EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Leakage-Controlled Deep Learning for Multi-Analyte Classification and Quantification in Fast-Scan Cyclic Voltammetry

Navoda Udawaththa iD, Parth Ganeriwala iD, Khan Mohammad Al Farabi, Brianna Romero, Siddhartha Bhattacharyya iD, Pavithra Pathirathna iD

Sensors · 08.11.2026 · 26 (21) · 7059

DOI: 10.3390/s26217059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.11.2026. Verfasst von Navoda Udawaththa und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry and Chemical Engineering, Florida Institute of Technology, Melbourne, FL 32901, USA. Hauptthemen laut MEDLINE: Deep Learning, Electrochemical Techniques. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fast-scan cyclic voltammetry (FSCV) is a widely used electrochemical technique for real-time monitoring of neurotransmitters; however, quantitative interpretation remains dependent on calibration curves generated in simplified in vitro environments that may not accurately reflect the complexity of biological matrices. To address the need for automated FSCV interpretation, we developed a two-stage artificial intelligence (AI) framework integrating analyte classification and concentration prediction. FSCV data were collected for serotonin (5-HT), dopamine (DA), ascorbic acid (AA), and copper (Cu2+) using analyte-specific waveforms, generating a dataset of 30,811 cyclic voltammograms from 192 independent experimental runs. Classification models were evaluated using strict run-level partitioning, while regression performance was additionally assessed using run-level and leave-one-electrode-out (LOEO) validation. Four classification architectures were evaluated: a lightweight image-based convolutional neural network (CNN), a feature-engineered multilayer perceptron (MLP), a transfer-learning ResNet18 model, and a one-dimensional CNN (1D-CNN) trained directly on raw voltammograms. The 1D-CNN achieved the highest classification accuracy (99.8%), outperforming transfer learning (98.68%), the lightweight CNN (97.38%), and the feature-based MLP (76.3 ± 0.6%) while maintaining substantially lower model complexity than ResNet18. Input-channel ablation indicated that waveform-specific acquisition protocols contributed to classification performance. For quantitative analysis, analyte-specific artificial neural networks (ANNs) were trained to predict concentrations from voltammetric morphology, achieving coefficients of determination (R2) of 0.9958, 0.9970, 0.9849, and 0.9561 for 5-HT, DA, Cu2+, and AA, respectively, under the original random sample-level partitioning. However, mean R2 values decreased to 0.74–0.88 under run-level validation and 0.61–0.86 under LOEO validation, with conventional peak-current calibration outperforming the ANNs under LOEO conditions. Integration of classification and regression models into an automated inference pipeline enabled sequential analyte identification and concentration estimation from FSCV data. In an additional end-to-end evaluation using the 1D-CNN classifier and analyte-specific ANN regressors, incorrect analyte routing, although infrequent (approximately 0.8%), produced substantial concentration-prediction errors. These results demonstrate the potential of morphology-aware deep learning for automated FSCV interpretation while highlighting the need for improved quantitative reliability and further validation using independent electrodes, mixed-analyte samples, and complex biological matrices.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningElectrochemical TechniquesConvolutional Neural NetworksCopperMultilayer PerceptronsDopamineSerotoninAscorbic AcidNeural Networks, ComputerClassification Algorithms

Stichwörter der Autor:innen

artificial neural networkconvolutional neural networkfast scan cyclic voltammetryheavy metalsneurotransmitters

Substanzen

CopperDopamineSerotoninAscorbic Acid

Autor:innen und Institutionen

  • Department of Chemistry and Chemical Engineering, Florida Institute of Technology, Melbourne, FL 32901, USA.
  • Department of Electrical Engineering and Computer Science, Florida Institute of Technology, Melbourne, FL 32901, USA.

ORCID-Profile: Navoda Udawaththa, Parth Ganeriwala, Siddhartha Bhattacharyya, Pavithra Pathirathna

Zitieren

APA

Udawaththa, N., Ganeriwala, P., Farabi, K. M. A., Romero, B., Bhattacharyya, S., & Pathirathna, P. (2026). Leakage-Controlled Deep Learning for Multi-Analyte Classification and Quantification in Fast-Scan Cyclic Voltammetry. Sensors, 26(21), 7059. https://doi.org/10.3390/s26217059

Vancouver

Udawaththa N, Ganeriwala P, Farabi KMA, Romero B, Bhattacharyya S, Pathirathna P. Leakage-Controlled Deep Learning for Multi-Analyte Classification and Quantification in Fast-Scan Cyclic Voltammetry. Sensors. 2026;26(21):7059. doi:10.3390/s26217059

BibTeX
@article{Udawaththa2026,
  author = {Udawaththa, Navoda and Ganeriwala, Parth and Farabi, Khan Mohammad Al and Romero, Brianna and Bhattacharyya, Siddhartha and Pathirathna, Pavithra},
  title = {Leakage-Controlled Deep Learning for Multi-Analyte Classification and Quantification in Fast-Scan Cyclic Voltammetry},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7059},
  doi = {10.3390/s26217059}
}
Kostenlos starten →