Electrochemical and optical detection and machine learning applied to images of genosensors for diagnosis of prostate cancer with the biomarker PCA3

Ribas L.C., Sá Junior J.J., Scabini L.F., Bruno O.M.

• A high texture descriptor is proposed. • It is based on the fusion of complex networks and randomized neural networks. • Texture images are modelled as complex networks with different scales. • Network topological characteristics are used to train a randomized neural network. • The output weights of the randomized neural network are used as a texture descriptors. This paper presents a high discriminative texture analysis method based on the fusion of complex networks and randomized neural networks. In this approach, the input image is modeled as a complex network and its topological properties as well as the image pixels are used to train randomized neural networks to create a signature that represents the deep characteristics of the texture. The results obtained surpassed the accuracy of many methods available in the literature. This performance demonstrates that our proposed approach opens a promising source of research, which consists of exploring the synergy of neural networks and complex networks in the texture analysis field.

Soares J.C., Soares A.C., Rodrigues V.C., Melendez M.E., Santos A.C., Faria E.F., Reis R.M., Carvalho A.L., Oliveira O.N.

Diagnosis of prostate cancer via PCA3 biomarker detection is promising to be much more efficient than with the prostatic specific antigens currently used. In this study, we present the first electrochemical and impedance-based biosensors that are capable of detecting PCA3 down to 0.128 nmol/L. The biosensors were made with a layer of PCA3-complementary single-stranded DNA (ssDNA) probe, immobilized on a layer-by-layer (LbL) film of chitosan (CHT) and carbon nanotubes (MWCNT). They are highly selective to PCA3, which was confirmed in impedance measurements and with polarization-modulated infrared reflection absorption spectroscopy (PM-IRRAS). Using information visualization methods, we could also distinguish between cell lines expressing the endogenous PCA3 long noncoding RNA (lncRNA) from cells that did not contain detectable levels of this biomarker. Since the methods involved in fabrication the biosensors are potentially low cost, one may hope to deploy PCA3 tests in any laboratory of clinical analyses and even for point-of-care diagnostics.

Qian L., Li Q., Baryeh K., Qiu W., Li K., Zhang J., Yu Q., Xu D., Liu W., Brand R.E., Zhang X., Chen W., Liu G.

Pancreatic cancer is characterized by extremely high mortality and poor prognosis and is projected to be the leading cause of cancer deaths by 2030. Due to the lack of early symptoms and appropriate methods to detect pancreatic carcinoma at an early stage as well as its aggressive progression, the disease is often quite advanced by the time a definite diagnosis is established. The 5-year relative survival rate for all stages is approximately 8%. Therefore, detection of pancreatic cancer at an early surgically resectable stage is the key to decrease mortality and to improve survival. The traditional methods for diagnosing pancreatic cancer involve an imaging test, such as ultrasound or magnetic resonance imaging, paired with a biopsy of the mass in question. These methods are often expensive, time consuming, and require trained professionals to use the instruments and analyze the imaging. To overcome these issues, biosensors have been proposed as a promising tool for the early diagnosis of pancreatic cancer. The present review critically discusses the latest developments in biosensors for the early diagnosis of pancreatic cancer. Protein and microRNA biomarkers of pancreatic cancer and corresponding biosensors for pancreatic cancer diagnosis have been reviewed, and all these cases demonstrate that the emerging biosensors are becoming an increasingly relevant alternative to traditional techniques. In addition, we discuss the existing problems in biosensors and future challenges.

Fu X., Wen J., Li J., Lin H., Liu Y., Zhuang X., Tian C., Chen L.

A simple, rapid and convenient SERS-based competitive lateral flow assay was developed for highly sensitive detection of PCA3 mimic DNA.

Bhatt G., Bhattacharya S.

