Role of Machine Learning Assisted Biosensors in Point-of-Care-Testing For Clinical Decisions

Point-of-Care-Testing (PoCT) has emerged as an essential component of modern healthcare, providing rapid, low-cost, and simple diagnostic options. The integration of Machine Learning (ML) into biosensors has ushered in a new era of innovation in the field of PoCT. This article investigates the numerous uses and transformational possibilities of ML in improving biosensors for PoCT. ML algorithms, which are capable of processing and interpreting complicated biological data, have transformed the accuracy, sensitivity, and speed of diagnostic procedures in a variety of healthcare contexts. This review explores the multifaceted applications of ML models, including classification and regression, displaying how they contribute to improving the diagnostic capabilities of biosensors. The roles of ML-assisted electrochemical sensors, lab-on-a-chip sensors, electrochemiluminescence/chemiluminescence sensors, colorimetric sensors, and wearable sensors in diagnosis are explained in detail. Given the increasingly important role of ML in biosensors for PoCT, this study serves as a valuable reference for researchers, clinicians, and policymakers interested in understanding the emerging landscape of ML in point-of-care diagnostics.

SOFB is a comprehensive ensemble deep learning approach for elucidating and characterizing protein-nucleic-acid-binding residues

Proteins and nucleic-acids are essential components of living organisms that interact in critical cellular processes. Accurate prediction of nucleic acid-binding residues in proteins can contribute to a better understanding of protein function. However, the discrepancy between protein sequence information and obtained structural and functional data renders most current computational models ineffective. Therefore, it is vital to design computational models based on protein sequence information to identify nucleic acid binding sites in proteins. Here, we implement an ensemble deep learning model-based nucleic-acid-binding residues on proteins identification method, called SOFB, which characterizes protein sequences by learning the semantics of biological dynamics contexts, and then develop an ensemble deep learning-based sequence network to learn feature representation and classification by explicitly modeling dynamic semantic information. Among them, the language learning model, which is constructed from natural language to biological language, captures the underlying relationships of protein sequences, and the ensemble deep learning-based sequence network consisting of different convolutional layers together with Bi-LSTM refines various features for optimal performance. Meanwhile, to address the imbalanced issue, we adopt ensemble learning to train multiple models and then incorporate them. Our experimental results on several DNA/RNA nucleic-acid-binding residue datasets demonstrate that our proposed model outperforms other state-of-the-art methods. In addition, we conduct an interpretability analysis of the identified nucleic acid binding residue sequences based on the attention weights of the language learning model, revealing novel insights into the dynamic semantic information that supports the identified nucleic acid binding residues. SOFB is available at https://github.com/Encryptional/SOFB and https://figshare.com/articles/online_resource/SOFB_figshare_rar/25499452 .

A perspective on computer vision in biosensing

Computer vision has become a powerful tool in the field of biosensing, aiding in the development of innovative and precise systems for the analysis and interpretation of biological data. This interdisciplinary approach harnesses the capabilities of computer vision algorithms and techniques to extract valuable information from various biosensing applications, including medical diagnostics, environmental monitoring, and food health. Despite years of development, there is still significant room for improvement in this area. In this perspective, we outline how computer vision is applied to raw sensor data in biosensors and its advantages to biosensing applications. We then discuss ongoing research and developments in the field and subsequently explore the challenges and opportunities that computer vision faces in biosensor applications. We also suggest directions for future work, ultimately underscoring the significant impact of computer vision on advancing biosensing technologies and their applications.

Machine Learning in Bioelectrocatalysis

At present, the global energy crisis and environmental pollution coexist, and the demand for sustainable clean energy has been highly concerned. Bioelectrocatalysis that combines the benefits of biocatalysis and electrocatalysis produces high-value chemicals, clean biofuel, and biodegradable new materials. It has been applied in biosensors, biofuel cells, and bioelectrosynthesis. However, there are certain flaws in the application process of bioelectrocatalysis, such as low accuracy/efficiency, poor stability, and limited experimental conditions. These issues can possibly be solved using machine learning (ML) in recent reports although the combination of them is still not mature. To summarize the progress of ML in bioelectrocatalysis, this paper first introduces the modeling process of ML, then focuses on the reports of ML in bioelectrocatalysis, and ultimately makes a summary and outlook about current issues and future directions. It is believed that there is plenty of scope for this interdisciplinary research direction.

