Skip to content
DraconiticResearch
Search Sources API
190,860 studies31 sourcesUpdated 38 min ago
PreprintCC BYChemRxiv

Active Noise Cancelling in Point-of-Care Testing

  • Minhao Liu1,2
  • Pu Sun1,2
  • Nazmul Huda Ovi1,2
  • Zhicheng Peng1,2
  • Zhugang Liu1,2
  • Muhammad Wasim1,2
  • Qingkai Yuan1,2
  • Prabhav Kuruva1,2
  • Isabela Bejgel de Araujo1,2
  • Yanfeng Ma1,2
  • Subarna Akter1,2
  • Michael Castillo1,2
9 more authors
  • Jeshua Podliska1,2
  • Roman Sarkar1,2
  • Brianna Garcia1,2
  • Sheng He3
  • Yangming Ou3
  • Nguyen N. Nguyen4
  • Robert H. Christenson5,6
  • Sheng Feng5,6
  • Hui Chen1,2
6 affiliations
  1. 1Department of Chemistry and Biochemistry
  2. 2Texas Tech University
  3. 3Harvard Medical School
  4. 4Baylor Scott and White Health
  5. 5Department of Pathology
  6. 6University of Maryland Medical Center
Open at sourcePDFDOICite

Abstract

Point-of-care testing (POCT) holds great potential to improve diagnostic accessibility because of its low cost, portability, user-friendliness, and rapid turnaround times. However, the limited analytical precision and high error rates of most POCT platforms usually caused by the assay noises at the POC settings frequently create diagnostic ambiguity and lead to further confirmatory testing. Consequently, these limitations restrict broader clinical translation. To address this issue, we introduce an active assay noise canceling approach, using the deep-learning-based Whole-Process Analysis (WPA), a universal, device-adaptable software paradigm without altering assay hardware or chemistry. Instead of relying on static endpoint readouts, WPA uses a deep-learning architecture to continuously capture the spatiotemporal evolution of the entire POCT assay process. The architecture decodes dynamic, high-dimensional "assay noise footprints" and algorithmically compensate for the signal variations caused by assay noises. We demonstrated the proof of concept, we chose the lateral flow assay (LFA) as a model, which is a leading POCT platform. We validated WPA for xylazine LFA across 251 patient urine samples, benchmarking against gold-standard liquid chromatography-tandem mass spectrometry (LC-MS/MS). WPA drastically decreased signal variations among different clinical samples and compressed the diagnostic gray zone, delivering 94.02% accuracy (95% CI: 90.33%-96.62%), 71.15% sensitivity (95% CI: 56.92%-82.87%), and 100% specificity (95% CI: 98.16%-100.00%), compared with human reading, which achieved 89.2% accuracy (95% CI: 84.74%-92.79%), 48.1% sensitivity (95% CI: 34.01%-62.37%), and 100% specificity (95% CI: 98.16%-100.00%). By computationally untangling true analyte signals from assay noises in POC settings, WPA provides a transformative, device-adaptable pathway to improve POCT accuracy and precision without altering assay hardware or chemistry.