Biosensors are a very well cherished research topic and have found an inseparable status from clinical diagnostics in specific and society at large. As the name suggests, biosensors or biological sensors are devices which detect the presence of biological entities or their constituents and derivatives. The field started decades ago and has matured quite well since its inception. The most important performance factors that are associated with biosensors are sensitivity, specificity, and limit of detection. The remaining efforts of the biosensor research domain focus on miniaturization aspects of the sensors. The growing advancements in this field have evolved the technology of biosensors to cater to full-scale diagnosis on microchips, bedside diagnostics, reduced cost, and increased speed of diagnostics. Biosensors are characterized through many different aspects; for example, one way is to classify them on the basis of the type of bio-recognition step that they would utilize or another way can be based on the type of detection scheme that they may integrate, etc. Depending on the bio-recognition layer’s properties, biosensors can be cell based, nucleic acid probe based, antibody/antigen based, or aptamer based, while depending on the type of detection scheme, biosensors can be viewed as colorimetric sensors, optical sensors, electrochemical sensors, mechanical sensors, etc. There are some other parallel areas of research like microfluidics and microelectromechanical systems where one of the main applications lies in the biosensor domain. This review article discusses the various aspects of biosensors, from their design, realization, to testing, along with various detection strategies. The assembly includes fabrication strategies particularly for microchip technology-based biosensing solutions, microchannels, integration to microfluidics, etc., while categorization deals with various kinds and applications of different biosensors.

Goldsmith B.R., Locascio L., Gao Y., Lerner M., Walker A., Lerner J., Kyaw J., Shue A., Afsahi S., Pan D., Nokes J., Barron F.

The prevailing philosophy in biological testing has been to focus on simple tests with easy to interpret information such as ELISA or lateral flow assays. At the same time, there has been a decades long understanding in device physics and nanotechnology that electrical approaches have the potential to drastically improve the quality, speed, and cost of biological testing provided that computational resources are available to analyze the resulting complex data. This concept can be conceived of as “the internet of biology” in the same way miniaturized electronic sensors have enabled “the internet of things.” It is well established in the nanotechnology literature that techniques such as field effect biosensing are capable of rapid and flexible biological testing. Until now, access to this new technology has been limited to academic researchers focused on bioelectronic devices and their collaborators. Here we show that this capability is retained in an industrially manufactured device, opening access to this technology generally. Access to this type of production opens the door for rapid deployment of nanoelectronic sensors outside the research space. The low power and resource usage of these biosensors enables biotech engineers to gain immediate control over precise biological and environmental data.

Eskra J.N., Rabizadeh D., Pavlovich C.P., Catalona W.J., Luo J.

Prostate cancer is the most common cancer in American men that ranges from low risk states amenable to active surveillance to high-risk states that can be lethal especially if untreated. There is a critical need to develop relatively non-invasive and clinically useful methods for screening, detection, prognosis, disease monitoring, and prediction of treatment efficacy. In this review, we focus on important advances as well as future efforts needed to drive clinical innovation in this area of urine biomarker research for prostate cancer detection and prognostication. We provide a review of current literature on urinary biomarkers for prostate cancer. We evaluate the strengths and limitations of a variety of approaches that vary in sampling strategies and targets measured; discuss reported urine tests for prostate cancer with respect to their technical, analytical, and clinical parameters; and provide our perspectives on critical considerations in approaches to developing a urine-based test for prostate cancer. There has been an extensive history of exploring urine as a source of biomarkers for prostate cancer that has resulted in a variety of urine tests that are in current clinical use. Importantly, at least three tests have demonstrated high sensitivity (~90%) and negative predictive value (~95%) for clinically significant tumors; however, there has not been widespread adoption of these tests. Conceptual and methodological advances in the field will help to drive the development of novel urinary tests that in turn may lead to a shift in the clinical paradigm for prostate cancer diagnosis and management.

Humeau-Heurtier A.

Texture analysis is used in a very broad range of fields and applications, from texture classification (e.g., for remote sensing) to segmentation (e.g., in biomedical imaging), passing through image synthesis or pattern recognition (e.g., for image inpainting). For each of these image processing procedures, first, it is necessary to extract—from raw images—meaningful features that describe the texture properties. Various feature extraction methods have been proposed in the last decades. Each of them has its advantages and limitations: performances of some of them are not modified by translation, rotation, affine, and perspective transform; others have a low computational complexity; others, again, are easy to implement; and so on. This paper provides a comprehensive survey of the texture feature extraction methods. The latter are categorized into seven classes: statistical approaches, structural approaches, transform-based approaches, model-based approaches, graph-based approaches, learning-based approaches, and entropy-based approaches. For each method in these seven classes, we present the concept, the advantages, and the drawbacks and give examples of application. This survey allows us to identify two classes of methods that, particularly, deserve attention in the future, as their performances seem interesting, but their thorough study is not performed yet.