Reduction of Biosensor False Responses and Time Delay Using Dynamic Response and Theory-Guided Machine Learning

Here, we provide a new methodology for reducing false results and time delay of biosensors, which are barriers to industrial, healthcare, military, and consumer applications. We show that integrating machine learning with domain knowledge in biosensing can complement and improve the biosensor accuracy and speed relative to the performance achieved by traditional regression analysis of a standard curve based on the biosensor steady-state response. The methodology was validated by rapid and accurate quantification of microRNA across the nanomolar to femtomolar range using the dynamic response of cantilever biosensors. Theory-guided feature engineering improved the performance and efficiency of several classification models relative to the performance achieved using traditional feature engineering methods (TSFRESH). In addition to the entire dynamic response, the technique enabled rapid and accurate quantification of the target analyte concentration and false-positive and false-negative results using the initial transient response, thereby reducing the required data acquisition time (i.e., time delay). We show that model explainability can be achieved by combining theory-guided feature engineering and feature importance analysis. The performance of multiple classifiers using both TSFRESH- and theory-based features from the biosensor's initial transient response was similar to that achieved using the entire dynamic response with data augmentation. We also show that the methodology can guide design of experiments for high-performance biosensing applications, specifically, the selection of data acquisition parameters (e.g., time) based on potential application-dependent performance thresholds. This work provides an example of the opportunities for improving biosensor performance, such as reducing biosensor false results and time delay, using explainable machine learning models supervised by domain knowledge in biosensing.

Advancements in SARS-CoV-2 Testing: Enhancing Accessibility through Machine Learning-Enhanced Biosensors

The COVID-19 pandemic highlighted the importance of widespread testing for SARS-CoV-2, leading to the development of various new testing methods. However, traditional invasive sampling methods can be uncomfortable and even painful, creating barriers to testing accessibility. In this article, we explore how machine learning-enhanced biosensors can enable non-invasive sampling for SARS-CoV-2 testing, revolutionizing the way we detect and monitor the virus. By detecting and measuring specific biomarkers in body fluids or other samples, these biosensors can provide accurate and accessible testing options that do not require invasive procedures. We provide examples of how these biosensors can be used for non-invasive SARS-CoV-2 testing, such as saliva-based testing. We also discuss the potential impact of non-invasive testing on accessibility and accuracy of testing. Finally, we discuss potential limitations or biases associated with the machine learning algorithms used to improve the biosensors and explore future directions in the field of machine learning-enhanced biosensors for SARS-CoV-2 testing, considering their potential impact on global healthcare and disease control.

A Connected World: System-Level Support Through Biosensors

The goal of protecting the health of future generations is a blueprint for future biosensor design. Systems-level decision support requires that biosensors provide meaningful service to society. In this review, we summarize recent developments in cyber physical systems and biosensors connected with decision support. We identify key processes and practices that may guide the establishment of connections between user needs and biosensor engineering using an informatics approach. We call for data science and decision science to be formally connected with sensor science for understanding system complexity and realizing the ambition of biosensors-as-a-service. This review calls for a focus on quality of service early in the design process as a means to improve the meaningful value of a given biosensor. We close by noting that technology development, including biosensors and decision support systems, is a cautionary tale. The economics of scale govern the success, or failure, of any biosensor system.

Applications of Transistor-Based Biochemical Sensors

Transistor-based biochemical sensors feature easy integration with electronic circuits and non-invasive real-time detection. They have been widely used in intelligent wearable devices, electronic skins, and biological analyses and have shown broad application prospects in intelligent medical detection. Field-effect transistor (FET) sensors have high sensitivity, reasonable specificity, rapid response, and portability and provide unique signal amplification during biochemical detection. Organic field-effect transistor (OFET) sensors are lightweight, flexible, foldable, and biocompatible with wearable devices. Organic electrochemical transistor (OECT) sensors convert biological signals in body fluids into electrical signals for artificial intelligence analysis. In addition to biochemical markers in body fluids, electrophysiology indicators such as electrocardiogram (ECG) signals and body temperature can also cause changes in the current or voltage of transistor-based biochemical sensors. When modified with sensitive substances, sensors can detect specific analytes, improve sensitivity, broaden the detection range, and reduce the limit of detection (LoD). In this review, we introduce three kinds of transistor-based biochemical sensors: FET, OFET, and OECT. We also discuss the fabrication processes for transistor sources, drains, and gates. Furthermore, we demonstrated three sensor types for body fluid biomarkers, electrophysiology signals, and development trends. Transistor-based biochemical sensors exhibit excellent potential in multi-mode intelligent analysis and are good candidates for the next generation of intelligent point-of-care testing (iPOCT).

