Artificial intelligence as a potential tool for oxidative stress estimation in medicine

Abstract

Aim: Oxidative stress (OS) remains an intensively studied scientific problem. The quantitative measurement of OS is an unsolved task, largely due to the existence of numerous complex, non-linear interactions of its components, which can not be measured by traditional statistical methods. Modern mathematical processing based on artificial intelligence (AI) could be a promising method of OS assessment in medicine. The aim of the study was to investigate the potential possibilities of using multilayer neural networks to improve the diagnostic informativeness of the OS indicator-antioxidant (AO) activity (AOA) in patients with cardiovascular diseases (CVDs).

Methods: A cross-sectional study of a sample of 856 people, healthy volunteers and several groups of patients with CVDs (hypertension, including those complicated by coronary heart disease and/or cerebral ischemia, chronic cerebral ischemia), was carried out. The potentiometric method of determining the OS indicator, index of blood serum AOA, was used in comparison with a number of laboratory tests and clinical data. After the results of linear statistical evaluations were not satisfactory enough, а multilayer perceptron classifier was constructed for data analysis.

Results: By training a neural network, it was possible to assign a patient to one of the above-mentioned groups with 85% accuracy on the basis of 8 parameters selected from all the patients’ clinical and laboratory data, including the AOA value.

Conclusions: The use of multilayer neural networks can improve the diagnostic value of information obtained during the measurement of AOA index, in combination with simple laboratory tests in patients with CVDs. The application of AI algorithms is a promising tool to improve the laboratory measurement of OS and a potential solution to overcome the contradictions in the existing approaches to the evaluation of OS.

Keywords

Oxidative stress / antioxidant activity / artificial intelligence in medicine / machine learning algorithm / neural networks in medicine / potentiometry

References

[1] Singh PP, Chandra A, Mahdi F, Roy A, Sharma P. Reconvene and reconnect the antioxidant hypothesis in human health and disease. Indian J Clin Biochem. 2010; 25:225-43.

[2] Halliwell B, Gutteridge JMC. Free Radicals in Biology and Medicine. 5th ed. Oxford: Oxford Academic; 2015.

[3] Sies H, Berndt C, Jones DP. Oxidative Stress. Annu Rev Biochem. 2017; 86:715-48.

[4] SIES H. 1 - Oxidative Stress: Introductory Remarks. In: SIES H, editor. Oxidative Stress. London: Academic Press; 1985. pp. 1-8.

[5] Jones DP, Sies H. The Redox Code. Antioxid Redox Signal. 2015; 23:734-46.

[6] Dickinson BC, Chang CJ. Chemistry and biology of reactive oxygen species in signaling or stress responses. Nat Chem Biol. 2011; 7:504-11.

[7] Rajendran P, Nandakumar N, Rengarajan T, Palaniswami R, Gnanadhas EN, Lakshminarasaiah U, et al. Antioxidants and human diseases. Clin Chim Acta. 2014; 436:332-47.

[8] Zhang L, Wang K, Lei Y, Li Q, Nice EC, Huang C. Redox signaling: Potential arbitrator of autophagy and apoptosis in therapeutic response. Free Radic Biol Med. 2015; 89:452-65.

[9] Dan Dunn J, Alvarez LA, Zhang X, Soldati T. Reactive oxygen species and mitochondria: A nexus of cellular homeostasis. Redox Biol. 2015; 6:472-85.

[10] Cortese-Krott MM, Koning A, Kuhnle GGC, Nagy P, Bianco CL, Pasch A, et al. The Reactive Species Interactome: Evolutionary Emergence, Biological Significance, and Opportunities for Redox Metabolomics and Personalized Medicine. Antioxid Redox Signal. 2017; 27:684-712.

[11] Santolini J, Wootton SA, Jackson AA, Feelisch M. The Redox architecture of physiological function. Curr Opin Physiol. 2019; 9:34-47.

[12] Georgieva E, Ivanova D, Zhelev Z, Bakalova R, Gulubova M, Aoki I. Mitochondrial Dysfunction and Redox Imbalance as a Diagnostic Marker of “Free Radical Diseases”. Anticancer Res. 2017; 37:5373-81.

[13] Sies H, Jones D. Oxidative Stress*. In: Fink G, editor. Encyclopedia of Stress (Second Edition). New York: Academic Press; 2007. pp. 45-8.

[14] Katerji M, Filippova M, Duerksen-Hughes P. Approaches and Methods to Measure Oxidative Stress in Clinical Samples: Research Applications in the Cancer Field. Oxid Med Cell Longev. 2019; 2019:1279250.

[15] Murphy MP, Bayir H, Belousov V, Chang CJ, Davies KJA, Davies MJ, et al. Guidelines for measuring reactive oxygen species and oxidative damage in cells and in vivo. Nat Metab. 2022; 4:651-62.

