao, T., Niu, X., Li, H., Xianyu, Y., Wang, Z., Wu, L., Pan, L., Wang, Z., & Chen, Y. (2026). Generative AI Enables Rapid Point-of-Care Diagnostics via Signal Prediction in Pre-equilibrium Immunoassays. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.6c06586

Vancouver

Zhao W, Xie D, Xiao T, Niu X, Li H, Xianyu Y, et al. Generative AI Enables Rapid Point-of-Care Diagnostics via Signal Prediction in Pre-equilibrium Immunoassays. Analytical Chemistry. 2026. doi:10.1021/acs.analchem.6c06586

BibTeX
@article{Zhao2026,
  author = {Zhao, Weiqi and Xie, Dingyang and Xiao, Ting and Niu, Xiaohu and Li, Huanhuan and Xianyu, Yunlei and Wang, Zhaoqin and Wu, Long and Pan, Liping and Wang, Zhenghao and Chen, Yiping},
  title = {Generative AI Enables Rapid Point-of-Care Diagnostics via Signal Prediction in Pre-equilibrium Immunoassays},
  journal = {Analytical Chemistry},
  year = {2026},
  doi = {10.1021/acs.analchem.6c06586}
}
Kostenlos starten →