AI-Assisted Detection of Biomarkers by Sensors and Biosensors for Early Diagnosis and Monitoring

Abstract

The steady progress in consumer electronics, together with improvement in microflow techniques, nanotechnology, and data processing, has led to implementation of cost-effective, user-friendly portable devices, which play the role of not only gadgets but also diagnostic tools. Moreover, numerous smart devices monitor patients' health, and some of them are applied in point-of-care (PoC) tests as a reliable source of evaluation of a patient's condition. Current diagnostic practices are still based on laboratory tests, preceded by the collection of biological samples, which are then tested in clinical conditions by trained personnel with specialistic equipment. In practice, collecting passive/active physiological and behavioral data from patients in real time and feeding them to artificial intelligence (AI) models can significantly improve the decision process regarding diagnosis and treatment procedures via the omission of conventional sampling and diagnostic procedures while also excluding the role of pathologists. A combination of conventional and novel methods of digital and traditional biomarker detection with portable, autonomous, and miniaturized devices can revolutionize medical diagnostics in the coming years. This article focuses on a comparison of traditional clinical practices with modern diagnostic techniques based on AI and machine learning (ML). The presented technologies will bypass laboratories and start being commercialized, which should lead to improvement or substitution of current diagnostic tools. Their application in PoC settings or as a consumer technology accessible to every patient appears to be a real possibility. Research in this field is expected to intensify in the coming years. Technological advancements in sensors and biosensors are anticipated to enable the continuous real-time analysis of various omics fields, fostering early disease detection and intervention strategies. The integration of AI with digital health platforms would enable predictive analysis and personalized healthcare, emphasizing the importance of interdisciplinary collaboration in related scientific fields.

Keywords: artificial intelligence; bioelectronics; biomarkers; biosensors; machine learning; sensors.

Figure 4

(A) One-step multiplex analysis of breast cancer exosomes based on an electrochemical strategy assisted by AuNPs. Reproduced with permission from [112]. (B) Setup of the AI–coupled plasmonic infrared sensor for the detection of structural protein biomarkers in neurodegenerative diseases. Reproduced with permission from [130]. (C) Scheme of the multiplexed quantitative detection of biomarkers in sputum by a PoC paper-microfluidic electrochemical device [113]. (D) Example of a handheld LC diagnosis device based on MIP sensor. A patient blows into the replaceable mouthpiece and the results will be shown on his/her smartphone instantly. The mobile application that graphs the data during the test, and the exploded view of the proposed lung cancer diagnosis handheld device. Reproduced with permission from [114]. (E) The construction and working process of the AuNPs@NIPAm-co-AAc microgel electrodes and detection process of miRNA-21. Reproduced with permission from [111].

Figure 1

A schematic representation of (bio)sensor components for detecting biomarkers. ML- and AI-based data processing enables integration and combination of traditional biomarkers with digital ones to personalize healthcare. The acquired data can then be collected, distributed, and evaluated by clinicians and individual patients. Created with BioRender.com.

Figure 2

The key stages during the development of diagnostic tools based on sensors and biosensors.

Figure 3

Examples of devices for the detection and/or monitoring of traditional biomarkers.

Figure 5

(A) Scheme of electrical impedance cytometer. As cells pass from the inlet to the outlet in these biosensors, alterations in impedance are detected by a lock-in amplifier. This amplifier can simultaneously apply signals at various frequencies. Subsequently, the data are recorded and analyzed using SVM. Reproduced with permission from [155]. (B) Interfacing 1D graphene nanoribbons with 2D MXene for the development of pressure biosensor, trained using ML algorithm. Reproduced with permission from [157]. (C) Schematic illustration of angiotensin converting enzyme 2 (ACE2)-functionalized AgNR@SiO₂ array for SARS-CoV-2 variant detection. Reproduced with permission from [162].

Figure 6

The scheme of analyzing proteomic data using BINNs. First step is the creation of a BINN for each dataset by selecting relevant pathways from a database such as Reactome. BINNs are trained using protein quantities from each sample to distinguish between two subphenotypes. Subsequently, SHAP (feature attribution method) is used to interpret the networks, providing feature importance values for biomarker identification. Reproduced with permission from [213]. Created with BioRender.com.

Figure 7

AI-assisted biomarker discovery compared to classic procedures.