Soares A.C., Soares J.C., Rodrigues V.C., Follmann H.D., Arantes L.M., Carvalho A.C., Melendez M.E., Fregnani J.H., Reis R.M., Carvalho A.L., Oliveira O.N.

High-risk human papillomavirus (HPV) infection, mainly with HPV16 type, has been increasingly considered as an important etiologic factor in head and neck cancers. Detection of HPV16 is therefore crucial for these types of cancer, but clinical tests are not performed routinely in public health systems owing to the high cost and limitations of the existing tests. In this article, we report on a potentially low-cost genosensor capable of detecting low concentrations of HPV16 in buffer samples and distinguishing, with high accuracy, head and neck cancer cell lines according to their HPV16 status. The genosensor consisted of a microfluidic device that had an active layer of a HPV16 capture DNA probe (cpHPV16) deposited onto a layer-by-layer film of chitosan and chondroitin sulfate. Impedance spectroscopy was the principle of detection utilized, leading to a limit of detection of 10.5 pM for complementary ssDNA HPV16 oligos (ssHPV16). The genosensor was also able to distinguish among HPV16+ and HPV16- cell lines, using the multidimensional projection technique interactive document mapping. Hybridization between the ssHPV16 oligos and cpHPV16 probe was confirmed with polarization-modulated infrared reflection-absorption spectroscopy, where PO2 and amide I and amide II bands from adenine and thymine were monitored. The electrical response could be modeled as resulting from an adsorption process represented in a Freundlich model. Because the fabrication procedures of the microfluidic devices and genosensors and the data collection and analysis can be implemented at low cost, the results presented here amount to a demonstration of possible routine screening for HPV infections.

Chistiakov D.A., Myasoedova V.A., Grechko A.V., Melnichenko A.A., Orekhov A.N.

The diagnostics and management of localized prostate cancer is complicated because of cancer heterogeneity and differentiated progression in various subgroups of patients. As a prostate cancer biomarker, FDA-approved detection assay for serum prostate specific antigen (PSA) and its derivatives are not potent enough to diagnose prostate cancer, especially high-grade disease (Gleason ≥7). To date, a collection of new biomarkers was developed. Some of these markers are superior for primary screening while others are particularly helpful for cancer risk stratification, detection of high-grade cancer, and prediction of adverse events. Two of those markers such as proPSA (a part of the Prostate Health Index (PHI)) and prostate specific antigen 3 (PCA3) (a part of the PCA3 Progensa test) were recently approved by FDA for clinical use. Other markers are not PDA-approved yet but are available from Clinical Laboratory Improvement Amendment (CLIA)-certified clinical laboratories. In this review, we characterize diagnostic performance of these markers and their diagnostic and prognostic utility for prostate cancer.

Kassal P., Steinberg M.D., Steinberg I.M.

Parallel advances in chemical sensing and wireless communication technologies have sparked the development of wireless chemical sensors (WCSs). These hybrid devices enable wireless determination, collection and distribution of (bio)chemical analytical information in a way that is significantly impacting the Sensor Internet of Things with applications in healthcare, defence, sport, the environment, and agriculture. Challenges and examples for each of the major chemical sensor and major radio technologies related to different application areas are reviewed, including the latest trends emerging from wearable sensors. The review focuses on radio-based WCSs, and finds that ubiquitous wireless technologies such as Bluetooth, ZigBee, radio-frequency identification (RFID) and near-field communication (NFC) are helping make analytical (bio)chemical sensing appropriate and realistic for mass market adoption, in particular for two major classes of chemical sensor – electrochemical and optical. The review provides an in-depth analysis of academic WCS research publications over the ten year period 2007–2017.

Rodrigues V.C., Moraes M.L., Soares J.C., Soares A.C., Sanfelice R., Deffune E., Oliveira O.N.