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.

Wearable artificial intelligence biosensor networks

The demand for high-quality healthcare and well-being services is remarkably increasing due to the ageing global population and modern lifestyles. Recently, the integration of wearables and artificial intelligence (AI) has attracted extensive academic and technological attention for its powerful high-dimensional data processing of wearable biosensing networks. This work reviews the recent developments in AI-assisted wearable biosensing devices in disease diagnostics and fatigue monitoring demonstrating the trend towards personalised medicine with highly efficient, cost-effective, and accurate point-of-care diagnosis by finding hidden patterns in biosensing data and detecting abnormalities. The reliability of adaptive learning and synthetic data and data privacy still need further investigation to realise personalised medicine in the next decade. Due to the worldwide popularity of smartphones, they have been utilised for sensor readout, wireless data transfer, data processing and storage, result display, and cloud server communication leading to the development of smartphone-based biosensing systems. The recent advances have demonstrated a promising future for the healthcare system because of the increasing data processing power, transfer efficiency and storage capacity and diversifying functionalities.

E.P.A.S.S: Electroanalytical Pillbox Assessment Sensor System, A Case Study Using Metformin Hydrochloride

Adulteration of medications is an emerging and significant threat to human health and well-being, even though adulterants are still often not considered seriously in clinical or forensic toxicology. Screening of drug adulterations is a major challenge and concern for regulatory authorities worldwide. Metformin hydrochloride, an important drug to treat diabetes, is found to be adulterated worldwide and a major reason to worry about the health and safety procedure. We have demonstrated a first-of-a-kind electrochemical biomedical device utilizing exfoliated graphene oxide (GO)─Nafion-modified customized gold screen-printed electrodes (spiral electrochemical notification-coupled electrode, SENCE), driven by electrochemical adsorptive stripping voltammetry, to identify the trace level adulteration in metformin. The GO-Nafion-SPE interface has been characterized by powder X-ray diffraction, X-ray photoelectron spectroscopy, scanning electron microscopy, energy-dispersive X-ray analysis, and Fourier transform infrared. Custom-made screen-printed SENCEs have been functionalized with GO nanoparticles (transducer) to obtain a fingerprint signal response of metformin using differential pulse voltammetry. A linear calibrated dose response has been obtained with n = 3 repetitions with a low limit of detection of 10 ppm for metformin. We have used the sensing response as a function of adulteration, and it is extensively supported by rigorous statistical analysis along with the help of the machine learning tool. This is a first-of-its-kind IoT-enabled electrochemical sensor and analysis platform that can detect drug adulteration as a low, medium, and high output.

Development of a Biosensor Based on Angiotensin-Converting Enzyme II for Severe Acute Respiratory Syndrome Coronavirus 2 Detection in Human Saliva

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the novel coronavirus responsible for COVID-19. Infection in humans requires angiotensin-converting enzyme II (hACE2) as the point of entry for SARS-CoV-2. PCR testing is generally definitive but expensive, although it is highly sensitive and accurate. Biosensor-based monitoring could be a low-cost, accurate, and non-invasive approach to improve testing capacity. We develop a capacitive hACE2 biosensor for intact SARS-CoV-2 detection in saliva. Laser-induced graphene (LIG) electrodes were modified with platinum nanoparticles. The quality control of LIG electrodes was performed using cyclic voltammetry. Truncated hACE2 was used as a biorecognition element and attached to the electrode surface by streptavidin-biotin coupling. Biolayer interferometry was used for qualitative interaction screening of hACE2 with UV-attenuated virions. Electrochemical impedance spectroscopy (EIS) was used for signal transduction. Truncated hACE2 binds wild-type SARS-CoV-2 and its variants with greater avidity than human coronavirus (common cold virus). The limit of detection (LoD) is estimated to be 2,960 copies/ml. The detection process usually takes less than 30 min. The strength of these features makes the hACE2 biosensor a potentially low-cost approach for screening SARS-CoV-2 in non-clinical settings with high demand for rapid testing (for example, schools and airports).

