Robust detection of femtogram-level Alzheimer's biomarkers using machine learning-enhanced graphene biosensors
Biosensors and Bioelectronics · 2026-01 · 292 · 118074
DOI: 10.1016/j.bios.2025.118074 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors and Bioelectronics, 2026-01. Verfasst von Qingzhou Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, 518060, China. Electronic address: liuqingzhou@gml.ac.cn. Hauptthemen laut MEDLINE: Alzheimer Disease, Biosensing Techniques, Graphite, Amyloid beta-Peptides. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministerul Cercetării şi Inovării, Societat Catalana de Digestologia.
Abstract (Originalsprache)
Early diagnosis of Alzheimer's disease (AD) requires blood biomarker tests sensitive to femtogram/mL concentrations. Graphene field-effect transistors (GFETs) are promising for this application, but suffer from device-to-device variability and require recalibration after functionalization. Here, we demonstrate a machine learning approach that overcomes these limitations, enabling robust AD biomarker detection without individual device calibration. By training artificial neural networks (ANNs) on full GFET transfer characteristics, our method automatically extracts features resilient to device variations. We detected three AD biomarkers-Aβ42, Aβ40, and P-tau217-at concentrations from 1 fg/mL to 1.0 × 105 fg/mL with 98.9-100 % accuracy across multiple devices. Validation using 72 clinical plasma samples achieved four-way classification of cognitive states (healthy control, subjective cognitive decline, mild cognitive impairment, and AD), with multi-biomarker combinations improving diagnostic performance. SHAP (SHapley Additive exPlanations) analysis revealed that ANNs exploit previously uncharacterized regions of the GFET transfer characteristics that are not captured by conventional figures of merit. Unlike traditional approaches requiring device-specific calibration curves, our platform enables sensor deployment and maintains performance despite fabrication inconsistencies. This work demonstrates that machine learning can transform inherently variable graphene biosensors into reliable diagnostics, addressing a critical barrier to their potential implementation in point-of-care AD screening.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, 518060, China. Electronic address: liuqingzhou@gml.ac.cn.
- Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, 518060, China; The Institute for Advanced Study (IAS), Shenzhen University, Shenzhen, 518060, China.
- The Institute for Advanced Study (IAS), Shenzhen University, Shenzhen, 518060, China.
- Clinical and Immunology Laboratory, Longgang Central Hospital of Shenzhen, Shenzhen, 518116, China. Electronic address: liuyibiao12345@126.com.
- The Institute for Advanced Study (IAS), Shenzhen University, Shenzhen, 518060, China. Electronic address: xutailin@szu.edu.cn.
Förderung
- National Natural Science Foundation of China
- Ministerul Cercetării şi Inovării
- Societat Catalana de Digestologia
Zitieren
APA
Liu, Q., He, Y., Wang, Q., Min, S., Geng, H., Liu, Y., & Xu, T. (2026). Robust detection of femtogram-level Alzheimer's biomarkers using machine learning-enhanced graphene biosensors. Biosensors and Bioelectronics, 292, 118074. https://doi.org/10.1016/j.bios.2025.118074
Vancouver
Liu Q, He Y, Wang Q, Min S, Geng H, Liu Y, et al. Robust detection of femtogram-level Alzheimer's biomarkers using machine learning-enhanced graphene biosensors. Biosensors and Bioelectronics. 2026;292:118074. doi:10.1016/j.bios.2025.118074
BibTeX
@article{Liu2026,
author = {Liu, Qingzhou and He, Yuheng and Wang, Qiyu and Min, Shunhua and Geng, Haoyang and Liu, Yibiao and Xu, Tailin},
title = {Robust detection of femtogram-level Alzheimer's biomarkers using machine learning-enhanced graphene biosensors},
journal = {Biosensors and Bioelectronics},
year = {2026},
volume = {292},
pages = {118074},
doi = {10.1016/j.bios.2025.118074}
}
EUVIMED