STM Journals Peer-reviewed research from Consortium e-Learning Network

Research and Reviews: A Journal of Toxicology Original Research

Toxicology 4.0: Integrating Artificial Intelligence, Big Data, Health Informatics, and Precision Analytics for Predictive Toxicity Assessment, Real-Time Toxicovigilance, and Personalized Patient Safety

  1. Muchukota Sushma Department of Pharmacy Practice, Aditya Bangalore Institute of Pharmacy Education and Research, Bengaluru
  2. Gouthami Putlur Department of Pharmacy Practice, Balaji College of Pharmacy, Anantapur
  3. Anusha Reddy Konannagari Department of Pharmacy Practice, Balaji College of Pharmacy, Anantapur

Abstract

Background: Toxicology is undergoing a major transformation, increasingly described as Toxicology 4.0, driven by the integration of artificial intelligence (AI), big data analytics, health informatics, and precision analytics. Conventional toxicity testing is limited by high costs, lengthy timelines, and challenges in translating animal and low-throughput in vitro findings to humans. Aim and Objectives: To comprehensively evaluate the emerging role of Toxicology 4.0 in predictive toxicity assessment, real-time toxicovigilance, and personalized patient safety, with particular emphasis on AI-enabled computational toxicology, QSAR modelling, New Approach Methodologies (NAMs), AI- and NLP-based safety signal detection, and machine-learning-based pharmacokinetic and toxicogenomic approaches for individualized risk assessment and dosing. Methodology: A narrative review was undertaken by synthesizing current scientific evidence on AI, computational toxicology, big data, health informatics, toxicovigilance, NAMs, pharmacokinetic modelling, and toxicogenomics. The reviewed approaches were considered across three interconnected domains: predictive toxicity assessment, real-time toxicovigilance, and personalized patient safety. Results: AI-driven approaches have demonstrated potential to improve the prediction of hepatotoxicity, cardiotoxicity, and systemic toxicity, while computational models and NAMs can accelerate toxicity screening. AI and NLP-based systems facilitate scalable detection of adverse-event signals from electronic health records and spontaneous reporting systems. Machine-learning-augmented pharmacokinetic modelling and toxicogenomic risk stratification further support individualized dosing and safety assessment. However, implementation remains challenged by data heterogeneity, limited explainability, insufficient external validation, and evolving regulatory requirements. Conclusion: Toxicology 4.0 represents a promising shift toward data-driven, predictive, real-time, and personalized safety assessment. Its successful translation into clinical and regulatory practice will require standardized data infrastructure, robust and explainable AI models, rigorous validation, and multidisciplinary collaboration among toxicologists, clinicians, data scientists, and regulatory authorities.

Keywords

References (30)

