Machine learning toward high-performance electrochemical sensors.

The so-coined fourth paradigm in science has reached the sensing area, with the use of machine learning (ML) toward data-driven improvements in sensitivity, reproducibility, and accuracy, along with the determination of multiple targets from a single measurement using multi-output regression models. Particularly, the use of supervised ML models trained on large data sets produced by electrical and electrochemical bio/sensors has emerged as an impacting trend in the literature by allowing accurate analyses even in the presence of usual issues such as electrode fouling, poor signal-to-noise ratio, chemical interferences, and matrix effects. In this trend article, apart from an outlook for the coming years, we present examples from the literature that demonstrate how helpful ML algorithms can be for dispensing the adoption of experimental methods to address the aforesaid interfering issues, ultimately contributing to translate testing technologies into on-site, practical, and daily applications.

Ultradense Electrochemical Chips with Arrays of Nanostructured Microelectrodes to Enable Sensitive Diffusion-Limited Bioassays.

Nanostructured microelectrodes (NMEs) are an attractive alternative to yield sensitive bioassays in unprocessed samples. However, although valuable for different applications, nanoporous NMEs usually cannot boost the sensitivity of diffusion-limited analyses because of the enlarged Debye length within the nanopores, which reduces their accessibility. To circumvent this limitation, nanopore-free gold NMEs were electrodeposited from 45 µm SU-8 apertures, featuring nanoridged microspikes on a recessed surface of gold thin film while carrying interconnected crown-like and spiky structures along the edge of a SU-8 passivation layer. These structures were grown onto ultradense, vertical array chips that offer a promising strategy for translating reproducible, high-resolution, and cost-effective sensors into real-world applications. The NMEs yielded reproducible analyses, while machine learning allowed us to predict the analytical responses from NME electrodeposition data. By taking advantage of the high surface area and accessible structure of the NMEs, these structures provided a sensitivity for [Fe(CN)6]3-/4- that was 5.5× higher than that of bare WEs while also delivering a moderate antibiofouling property in undiluted human plasma. As a proof of concept, these electrodes were applied toward the fast (22 min) and simple determination of Staphylococcus aureus by monitoring the oxidation of [Fe(CN)6]4-, which acted as a cellular respiration rate redox reporter. The sensors also showed a wide dynamic range, spanning 5 orders of magnitude, and a calculated limit of detection of 0.2 CFU mL-1.

Single-Response Duplexing of Electrochemical Label-Free Biosensor from the Same Tag.

Multiplexing is a valuable strategy to boost throughput and improve clinical accuracy. Exploiting the vertical, meshed design of reproducible and low-cost ultra-dense electrochemical chips, the unprecedented single-response multiplexing of typical label-free biosensors is reported. Using a cheap, handheld one-channel workstation and a single redox probe, that is, ferro/ferricyanide, the recognition events taking place on two spatially resolved locations of the same working electrode can be tracked along a single voltammetry scan by collecting the electrochemical signatures of the probe in relation to different quasi-reference electrodes, Au (0 V) and Ag/AgCl ink (+0.2 V). This spatial isolation prevents crosstalk between the redox tags and interferences over functionalization and binding steps, representing an advantage over the existing non-spatially resolved single-response multiplex strategies. As proof of concept, peptide-tethered immunosensors are demonstrated to provide the duplex detection of COVID-19 antibodies, thereby doubling the throughput while achieving 100% accuracy in serum samples. The approach is envisioned to enable broad applications in high-throughput and multi-analyte platforms, as it can be tailored to other biosensing devices and formats.