Machine Learning for Estimating Electron Transfer Rates From Square Wave Voltammetry

Electrochemistry of surface-bound molecules is of high importance for numerous electronic and sensor applications. Extracting the electron transfer rate is beneficial for understanding surface-bound processes, but it requires experimental or computational rigor. We evaluate methods to determine electron transfer rates from large voltammetry sets from experiments via machine learning using decision tree ensembles, neural networks, and gaussian process regression models. We applied these to reproduce computational measures of electron transfer rates modeled by first principles. The best machine learning models were a random forest with 80 decision trees and a neural network with Bayesian regularization, producing root mean squared errors of 0.37 and 0.49 s-1 , respectively, corresponding to mean percent errors of 0.38 % and 0.52 %, respectively. This work establishes machine learning methods for rapidly acquiring electron transfer rates across large datasets for widespread applications.

Machine learning and chemometrics for electrochemical sensors: moving forward to the future of analytical chemistry

Electrochemical sensors and biosensors have been successfully used in a wide range of applications, but systematic optimization and nonlinear relationships have been compromised for electrode fabrication and data analysis. Machine learning and experimental designs are chemometric tools that have been proved to be useful in method development and data analysis. This minireview summarizes recent applications of machine learning and experimental designs in electroanalytical chemistry. First, experimental designs, e.g., full factorial, central composite, and Box-Behnken are discussed as systematic approaches to optimize electrode fabrication to consider the effects from individual variables and their interactions. Then, the principles of machine learning algorithms, including linear and logistic regressions, neural network, and support vector machine, are introduced. These machine learning models have been implemented to extract complex relationships between chemical structures and their electrochemical properties and to analyze complicated electrochemical data to improve calibration and analyte classification, such as in electronic tongues. Lastly, the future of machine learning and experimental designs in electrochemical sensors is outlined. These chemometric strategies will accelerate the development and enhance the performance of electrochemical devices for point-of-care diagnostics and commercialization.

Machine Learning Analysis for Phenolic Compound Monitoring Using a Mobile Phone-Based ECL Sensor

Machine learning (ML) can be an appropriate approach to overcoming common problems associated with sensors for low-cost, point-of-care diagnostics, such as non-linearity, multidimensionality, sensor-to-sensor variations, presence of anomalies, and ambiguity in key features. This study proposes a novel approach based on ML algorithms (neural nets, Gaussian Process Regression, among others) to model the electrochemiluminescence (ECL) quenching mechanism of the [Ru(bpy)₃]²⁺/TPrA system by phenolic compounds, thus allowing their detection and quantification. The relationships between the concentration of phenolic compounds and their effect on the ECL intensity and current data measured using a mobile phone-based ECL sensor is investigated. The ML regression tasks with a tri-layer neural net using minimally processed time series data showed better or comparable detection performance compared to the performance using extracted key features without extra preprocessing. Combined multimodal characteristics produced an 80% more enhanced performance with multilayer neural net algorithms than a single feature based-regression analysis. The results demonstrated that the ML could provide a robust analysis framework for sensor data with noises and variability. It demonstrates that ML strategies can play a crucial role in chemical or biosensor data analysis, providing a robust model by maximizing all the obtained information and integrating nonlinearity and sensor-to-sensor variations.

FEAST of biosensors: Food, environmental and agricultural sensing technologies (FEAST) in North America

We review the challenges and opportunities for biosensor research in North America aimed to accelerate translational research. We call for platform approaches based on: i) tools that can support interoperability between food, environment and agriculture, ii) open-source tools for analytics, iii) algorithms used for data and information arbitrage, and iv) use-inspired sensor design. We summarize select mobile devices and phone-based biosensors that couple analytical systems with biosensors for improving decision support. Over 100 biosensors developed by labs in North America were analyzed, including lab-based and portable devices. The results of this literature review show that nearly one quarter of the manuscripts focused on fundamental platform development or material characterization. Among the biosensors analyzed for food (post-harvest) or environmental applications, most devices were based on optical transduction (whether a lab assay or portable device). Most biosensors for agricultural applications were based on electrochemical transduction and few utilized a mobile platform. Presently, the FEAST of biosensors has produced a wealth of opportunity but faces a famine of actionable information without a platform for analytics.