  1. Zhang J, Li H, Zhang Y, Huang J, Ren L, Zhang C, Zou Q, Zhang Y. Computational toxicology in drug discovery: applications of artificial intelligence in ADMET and toxicity prediction. Brief Bioinform. 2025;26(5): bbaf533. doi:10.1093/bib/bbaf533
  2. Teunis M, Luechtefeld T, Hartung T. Editorial: leveraging artificial intelligence and open science for toxicological risk assessment. Front Toxicol. 2025; 7:1568453. doi:10.3389/ftox.2025.1568453
  3. Bai R, et al. Machine learning-enabled drug-induced toxicity prediction. Adv Sci (Weinh). 2025. doi:10.1002/advs.202413405
  4. Sheng QS, Liu B, Wang X, Hua L, Zhao SC, Sun XZ, Li MY, Zhang XY, Wang JX, Hu PL. Revolutionizing toxicological risk assessment: integrative advances in new approach methodologies (NAMs) and precision toxicology. Arch Toxicol. 2025; 99:4697-4707. doi:10.1007/s00204-025-04169-y
  5. Kleinstreuer N, Hartung T. Artificial intelligence (AI) - it's the end of the tox as we know it (and I feel fine). Arch Toxicol. 2024;98(3):735-754. doi:10.1007/s00204-023-03666-2
  6. Deepika D, Kanchan B, Sharma S, Kumar S, Pathak RK, Biosca Brull J, Sabuz O, Garcia Vilana S, Kumar V. Advancing human health risk assessment: the role of new approach methodologies. Front Toxicol. 2025;7 :1632941. doi:10.3389/ftox.2025.1632941
  7. Chou WC, Lin Z. Machine learning and artificial intelligence in physiologically based pharmacokinetic modelling. Toxicol Sci. 2023;191(1):1-14. doi:10.1093/toxsci/kfac101
  8. Warner J, Prada Jardim A, Albera C, et al. Artificial intelligence: applications in pharmacovigilance signal management. Pharmaceut Med. 2025;39(3):183-198. doi:10.1007/s40290-025-00561-2
  9. Algarvio RC, Conceicao J, Rodrigues PP, Ribeiro I, Ferreira-da-Silva R. Artificial intelligence in pharmacovigilance: a narrative review and practical experience with an expert-defined Bayesian network tool. Int J Clin Pharm. 2025;47(4):932-944. doi:10.1007/s11096-025-01975-3
  10. Ball R, Dal Pan G. "Artificial intelligence" for pharmacovigilance: ready for prime time? Drug Saf. 2022;45(5):429-438. doi:10.1007/s40264-022-01157-4
  11. Schmider J, Kumar K, LaForest C, Swankoski B, Naim K, Caubel PM. Innovation in pharmacovigilance: use of artificial intelligence in adverse event case processing. Clin Pharmacol Ther. 2019;105(4):954-961. doi:10.1002/cpt.1255
  12. Martin GL, et al. Validation of artificial intelligence to support the automatic coding of patient adverse drug reaction reports, using nationwide pharmacovigilance data. Drug Saf. 2022. doi:10.1007/s40264-022-01153-8
  13. Wang X, Chen J, Ji C, Wu F, Wu H. Integration of computational toxicology, toxicogenomics data mining, and omics techniques to unveil toxicity pathways. ACS Sustain Chem Eng. 2021;9(11):4130-4138. doi:10.1021/acssuschemeng.0c09196
  14. Kim MT, et al. Comparing machine learning algorithms for predicting drug-induced liver injury (DILI). Mol Pharm. 2020. doi:10.1021/acs.molpharmaceut.0c00326
  15. Li T, et al. DeepDILI: deep learning-powered drug-induced liver injury prediction using model-level representation. Chem Res Toxicol. 2021. doi:10.1021/acs.chemrestox.0c00374
  16. Igarashi Y, Nakatsu N, Yamashita T, Ono A, Ohno Y, Urushidani T, Yamada H. Open TG-GATEs: a large-scale toxicogenomics database. Nucleic Acids Res. 2014;43(D1):D921-D927. doi:10.1093/nar/gku955
  17. Shan G, Li X, Huang W. AI-enabled wearable and flexible electronics for assessing full personal exposures. Innovation (Camb). 2020;1(2):100031. doi:10.1016/j.xinn.2020.100031
  18. Hartung T, et al. AI: the Apollo guidance computer of the exposome moonshot. Front Artif Intell. 2025;8:1632520. doi:10.3389/frai.2025.1632520
  19. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447-453. doi:10.1126/science.aax2342
  20. Mennella C, Maniscalco U, De Pietro G, Esposito M. Ethical and regulatory challenges of AI technologies in healthcare: a narrative review. Heliyon. 2024;10(4):e26297. doi:10.1016/j.heliyon.2024.e26297
  21. Wang Z, Chen J, Hong H. Advancing computational toxicology in the big data era by artificial intelligence: data-driven and mechanism-driven modeling for chemical toxicity. Chem Res Toxicol. 2021;34(2):317-329. doi:10.1021/acs.chemrestox.8b00393
  22. Frueh FW, Huang SM, Lesko LJ. Guest editorial: regulatory acceptance of toxicogenomics data. Environ Health Perspect. 2004;112(14): A804-A805. doi:10.1289/ehp.112-1277121
  23. Zhang F, Li F, Tan J, Zhang N, Han Y, Liao J, Zhai H. Editorial: advances and applications of predictive toxicology in knowledge discovery, risk assessment, and drug development. Front Pharmacol. 2025; 16:1721364. doi:10.3389/fphar.2025.1721364
  24. Shao K, Ji C, Gadagbui B. Editorial: next generation chemical risk assessment: integration of advances in toxicology, biology and computation. Front Toxicol. 2024;6:1440229. doi:10.3389/ftox.2024.1440229
  25. Singh AV, Chandrasekar V, Paudel N, Laux P, Luch A, Gemmati D, Tisato V, Prabhu KS, Uddin S, Dakua SP. Integrative toxicogenomics: advancing precision medicine and toxicology through artificial intelligence and OMICs technology. Biomed Pharmacother. 2023;163:114784. doi:10.1016/j.biopha.2023.114784
  26. Luechtefeld T, Rowlands C, Hartung T. Big-data and machine learning to revamp computational toxicology and its use in risk assessment. Toxicol Res (Camb). 2018;7(5):732-744. doi:10.1039/C8TX00051D.
  27. Li S, Lu X, Li Y, et al. Advancing computational toxicology in the big data era by artificial intelligence: data-driven and mechanism-driven modeling for chemical toxicity. Chem Res Toxicol. 2019;32(4):536-547. doi:10.1021/acs.chemrestox.8b00393.
  28. Hartung T. Artificial intelligence as the new frontier in chemical risk assessment. Front Artif Intell. 2023;6:1269932. doi:10.3389/frai.2023.1269932.
  29. Hartung T. Predicting toxicity of chemicals: software beats animal testing. EFSA J. 2019;17(7):e170710. doi:10.2903/j.efsa.2019.e170710.
  30. Teunis M, Luechtefeld T, Hartung T. Editorial: Leveraging artificial intelligence and open science for toxicological risk assessment. Front Toxicol. 2025;7:1568453. doi:10.3389/ftox.2025.1568453.
Support