The integration of artificial intelligence (AI) into point-of-care (POC) biosensing has the potential to revolutionize diagnostic methodologies by offering rapid, accurate, and accessible health assessment directly at the patient level. This review paper explores the transformative impact of AI technologies on POC biosensing, emphasizing recent computational advancements, ongoing challenges, and future prospects in the field. We provide an overview of core biosensing technologies and their use at the POC, highlighting ongoing issues and challenges that may be solved with AI. We follow with an overview of AI methodologies that can be applied to biosensing, including machine learning algorithms, neural networks, and data processing frameworks that facilitate real-time analytical decision-making. We explore the applications of AI at each stage of the biosensor development process, highlighting the diverse opportunities beyond simple data analysis procedures. We include a thorough analysis of outstanding challenges in the field of AI-assisted biosensing, focusing on the technical and ethical challenges regarding the widespread adoption of these technologies, such as data security, algorithmic bias, and regulatory compliance. Through this review, we aim to emphasize the role of AI in advancing POC biosensing and inform researchers, clinicians, and policymakers about the potential of these technologies in reshaping global healthcare landscapes.

Continuous measurement of proteins in vivo is important for real-time disease management and prevention. Implantable sensors for monitoring small molecules such as glucose have been available for more than a decade. However, analysis of proteins remains an unmet need because the lower physiological levels require that sensors have high affinities, which are linked to long complexation half-lives ( t _1/2 ~20 hours) and slow equilibration when concentrations decrease. We report active-reset sensors by use of high-frequency oscillations to accelerate dissociation, which enables regeneration of the unbound form of the sensor within 1 minute. When implemented within implanted devices, these sensors allow for real-time, in vivo monitoring of proteins within interstitial fluid. Active-reset protein sensors track biomarker levels on a physiological timescale for inflammation monitoring in living animals.

Wearable microneedle biosensors promise real-time molecular monitoring for precision medicine but are limited by low sensitivity and tissue abrasion. Overcoming these challenges, we recast electrode functionality not merely as a sensing substrate but as a mechanism for resilient, high signal-to-noise ratio (SNR) measurements in tissue. Our microneedle-based resilient nanostructured bioelectrode (RNB) is fabricated using a bilayer process that strengthens the electrode with a micrometer-thick gold adhesion layer and reduces fabrication-induced stress through controlled dealloying. The resulting RNBs are corrosion resistant, stable over a wide potential window, and have an artifact-free, nanocavity-textured interface. They integrate receptor-based electrochemical biosensors with enhanced SNR through increased active area, diffusion, and antifouling while remaining abrasion immune in megapascal-stiff tissues. The RNB extended in vivo biosensor lifetime for pharmacokinetics monitoring to 6 days in a freely moving rat. Paired with a blood–interstitial fluid equilibrium–based bioanalytical framework, the RNB accurately derived blood-equivalent pharmacokinetic parameters, enabling not only precision dosing of narrow therapeutic index drugs but also the direct assessment of hepatic and renal clearance. In hepatic studies, the RNB revealed delayed clearance of a chemotherapeutic (irinotecan) in liver-damaged models. In renal studies, RNB recordings correlated with blood antibiotic pharmacokinetics across chronic kidney disease severities. The RNB detected renal impairment earlier than conventional biomarker thresholds through drug clearance quantification and captured recovery under therapeutic intervention. These results establish the RNB as a viable microneedle platform for high-fidelity in vivo deployment of electrochemical biosensors, enabling minimally invasive, longitudinal monitoring of low-concentration analytes and real-time assessment of organ function.

Over the past four decades, Lyme disease has remained a virulent and pervasive illness, persisting throughout North America and many other regions of the world. Recent increases in illness in many countries has sparked a renewed interest in improved Lyme diagnostics. While current standards of diagnosis are acceptable for the late stages of the disease, it remains difficult to accurately diagnose early forms of the illness. In addition, current diagnostic methods tend to be relatively expensive and require a large degree of laboratory-based analysis. Biosensors represent the fusion of biological materials with chemical techniques to provide simple, inexpensive alternatives to traditional diagnostic methods. Lyme disease biosensors have the potential to better diagnose early stages of the illness and provide possible patients with an inexpensive, commercially available test. This review examines the current state of Lyme disease biosensing, with a focus on previous biosensor development and essential future considerations.

Lyme disease, caused by infection with pathogenic Borrelia bacteria, has emerged as a pervasive illness throughout North America and many other regions of the world in recent years, owing in part to climate-mediated habitat expansion of the tick vectors. Standard diagnostic testing has remained largely unchanged over the past several decades and is indirect, relying on detection of antibodies against the Borrelia pathogen, rather than detection of the pathogen itself. The development of new rapid, point-of-care tests for Lyme disease that directly detects the pathogen could drastically improve patient health by enabling faster and more frequent testing that could better inform patient treatment. Here, we describe a proof-of-concept electrochemical sensing approach to the detection of the Lyme disease-causing bacteria, which utilizes a biomimetic electrode to interact with the Borrelia bacteria that induce impedance alterations. In addition, the catch-bond mechanism between bacterial BBK32 protein and human fibronectin protein, which exhibits improved bond strength with increased tensile force, is tested within an electrochemical injection flow-cell to achieve Borrelia detection under shear stress.

Cuprous oxide (Cu₂O) was synthesized for the first time via an open bipolar electrochemistry (BPE) approach and characterized in parallel with the commercially available material. As compared to the reference, Cu₂O formed through a BPE reaction demonstrated a decrease in particle size; an increase in photocurrent; more efficient light scavenging; and structure-correlated changes in the flat band potential and charge carrier concentration. More importantly, as-synthesized oxides were all phase-pure, defect-free, and had an average crystallite size of 20 nm. Ultimately, this study demonstrates the impact of reaction conditions (e.g., applied potential, reaction time) on structure, morphology, surface chemistry, and photo-electrochemical activity of semiconducting oxides, and at the same time, the ability to maintain a green synthetic protocol and potentially create a scalable product. In the proposed BPE synthesis, we introduced a common food supplement (potassium gluconate) as a reducing and complexing agent, and as an electrolyte, allowing us to replace the more harmful reactants that are conventionally used in Cu₂O production. In addition, in the BPE process very corrosive reactants, such as hydroxides and metal precursors (required for synthesis of oxides), are generated in situ in stoichiometric quantity, providing an alternative methodology to generate various nanostructured materials in high yields under mild conditions.