We report on immunosensors to detect D-dimer, a biomarker of venous thromboembolism, which are made with layer-by-layer (LbL) films containing immobilized anti-D-dimer monoclonal antibody alternated with a layer of chitosan/gold nanoparticles (AuNpChi). Detection was due to irreversible adsorption of the antigen D-dimer on its corresponding antibody according to a Langmuir-Freundlich model, thus giving rise to ellipsoidal structures in scanning electron microscopy images whose size and number increased with D-dimer concentration. The chemical groups involved in the adsorption process were inferred from polarization-modulated infrared reflection absorption (PM-IRRAS) through changes in the amide and carbonyl bands. Detection of D-dimer was made with electrical impedance spectroscopy, electrochemical impedance spectroscopy and cyclic voltammetry. The latter was the most sensitive with a detection limit of 9 × 10−4 µg/mL, sensitivity of 0.27 × 10−6 A/µgmL−1 with linear increase from 0 to 1 µg/mL. The selecti...

Ibau C., Md Arshad M.K., Gopinath S.C.

Early cancer diagnosis remains the holy-grail in the battle against cancers progression. Tainted with debates and medical challenges, current therapeutic approaches for prostate cancer (PCa) lack early preventive measures, rapid diagnostic capabilities, risk factors identification, and portability, i.e. the inherent attributes offered by the label-free biosensing devices. Electronic assisted immunosensing systems inherit the high sensitivity and specificity properties due to the predilection of the antigen-antibody affinity. Bioelectronic immunosensor for PCa has attracted much attentions among the researchers due to its high-performance, easy to prepare, rapid feedback, and possibility for miniaturization. This review explores the current advances on bioelectronic immunosensors for the detection of PCa biomarker revealed in the past decade. The research milestones and current trends of the immunosensors are reported to project the future visions in order to propel their "lab-to-market" realization.

Pasinszki T., Krebsz M., Tung T.T., Losic D.

Liu W., Wang Z., Liu X., Zeng N., Liu Y., Alsaadi F.E.

This work was supported in part the Royal Society of the UK, the National Natural Science Foundation of China under Grants 61329301, 61374010, and 61403319, and the Alexander von Humboldt Foundation of Germany.

Jihad S.M., Alsaud A.A., Almukhtar F.H., Kareem S., Yousif R.Z.

Oiticica P.R., Angelim M.K., Soares J.C., Soares A.C., Proença-Módena J.L., Bruno O.M., Oliveira O.N.

Khan A., Khan H., He N., Li Z., Alyahya H.K., Bin Jardan Y.A.

Lung cancer is a devastating public health threat and a leading cause of cancer-related deaths. Therefore, it is imperative to develop sophisticated techniques for the non-invasive detection of lung cancer. Extracellular vesicles expressing programmed death ligand-1 (PD-L1) markers (PD-L1@EVs) in the blood are reported to be indicative of lung cancer and response to immunotherapy. Our approach is the development of a colorimetric aptasensor by combining the rapid capturing efficiency of (Fe3O4)-SiO2-TiO2 for EV isolation with PD-L1 aptamer-triggered enzyme-linked hybridization chain reaction (HCR) for signal amplification. The numerous HRPs catalyze their substrate dopamine (colorless) into polydopamine (blackish brown). Change in chromaticity directly correlates with the concentration of PD-L1@EVs in the sample. The colorimetric aptasensor was able to detect PD-L1@EVs at concentrations as low as 3.6×102 EVs/mL with a wide linear range from 103 to 1010 EVs/mL with high specificity and successfully detected lung cancer patients’ serum from healthy volunteers’ serum. To transform the qualitative colorimetric approach into a quantitative operation, we developed an intelligent convolutional neural network (CNN)-powered quantitative analyzer for chromaticity in the form of a smartphone app named ExoP, thereby achieving the intelligent analysis of chromaticity with minimal user intervention or additional hardware attachments for the sensitive and specific quantification of PD-L1@EVs. This combined approach offers a simple, sensitive, and specific tool for lung cancer detection using PD-L1@EVs. The addition of a CNN-powered smartphone app further eliminates the need for specialized equipment, making the colorimetric aptasensor more accessible for low-resource settings.

Fu H., She Y., Chen H., Hu Y., Long W., Che S., Lan W., Fan Y., Wu M.