Related

  1. Onsite DADQs-assisted chemiluminescence wavelength shift from luminol µPADs to tetracyanoquinodimethane-based fluorophores enabling sensitised emission of AuNPs in point-of-source testing (PoST) multimode device.
    Anuradha Sureshrao Mohitkar, Pavar Sai Kumar, Rituparna Sinha +3
    RSC advancesPeer-reviewedCC BY-NCFull textGeneral chemistryEurope PMC
  2. Active-Space Selection in Nonadiabatic Dynamics Simulations of Dense Manifolds of Excited States: When Local Diabatization Needs Great Care
    Alexey V. Akimov
    ChemRxivPreprintLicence not stated1 citedGeneral chemistryChemRxiv
  3. Rapid Point-of-Care Quantification of Urinary Tract Infection Biomarker Xanthine Oxidase
    Ellen Stadler, Mark Sutton, Colin Brown +5
    ACS OmegaPeer-reviewedCC BY 4.0Full textGeneral chemistryCrossref
  4. Quality control measurement science: Point-of-care opioid compounding and personalized pain management
    Thomas P. Forbes, Zainab Altamimi, Jeffrey Lawrence +1
    ChemRxivPreprintCC BY-NCFull textAnalytical chemistryChemRxiv
  5. Enhanced Paper-Based DNA Adsorption and Point-of-Care Detection of High-Risk Human Papillomaviruses 16 and 18.
    Neha Rani Das, Mohamed Asif Shajahan, Sivie Kurian +10
    ChemRxivPreprintCC BYFull textGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{liu2026active,
  title = {{Active Noise Cancelling in Point-of-Care Testing}},
  author = {Minhao Liu and Pu Sun and Nazmul Huda Ovi and Zhicheng Peng and Zhugang Liu and Muhammad Wasim and Qingkai Yuan and Prabhav Kuruva and Isabela Bejgel de Araujo and Yanfeng Ma and Subarna Akter and Michael Castillo and Jeshua Podliska and Roman Sarkar and Brianna Garcia and Sheng He and Yangming Ou and Nguyen N. Nguyen and Robert H. Christenson and Sheng Feng and Hui Chen},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15007405/v2},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15007405/v2},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - Active Noise Cancelling in Point-of-Care Testing
AU  - Minhao Liu
AU  - Pu Sun
AU  - Nazmul Huda Ovi
AU  - Zhicheng Peng
AU  - Zhugang Liu
AU  - Muhammad Wasim
AU  - Qingkai Yuan
AU  - Prabhav Kuruva
AU  - Isabela Bejgel de Araujo
AU  - Yanfeng Ma
AU  - Subarna Akter
AU  - Michael Castillo
AU  - Jeshua Podliska
AU  - Roman Sarkar
AU  - Brianna Garcia
AU  - Sheng He
AU  - Yangming Ou
AU  - Nguyen N. Nguyen
AU  - Robert H. Christenson
AU  - Sheng Feng
AU  - Hui Chen
PY  - 2026
DA  - 2026/10/07
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15007405/v2
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15007405/v2
AB  - Point-of-care testing (POCT) holds great potential to improve diagnostic accessibility because of its low cost, portability, user-friendliness, and rapid turnaround times. However, the limited analytical precision and high error rates of most POCT platforms usually caused by the assay noises at the POC settings frequently create diagnostic ambiguity and lead to further confirmatory testing. Consequently, these limitations restrict broader clinical translation. To address this issue, we introduce an active assay noise canceling approach, using the deep-learning-based Whole-Process Analysis (WPA), a universal, device-adaptable software paradigm without altering assay hardware or chemistry. Instead of relying on static endpoint readouts, WPA uses a deep-learning architecture to continuously capture the spatiotemporal evolution of the entire POCT assay process. The architecture decodes dynamic, high-dimensional "assay noise footprints" and algorithmically compensate for the signal variations caused by assay noises. We demonstrated the proof of concept, we chose the lateral flow assay (LFA) as a model, which is a leading POCT platform. We validated WPA for xylazine LFA across 251 patient urine samples, benchmarking against gold-standard liquid chromatography-tandem mass spectrometry (LC-MS/MS). WPA drastically decreased signal variations among different clinical samples and compressed the diagnostic gray zone, delivering 94.02% accuracy (95% CI: 90.33%-96.62%), 71.15% sensitivity (95% CI: 56.92%-82.87%), and 100% specificity (95% CI: 98.16%-100.00%), compared with human reading, which achieved 89.2% accuracy (95% CI: 84.74%-92.79%), 48.1% sensitivity (95% CI: 34.01%-62.37%), and 100% specificity (95% CI: 98.16%-100.00%). By computationally untangling true analyte signals from assay noises in POC settings, WPA provides a transformative, device-adaptable pathway to improve POCT accuracy and precision without altering assay hardware or chemistry.
ER  -