[16] Sies H, Jones DP. Reactive oxygen species (ROS) as pleiotropic physiological signalling agents. Nat Rev Mol Cell Biol. 2020; 21:363-83.

[17] Vadgama P. Oxidative Free Radicals and Other Species: Selective Messengers with a Reactive Capacity for Unselective Tissue Damage. Chemosensors. 2021; 9:89.

[18] Dotan Y, Lichtenberg D, Pinchuk I. Lipid peroxidation cannot be used as a universal criterion of oxidative stress. Prog Lipid Res. 2004; 43:200-27.

[19] Frijhoff J, Winyard PG, Zarkovic N, Davies SS, Stocker R, Cheng D, et al. Clinical Relevance of Biomarkers of Oxidative Stress. Antioxid Redox Signal. 2015; 23:1144-70.

[20] Sun Y, Yang C, Tsao R. Nomenclature and general classification of antioxidant activity/capacity assays. In: Apak R, Capanoglu E, Shahidi F, editors. Measurement of Antioxidant Activity & Capacity: Recent Trends and Applications. John Wiley & Sons Ltd; 2018. pp. 1-19.

[21] Munteanu IG, Apetrei C. A Review on Electrochemical Sensors and Biosensors Used in Assessing Antioxidant Activity. Antioxidants (Basel). 2022; 11:584.

[22] Brainina KZ, Alyoshina LV, Gerasimova EL, Kazakov YE, Ivanova AV, Beykin YB, et al. New Electrochemical Method of Determining Blood and Blood Fractions Antioxidant Activity. Electroanalysis. 2009; 21:618-24.

[23] Brainina KZ, Kazakov YE. Electrochemical Hybrid Methods and Sensors for Antioxidant/Oxidant Activity Monitoring and Their Use as a Diagnostic Tool of Oxidative Stress: Future Perspectives and Challenges. Chemosensors. 2020; 8:90.

[24] Kazakov Y, Khodos M, Vidrevich M, Brainina K. Potentiometry as a Tool for Monitoring of Antioxidant Activity and Oxidative Stress Estimation in Medicine. Crit Rev Anal Chem. 2019; 49:150-9.

[25] Kazakov Y, Tarasov A, Alyoshina L, Brainina K. Interplay between antioxidant activity, health and disease. Biointerface Res Appl Chem. 2020; 10:4893-901.

[26] Kazakov Y, Brainina K. Oxidation and Reduction Processes in Vivo and in Vitro: Current Concepts, Monitoring and Perspectives. Newcastle upon Tyne: Cambridge Scholars Publishing; 2024.

[27] Apak R, Güçlü K, Demirata B, Ozyürek M, Celik SE, Bektaşoğlu B, et al. Comparative evaluation of various total antioxidant capacity assays applied to phenolic compounds with the CUPRAC assay. Molecules. 2007; 12:1496-547.

[28] Apak R, Özyürek M, Güçlü K, Çapanoğlu E. Antioxidant Activity/Capacity Measurement. 1. Classification, Physicochemical Principles, Mechanisms, and Electron Transfer (ET)-Based Assays. J Agric Food Chem. 2016; 64:997-1027.

[29] Sies H. Oxidative stress: a concept in redox biology and medicine. Redox Biol. 2015; 4:180-3.

[30] Sies H, Belousov VV, Chandel NS, Davies MJ, Jones DP, Mann GE, et al. Defining roles of specific reactive oxygen species (ROS) in cell biology and physiology. Nat Rev Mol Cell Biol. 2022; 23:499-515.

[31] Lichtenberg D, Pinchuk I, Yonassi E, Weber D, Grune T. Oxidative Stress Is a Concept, Not an Indication for Selective Antioxidant Treatment. Antioxidants (Basel). 2023; 12:1188.

[32] Budnikov GK, Ziyatdinova GK. Antioxidants As Analytes in Analytical Chemistry. J Anal Chem. 2005; 60:600-13.

[33] Lichtenberg D, Pinchuk I, Weber D. Oxidative stress, as assayed by a single test, cannot be used as a diagnostic tool. Biofactors. 2018; 44:222-3.

[34] Pinchuk I, Kohen R, Stuetz W, Weber D, Franceschi C, Capri M, et al. Do low molecular weight antioxidants contribute to the Protection against oxidative damage? The interrelation between oxidative stress and low molecular weight antioxidants based on data from the MARK-AGE study. Arch Biochem Biophys. 2021; 713:109061.

[35] Uppu RM, Woods D, Parinandi NL. Measurement of Oxidative Stress Status in Human Populations: A Critical Need for a Metabolomic Profiling. In: Berliner LJ, Parinandi NL, editors. Measuring Oxidants and Oxidative Stress in Biological Systems. Cham: Springer International Publishing; 2020. pp. 123-31.

[36] Hulsen T. Artificial Intelligence in Healthcare: ChatGPT and Beyond. AI. 2024; 5:550-4.