Hensel R.C., Di Vizio B., Materòn E.M., Shimizu F.M., Angelim M.K., de Souza G.F., Módena J.L., Moraes-Vieira P.M., de Azevedo R.B., Litti L., Agnoli S., Casalini S., Oliveira Jr. O.N.

Immunosensors based on electrical impedance spectroscopy allow for label-free, real-time detection of biologically relevant molecules and pathogens, without requiring electro-active materials. Here, we investigate the influence of bare gold nanoparticles (AuNPs), synthesized via laser ablation in solution, on the performance of an impedimetric immunosensor for detecting severe acute respiratory syndrome coronavirus (SARS-CoV-2). Graphene acetic acid (GAA) was used in the active layer for immobilizing anti-SARS-CoV-2 antibodies, owing to its high density of carboxylic groups. Immunosensors incorporating AuNPs exhibited superior performance compared to those relying solely on GAA, achieving a limit of detection (LoD) of 3 x 10

Zhang R., Zuo X., Yin F.

Alom S., Ali F., Kathuria D.

Point-of-care testing (POCT) via paper-based colorimetric sensors allows for on-site testing, with biomarker detection visible to the naked eye within minutes, leading to better health management. In this chapter, we emphasise the fundamentals, fabrication techniques and development of paper-based colorimetric sensors. The use of POCT paper-based colorimetric sensors for the diagnosis of biomarkers associated with various diseases such as COVID-19, HIV, dengue, malaria, diabetes, cancer, etc. has been discussed in detail. The application of paper-based colorimetric sensors in the detection of fertility and pregnancy has also been highlighted. The unique properties of paper have also been summarised in order to create cost-effective, simple and easy-to-use devices. In the end, the challenges and emerging opportunities of POCT, paper-based colorimetric sensors have also been discussed. This chapter paves the way for research in paper-based colorimetric sensors.

Li H., Wang X., Wu H., Wang W., Zheng A., Zhu J., Liang L., Sun H., Lu L., Lv J., Yu Q., Wang H., Yu B.

Low accuracy of diagnosing prostate cancer (PCa) was easily caused by only assaying single prostate specific antigen (PSA) biomarker. Although conventional reported methods for simultaneous detection of two specific PCa biomarkers could improve the diagnostic efficiency and accuracy, low detection sensitivity restrained their use in extreme early-stage PCa clinical assay applications. In order to overcome above drawbacks, this paper herein proposed a multiplexed dual optical microfibers separately functionalized with gold nanorods (GNRs) and Au nanobipyramids (Au NBPs) nanointerfaces with strong localized surface plasmon resonance (LSPR) effects. The sensors could simultaneously detect PSA protein biomarker and long noncoding RNA prostate cancer antigen 3 (lncRNA PCA3) with ultrahigh sensitivity and remarkable specificity. Consequently, the proposed dual optical microfibers multiplexed biosensors could detect the PSA protein and lncRNA PCA3 with ultra-low limit-of-detections (LODs) of 3.97 × 10

Broomfield J., Kalofonou M., Bevan C.L., Georgiou P.

Current diagnostic and prognostic tests for prostate cancer require specialised laboratories and have low specificity for prostate cancer detection. As such, recent advancements in electrochemical devices for point of care (PoC) prostate cancer detection have seen significant interest. Liquid-biopsy detection of relevant circulating and exosomal nucleic acid markers presents the potential for minimally invasive testing. In combination, electrochemical devices and circulating DNA and RNA detection present an innovative approach for novel prostate cancer diagnostics, potentially directly within the clinic. Recent research in electrochemical impedance spectroscopy, voltammetry, chronoamperometry and potentiometric sensing using field-effect transistors will be discussed. Evaluation of the PoC relevance of these techniques and their fulfilment of the WHO’s REASSURED criteria for medical diagnostics is described. Further areas for exploration within electrochemical PoC testing and progression to clinical implementation for prostate cancer are assessed.

Takita S., Nabok A., Mussa M., Kitchen M., Lishchuk A., Smith D.