Four electrode-based impedimetric biosensors for evaluating cytotoxicity of tamoxifen on cervical cancer cells

In the current study, novel four electrode-based impedimetric biosensors have been fabricated using photolithography techniques and utilized to evaluate the cytotoxicity of tamoxifen on cervical cancer cell lines. The cell impedance was measured employing the electric cell-substrate impedance sensing (ECIS) method over the frequency range of 100 Hz to 1 MHz. The results obtained from impedimetric biosensors indicate that tamoxifen caused a significant reduction in the number of HeLa cells on the electrode surfaces in a dose-dependent manner. Next, the impedance values recorded by the fabricated biosensors have been compared with the results obtained from the different conventional techniques such as 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl tetrazolium bromide (MTT), live-dead cell assay, and flow cytometric analysis to estimate the cytotoxicity of tamoxifen. The impedimetric cytotoxicity of tamoxifen over the growth and proliferation of HeLa cells correlates well with the traditional methods. In addition, the IC50 values obtained from impedimetric data and MTT assay are comparable, signifying that the ECIS technique can be an alternative method to assess the cytotoxicity of different novel drugs. The working principle of the biosensor has been examined by scanning electron microscopy, indicating the detachment of cells from gold surfaces in a dose-dependent manner, signifying the decrease in impedance at higher drug doses.

Advancing Biosensors with Machine Learning

Chemometrics play a critical role in biosensors-based detection, analysis, and diagnosis. Nowadays, as a branch of artificial intelligence (AI), machine learning (ML) have achieved impressive advances. However, novel advanced ML methods, especially deep learning, which is famous for image analysis, facial recognition, and speech recognition, has remained relatively elusive to the biosensor community. Herein, how ML can be beneficial to biosensors is systematically discussed. The advantages and drawbacks of most popular ML algorithms are summarized on the basis of sensing data analysis. Specially, deep learning methods such as convolutional neural network (CNN) and recurrent neural network (RNN) are emphasized. Diverse ML-assisted electrochemical biosensors, wearable electronics, SERS and other spectra-based biosensors, fluorescence biosensors and colorimetric biosensors are comprehensively discussed. Furthermore, biosensor networks and multibiosensor data fusion are introduced. This review will nicely bridge ML with biosensors, and greatly expand chemometrics for detection, analysis, and diagnosis.

Planar Interdigitated Aptasensor for Flow-Through Detection of Listeria spp. in Hydroponic Lettuce Growth Media

Irrigation water is a primary source of fresh produce contamination by bacteria during the preharvest, particularly in hydroponic systems where the control of pests and pathogens is a major challenge. In this work, we demonstrate the development of a Listeria biosensor using platinum interdigitated microelectrodes (Pt-IME). The sensor is incorporated into a particle/sediment trap for the real-time analysis of irrigation water in a hydroponic lettuce system. We demonstrate the application of this system using a smartphone-based potentiostat for rapid on-site analysis of water quality. A detailed characterization of the electrochemical behavior was conducted in the presence/absence of DNA and Listeria spp., which was followed by calibration in various solutions with and without flow. In flow conditions (100 mL samples), the aptasensor had a sensitivity of 3.37 ± 0.21 k log-CFU-1 mL, and the LOD was 48 ± 12 CFU mL-1 with a linear range of 102 to 104 CFU mL-1. In stagnant solution with no flow, the aptasensor performance was significantly improved in buffer, vegetable broth, and hydroponic media. Sensor hysteresis ranged from 2 to 16% after rinsing in a strong basic solution (direct reuse) and was insignificant after removing the aptamer via washing in Piranha solution (reuse after adsorption with fresh aptamer). This is the first demonstration of an aptasensor used to monitor microbial water quality for hydroponic lettuce in real time using a smartphone-based acquisition system for volumes that conform with the regulatory standards. The aptasensor demonstrated a recovery of 90% and may be reused a limited number of times with minor washing steps.