[37] Hulsen T. Literature analysis of artificial intelligence in biomedicine. Ann Transl Med. 2022; 10:1284.

[38] El-Sherbini AH, Hassan Virk HU, Wang Z, Glicksberg BS, Krittanawong C. Machine-Learning-Based Prediction Modelling in Primary Care: State-of-the-Art Review. AI. 2023; 4:437-60.

[39] Huang T, Xu H, Wang H, Huang H, Xu Y, Li B, et al. Artificial intelligence for medicine: progress, challenges, and perspectives. Innovation Med. 2023; 1:100030.

[40] Mishra S. Artificial Intelligence: A Review of Progress and Prospects in Medicine and Healthcare. J Electron Electromedical Eng Med Inform. 2022; 4:1-23.

[41] Krones F, Marikkar U, Parsons G, Szmul A, Mahdi A. Review of multimodal machine learning approaches in healthcare. Inf Fusion. 2025; 114:102690.

[42] Chen W, Liu X, Zhang S, Chen S. Artificial intelligence for drug discovery: Resources, methods, and applications. Mol Ther Nucleic Acids. 2023; 31:691-702.

[43] Blasiak A, Khong J, Kee T. CURATE.AI: Optimizing Personalized Medicine with Artificial Intelligence. SLAS Technol. 2020; 25:95-105.

[44] Ahuja AS. The impact of artificial intelligence in medicine on the future role of the physician. PeerJ. 2019; 7:e7702.

[45] Montagna S, Pengo MF, Ferretti S, Borghi C, Ferri C, Grassi G, et al. Machine Learning in Hypertension Detection: A Study on World Hypertension Day Data. J Med Syst. 2023; 47:1.

[46] Boeken T, Feydy J, Leclen A, Soyer P, Feydy A, Barat M, et al. Artificial intelligence in diagnostic and interventional radiology: Where are we now? Diagn Interv Imaging. 2023; 104:1-5.

[47] Wasilewski T, Kamysz W, Gębicki J. AI-Assisted Detection of Biomarkers by Sensors and Biosensors for Early Diagnosis and Monitoring. Biosensors (Basel). 2024; 14:356.

[48] Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS One. 2017; 12:e0174944.

[49] Alaa AM, Bolton T, Di Angelantonio E, Rudd JHF, van der Schaar M. Cardiovascular disease risk prediction using automated machine learning: A prospective study of 423,604 UK Biobank participants. PLoS One. 2019; 14:e0213653.

[50] Iqbal MJ, Javed Z, Sadia H, Qureshi IA, Irshad A, Ahmed R, et al. Clinical applications of artificial intelligence and machine learning in cancer diagnosis: looking into the future. Cancer Cell Int. 2021; 21:270.

[51] Gould MK, Huang BZ, Tammemagi MC, Kinar Y, Shiff R. Machine Learning for Early Lung Cancer Identification Using Routine Clinical and Laboratory Data. Am J Respir Crit Care Med. 2021; 204:445-53.

[52] Gadalla AAH, Friberg IM, Kift-Morgan A, Zhang J, Eberl M, Topley N, et al. Identification of clinical and urine biomarkers for uncomplicated urinary tract infection using machine learning algorithms. Sci Rep. 2019; 9:19694.

[53] Mann M, Kumar C, Zeng WF, Strauss MT. Artificial intelligence for proteomics and biomarker discovery. Cell Syst. 2021; 12:759-70.

[54] Kyriazakos S, Pnevmatikakis A, Cesario A, Kostopoulou K, Boldrini L, Valentini V, et al. Discovering Composite Lifestyle Biomarkers With Artificial Intelligence From Clinical Studies to Enable Smart eHealth and Digital Therapeutic Services. Front Digit Health. 2021; 3:648190.

[55] Haykin S. Neural Networks and Learning Machines. 3rd ed. Prentice Hall; 2009.

[56] Osowski S. Sieci neuronowe do przetwarzania informacji. Oficyna Wydawnicza Politechniki Warszawska; 2020.

[57] Gao R, Bao S. Advances in the Application of Nano-Enzymes in the Electrochemical Detection of Reactive Oxygen Species: A Review. Chemosensors. 2023; 11:440.

[58] Saputra HA. Electrochemical sensors: basic principles, engineering, and state of the art. Monatsh Chem. 2023; 154:1083-100.

[59] Shen Y, Liu C, He H, Zhang M, Wang H, Ji K, et al. Recent Advances in Wearable Biosensors for Non-Invasive Detection of Human Lactate. Biosensors (Basel). 2022; 12:1164.

[60] Hatherley J, Sparrow R, Howard M. The Virtues of Interpretable Medical Artificial Intelligence. Camb Q Healthc Ethics. 2022;[Epub ahead of print].

[61] Cerrato PL, Halamka JD. How AI drives innovation in cardiovascular medicine. Front Cardiovasc Med. 2024; 11:1397921.