Prostate cancer (PCa) appears among the most frequently diagnosed types of malignancies in males. Because of the high demand and increasing detection rate of early PCa, alongside the specificity limitations of the gold standard clinical tools available for the diagnosis and prognosis of prostate cancer, there is an urgent need for more reliable PCa markers and highly sensitive diagnostic tools to avoid under-treatment and over-diagnosis. PCA3, or prostate cancer antigen 3, is a potential prostate cancer biomarker that is more specific and useful for preventing unnecessary repeat biopsies, particularly in men with persistently high prostate-specific antigen indices after a negative biopsy. Additionally, an electrochemically based biosensor would prove to be a powerful diagnostic tool for PCA3 detection in urine because of its simplicity, sensitivity, and cost-effectiveness, in contrast to the more traditional PCa diagnostics that depend on blood testing. This paper aimed to design a novel and simple electrochemical impedimetric biosensor based on a label-free RNA-aptamer (CG3-PCA3) as the molecular recognition element for detecting PCA3. The proposed aptasensor for the detection of PCA3 has been developed using a screen-printed carbon electrode (SPCE) modified by gold nanoparticles (AuNPs), further improving sensitivity and allowing the immobilisation of thiolate aptamers on its surface. The findings presented here demonstrated a high sensitivity to PCA3, with a detection limit of 20 fM in artificial urine and 1 fM in buffer. These results indicate that the PCA3 aptasensor could be a promising tool for routine PCa diagnosis due to its high sensitivity and cost-effectiveness.

de Souza F.G., Santos J.F., Silva-Calpa L.D., Pal K.

Background: Nanotechnology is a cornerstone of the scientific advances witnessed over the past few years. Nanotechnology applications are extensively broad, and an overview of the main trends worldwide can give an insight into the most researched areas and gaps to be covered. Objective: This document presents an overview of the trend topics of the three leading countries studying in this area, as well as Brazil for comparison. Method: The data mining was made from the Scopus database and analyzed using the VOSviewer and Voyant Tools software. Results: More than 44.000 indexed articles published from 2010 to 2020 revealed that the countries responsible for the highest number of published articles are The United States, China, and India, while Brazil is in the fifteenth position. Thematic global networks revealed that the standing-out research topics are health science, energy, wastewater treatment, and electronics. In a temporal observation, the primary topics of research are: India (2020), which was devoted to facing SARS-COV 2; Brazil (2019), which is developing promising strategies to combat cancer; China (2018), whit research on nanomedicine and triboelectric nanogenerators; the United States (2017) and the Global tendencies (2018) are also related to the development of triboelectric nanogenerators. The collected data are available on GitHub. Conclusions: This study demonstrates the innovative use of data-mining technologies to gain a comprehensive understanding of nanotechnology's contributions and trends and highlights the diverse priorities of nations in this cutting-edge field.

Mokni M., Tlili A., Khalij Y., Attia G., Zerrouki C., Hmida W., Othmane A., Bouslama A., Omezzine A., Fourati N.

This study investigates the feasibility of a simple electrochemical detection of Prostate Cancer Antigen 3 (PCA3) fragments extracted from patients’ urine, using a thiolated single-strand DNA probe immobilized on a gold surface without using a redox probe. To enhance the PCA3 recognition process, we conducted a comparative analysis of the hybridization location using two thiolated DNA probes: Probe 1 targets the first 40 bases, while Probe 2 targets the fragment from bases 47 to 86. Hybridization with PCA3 followed, using square wave voltammetry. The limit of detection of the designed genosenors were of the order of (2.2 ng/mL), and (1.6 ng/mL) for Probes 1 and 2, respectively, and the subsequent sensitivities were of the order of (0.09 ± 0.01) µA−1 · µg−1 · mL and (0.10 ± 0.01) µA−1 · µg−1 · mL. Specificity tests were then conducted with the sensor functionalized with Probe 2, as it presents better analytical performances. The electrochemical results indicate that the designed sensor can clearly discriminate a complementary target from a non-complementary one. A further modeling of the calibration curves with the Power Law/Hill model indicates that the dissociation constant increases by one order of magnitude, confirming the ability of the designed sensor to perfectly discriminate complementary targets from non-complementary ones.

Fu L., Karimi-Maleh H.