Laser-Induced Graphene Electrochemical Immunosensors for Rapid and Label-Free Monitoring of Salmonella enterica in Chicken Broth

Food-borne illnesses are a growing concern for the food industry and consumers, with millions of cases reported every year. Consequently, there is a critical need to develop rapid, sensitive, and inexpensive techniques for pathogen detection in order to mitigate this problem. However, current pathogen detection strategies mainly include time-consuming laboratory methods and highly trained personnel. Electrochemical in-field biosensors offer a rapid, low-cost alternative to laboratory techniques, but the electrodes used in these biosensors require expensive nanomaterials to increase their sensitivity, such as noble metals (e.g., platinum, gold) or carbon nanomaterials (e.g., carbon nanotubes, or graphene). Herein, we report the fabrication of a highly sensitive and label-free laser-induced graphene (LIG) electrode that is subsequently functionalized with antibodies to electrochemically quantify the food-borne pathogen Salmonella enterica serovar Typhimurium. The LIG electrodes were produced by laser induction on the polyimide film in ambient conditions and, hence, circumvent the need for high-temperature, vacuum environment, and metal seed catalysts commonly associated with graphene-based electrodes fabricated via chemical vapor deposition processes. After functionalization with Salmonella antibodies, the LIG biosensors were able to detect live Salmonella in chicken broth across a wide linear range (25 to 10⁵ CFU mL^-1) and with a low detection limit (13 ± 7 CFU mL^-1; n = 3, mean ± standard deviation). These results were acquired with an average response time of 22 min without the need for sample preconcentration or redox labeling techniques. Moreover, these LIG immunosensors displayed high selectivity as demonstrated by nonsignificant response to other bacteria strains. These results demonstrate how LIG-based electrodes can be used for electrochemical immunosensing in general and, more specifically, could be used as a viable option for rapid and low-cost pathogen detection in food processing facilities before contaminated foods reach the consumer.

SNAPS: Sensor Analytics Point Solutions for Detection and Decision Support Systems

In this review, we discuss the role of sensor analytics point solutions (SNAPS), a reduced complexity machine-assisted decision support tool. We summarize the approaches used for mobile phone-based chemical/biological sensors, including general hardware and software requirements for signal transduction and acquisition. We introduce SNAPS, part of a platform approach to converge sensor data and analytics. The platform is designed to consist of a portfolio of modular tools which may lend itself to dynamic composability by enabling context-specific selection of relevant units, resulting in case-based working modules. SNAPS is an element of this platform where data analytics, statistical characterization and algorithms may be delivered to the data either via embedded systems in devices, or sourced, in near real-time, from mist, fog or cloud computing resources. Convergence of the physical systems with the cyber components paves the path for SNAPS to progress to higher levels of artificial reasoning tools (ART) and emerge as data-informed decision support, as a service for general societal needs. Proof of concept examples of SNAPS are demonstrated both for quantitative data and qualitative data, each operated using a mobile device (smartphone or tablet) for data acquisition and analytics. We discuss the challenges and opportunities for SNAPS, centered around the value to users/stakeholders and the key performance indicators users may find helpful, for these types of machine-assisted tools.

Laser Scribed Graphene Biosensor for Detection of Biogenic Amines in Food Samples Using Locally Sourced Materials

In foods, high levels of biogenic amines (BA) are the result of microbial metabolism that could be affected by temperatures and storage conditions. Thus, the level of BA is commonly used as an indicator of food safety and quality. This manuscript outlines the development of laser scribed graphene electrodes, with locally sourced materials, for reagent-free food safety biosensing. To fabricate the biosensors, the graphene surface was functionalized with copper microparticles and diamine oxidase, purchased from a local supermarket; and then compared to biosensors fabricated with analytical grade materials. The amperometric biosensor exhibits good electrochemical performance, with an average histamine sensitivity of 23.3 µA/mM, a lower detection limit of 11.6 µM, and a response time of 7.3 s, showing similar performance to biosensors constructed from analytical grade materials. We demonstrated the application of the biosensor by testing total BA concentration in fish paste samples subjected to fermentation with lactic acid bacteria. Biogenic amines concentrations prior to lactic acid fermentation were below the detection limit of the biosensor, while concentration after fermentation was 19.24 ± 8.21 mg histamine/kg, confirming that the sensor was selective in a complex food matrix. The low-cost, rapid, and accurate device is a promising tool for biogenic amine estimation in food samples, particularly in situations where standard laboratory techniques are unavailable, or are cost prohibitive. This biosensor can be used for screening food samples, potentially limiting food waste, while reducing chances of foodborne outbreaks.