Asia Pacific Journal of Medical Toxicology

Artificial Intelligence Calculation of Median Lethal Dose: A Word of Caution

Document Type : Letter to Editor

Author

Fouad Kasim Mohammad 1, 2

1 Department of Physiology, Biochemistry and Pharmacology, College of Veterinary Medicine, University of Mosul, Mosul, Iraq

2 College of Nursing, The American University of Kurdistan, Duhok, Kurdistan Region, Iraq

https://doi.org/10.22038/apjmt.2025.89072.1517
Abstract
Traditional toxicity studies rely on laboratory animal experimentations to estimate the median lethal dose (LD50) of chemicals such as pesticides and medications. This scientific letter highlights the importance of using artificial intelligence (AI) tools (ChatGPT, Deep Seek and Perplexity) to calculate the LD50 values of diazinon in chicks and cadmium chloride in mice. The data of diazinon and cadmium LD50 experiments in animals were separately presented to each of the three AI tools to estimate LD50 values of both toxicants, which were then compared to those of already published results. By following optimal instructions and providing experimental data, the three AI tools (ChatGPT, Deep Seek and Perplexity) accurately determined the LD50 values of diazinon (6.32 mg/kg, orally) in chicks and cadmium chloride (8.6 mg/kg, intraperitoneally) in mice using the up-and-down method. However, when the AI tools were provided with limited information but the same data, inaccuracies arose in calculating the LD50 values for both diazinon and cadmium. A word of caution is, therefore in place herewith, when AI tools are used for estimation of toxicity output (LD50) that might simulate an in silico approach, even in case of availability of some experimental data, as presented currently in the form of doses used and animal survival and death.

Keywords

Toxicity calculation
LD50
In silico
Subjects
  1. Pillai SK, Kobayashi K, Michael M, Mathai T, Sivakumar B, Sadasivan P. John William Trevan’s concept of median lethal dose (LD50/LC50) – more misused than used. J Pre Clin Clin Res. 2021;15(3):137-41. doi:10.26444/jpccr/139588.
  2. Gad SC. Rodents model for toxicity testing and biomarkers. In: Gupta RC, editor. Biomarkers in toxicology. Academic Press; 2014. p. 7–69. https://doi.org/10.1016/B978-0-12-404630-6.00002-6
  1. Dixon WJ. Efficient analysis of experimental observations. Annu Rev Pharmacol Toxicol. 1980; 20:441-62. doi: 10.1146/annurev.pa.20.040180.002301
  2. Sewell F, Edwards J, Prior H, Robinson S. Opportunities to apply the 3Rs in safety assessment programs. ILAR J. 2016 Dec;57(2):234-45. doi: 10.1093/ilar/ilw024.
  3. Alam F, Mohammed Alnazzawi TS, Mehmood R, Al-Maghthawi A. A review of the applications, benefits, and challenges of generative ai for sustainable toxicology. Curr Res Toxicol. 2025 Apr 21;8:100232. doi: 10.1016/j.crtox.2025.100232.
  4. Mohammad FK, Al-Badrany YM, Al-Jobory MM. Acute toxicity and cholinesterase inhibition in chicks dosed orally with organophosphate insecticides. Arh Hig Rada Toksikol. 2008 Sep;59(3):145-51. doi: 10.2478/10004-1254-59-2008-1873.
  5. Al-Baggou BK, Mohammad FK. Effects of cadmium on the acute toxicity of cholinesterase inhibiting insecticides in mice. Arabian J Sci Res. 2022; 3(2).9. https://doi.org/10.5339/ajsr.2022.9. (in Arabic).
Asia Pacific Journal of Medical Toxicology
Volume 14, Issue 4
Autumn 2025
Pages 178-180

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us