Electrochemical biosensors have emerged as a promising technology for cancer detection due to their high sensitivity, rapid response, low cost, and capability for non-invasive detection. Recent advances in nanomaterials like nanoparticles, graphene, and nanowires have enhanced sensor performance to allow for cancer biomarker detection, like circulating tumor cells, nucleic acids, proteins and metabolites, at ultra-low concentrations. However, several challenges need to be addressed before electrochemical biosensors can be clinically implemented. These include improving sensor selectivity in complex biological media, device miniaturization for implantable applications, integration with data analytics, handling biomarker variability, and navigating regulatory approval. This editorial critically examines the prospects of electrochemical biosensors for efficient, low-cost and minimally invasive cancer screening. We discuss recent developments in nanotechnology, microfabrication, electronics integration, multiplexing, and machine learning that can help realize the potential of these sensors. However, significant interdisciplinary efforts among researchers, clinicians, regulators and the healthcare industry are still needed to tackle limitations in selectivity, size constraints, data interpretation, biomarker validation, toxicity and commercial translation. With committed resources and pragmatic strategies, electrochemical biosensors could enable routine early cancer detection and dramatically reduce the global cancer burden.

Varlamova E.V., Butakova M.A., Semyonova V.V., Soldatov S.A., Poltavskiy A.V., Kit O.I., Soldatov A.V.

The role of machine learning (a part of artificial intelligence—AI) in the diagnosis and treatment of various types of oncology is steadily increasing. It is expected that the use of AI in oncology will speed up both diagnostic and treatment planning processes. This review describes recent applications of machine learning in oncology, including medical image analysis, treatment planning, patient survival prognosis, and the synthesis of drugs at the point of care. The fast and reliable analysis of medical images is of great importance in the case of fast-flowing forms of cancer. The introduction of ML for the analysis of constantly growing volumes of big data makes it possible to improve the quality of prescribed treatment and patient care. Thus, ML is expected to become an essential technology for medical specialists. The ML model has already improved prognostic prediction for patients compared to traditional staging algorithms. The direct synthesis of the necessary medical substances (small molecule mixtures) at the point of care could also seriously benefit from the application of ML. We further review the main trends in the use of artificial intelligence-based technologies in modern oncology. This review demonstrates the future prospects of using ML tools to make progress in cancer research, as well as in other areas of medicine. Despite growing interest in the use of modern computer technologies in medical practice, a number of unresolved ethical and legal problems remain. In this review, we also discuss the most relevant issues among them.

Morozov A.O., Bazarkin A.K., Vovdenko S.V., Taratkin M.S., Balashova M.S., Enikeev D.V.

Introduction. Many molecular genetic analyses have been proposed to predict the course of prostate cancer (PCa). They have the potential to develop artificial intelligence (AI) algorithms by processing large amounts of data and define connections between them.Objective. To evaluate the possibilities of using artificial intelligence in early diagnosis and prognosis of prostate cancer.Materials & methods. We conducted a systematic review of the literature on the Medline citation database. We have selected papers that provide data on the use of AI in vitro, in vivo and in silico systems to determine biological and genetic markers and/or their relationship to clinical data of PCa-patients from 2020 to 2023. The quantitative synthesis includes 16 articles.Results. AI can identify metabolic and genetic «signature» of PCa, the key elements of signal pathways, thus fulfilling complex tasks in the field of bioinformatics. AI analyses various biomaterials: prostate tissue, blood, and urine. When evaluating prostate tissue for aberrations, AI can help a pathologist. For example, AI can predict the histological status of genes, eliminating the need for IHC or tissue sequencing, significantly reducing the economic cost of predicting the severity of the disease. In most cases, prostate tissue sequencing provides information to the attending physician, allowing the start of optimal treatment, considering the molecular or genetic «signature» of PCa. AI can be used as an alternative to existing population screening tools and a predictive castration-resistant PCa. The use of AI capabilities is more appropriate for blood and urine analysis, procedures that do not require additional economic costs for biomaterial sampling. In theory, this may be more affordable for the patient and the medical institution. It is worth noting that a few studies were conducted in silico (based on the analysis of molecular genetic databases without validation on cell lines or on real patients) and are useful as background information. However, the results can serve as a robust basis for further research in molecular diagnostics and genomics.Conclusion. It is possible to use AI in the search for key metabolites and genes of the elements of signalling pathways, as well as the determination of metastasis potential, because molecular or genetic «signature» of PCa allows the physician to start optimal treatment.