bioRxivBioengineeringPreprint
SMART-NeuroDx: A Reagent-Free Multianalyte Biosensor Platform with Machine-Learning Readout for Point-of-Care Dementia Screening
Sudhaunsh DeshpandeiD, Krzysztof PawlakiD, Moulya Badavanapalya Prathap, Cara Evans, Theresa Al-Alam, Anu Mary Joy, Ajith Mohan ArjuniD, Sanjiv SharmaiD
Abstract
Differentiating overlapping dementia pathologies, such as frontotemporal dementia and Alzheimers disease, calls for the simultaneous measurement of several blood biomarkers, yet electrochemical sensors remain predominantly single-target and dependent on labels and sample preparation. Here we report SMART-NeuroDx, a reagent-free electrochemical array that quantifies pTau217, GFAP, pTau181, and NfL directly from unprocessed plasma and serum in under 35 minutes. Four surface-confined redox-active molecularly imprinted polymer and aptamer-MIP recognition matrices are electropolymerized onto a four-working-electrode porous-gold printed-circuit array, using potential-assisted electrostatic gating keyed to each targets isoelectric point to prevent cross-channel template contamination during synthesis. Label-free Faradaic responses from the redox-active polymer backbone are acquired on a custom battery-powered STM32G4 handheld potentiostat and converted to concentration from five voltammetric features using cross-validated Random Forest and XGBoost regressors. The handheld unit reproduced the baseline fidelity of a commercial benchtop workstation and resolved sub-picogram pTau217 (limit of detection 0.087 pg mL-{superscript 1}) across marker-appropriate dynamic ranges, with inter-chip relative standard deviation at or below 5.34% and coefficients of determination of 0.94 to 0.99 against reference concentrations. Each channel retained selectivity in plasma and serum against competing neurological and inflammatory proteins, with non-specific signal deviation held below 10% by the hydrated PyPEG interfacial shell. The platform establishes reagent-free, simultaneous four-analyte neurodegeneration sensing on a single point-of-care device.
- organism: human
- assay: proteomics
- research focus: differential expression
- research focus: protein folding & dynamics
- approach: deep learning
- approach: machine learning (classical)
- Citations
- 0
Reproducibility ledger
Nobody has reported trying to reproduce this paper yet. Did you replicate an experiment or run the code? Your report saves the next lab a week.
Sign in to file a reproducibility report.
Related papers
- Machine Learning-Augmented Analysis of Nano-electrochemical Sensor Data for Predictive and Quantitative Assays of Complex Biological Samples
Chaitanya Gupta, Kishan Aryasomayajula, … Emmanuel P. Quévy·bioRxiv·Nov 27, 2025
- Neurons as biosensors for discriminating neurological disorders in a brain-on-chip platform: Application to Alzheimer s Disease using patient CSF
Louise Miny, Jessica Rontard, … Isabelle Quadrio·bioRxiv·Aug 23, 2024
- Ultrasensitive saliva-based detection of early Alzheimer's disease biomarkers via nanoparticle-enhanced evanescent scattering microscopy
Caterina Dallari, Georg Ladurner, … Francesco Saverio Pavone·ACS SensorsPeer-reviewed·Feb 13, 2026
- Ultrasensitive graphene FET aptasensor for direct attomolar detection of glutamate in human clinical samples
Mafalda Abrantes, Yolanda Blanco, … Pedro Alpuim·bioRxiv·Nov 5, 2025
- A reproducible approach for the use of aptamer libraries for the identification of Aptamarkers for brain amyloid deposition based on plasma analysis.
Cathal Meehan, Soizic Lecocq, Gregory Penner·PLoS ONEPeer-reviewed·Aug 27, 2024
- Advancing Early Diagnosis of Alzheimers Disease: A Paper-Based Aptasensor for Detecting Amyloid Beta(1-42) and p-tau181 from Plasma Using CdTe Quantum Dots
Elif Betül Balcı, Elif Nur Yildiz, … Umut Hasirci·bioRxiv·Jul 10, 2024