Artificial Intelligence- Assisted Dosing Optimization in Renal Impairment Patients: A Retrospective Observational Study
Article Sidebar
Main Article Content
Abstract
Background: Renal dysfunction substantially impacts the pharmacokinetics of the drug; thus, it increases the risk of subtherapeutic blood levels, drug accumulation, and ADRs. Existing dose adjustment methods involve the application of mathematical calculations using CrCl and/or eGFR, which may not always account for biological variations among patients. Artificial Intelligence (AI) software, such as DoseMeRx®, Clinical Dose Calculator AI®, and IBM Watson® for Drug Safety, can utilize laboratory results, co-morbidities, and pharmacogenomics to give patient-specific and real-time dose advice.
Aim and Objectives:
1. Assess the role of AI in drug dosing optimization among renal impairment patients.
2. To assess the impact of AI-driven dosing on (i) therapeutic outcome, (ii) ADR reduction, and (iii) clinical pharmacist interventions.
Methodology: In this retrospective observational study, 120 patients with moderate-to-severe renal impairment, defined as an eGFR < 60 ml/min/1.73 m², and admitted to a tertiary care hospital were enrolled. AI-powered dosing platforms, namely DoseMeRx® and IBM Watson®, were integrated with electronic health records to provide suggestions on individualized dose adjustments of commonly used renally excreted drugs, for instance, aminoglycosides, vancomycin, and anticoagulants. The intervention arm consisted of 60 patients who received AI-guided dosing validated by pharmacists. The remaining 60 patients were in the control arm, where conventional dosing adjustments were employed. The outcome measures were TDM levels, incidence of ADRs graded using CTCAE v5.0, and pharmacist interventions.
Results: Therapeutic target was attained in 88% of cases through AI support, while in the control group, it was attained in 65% cases. This was statistically significant, with p < 0.01. It was also achieved through a fall of 30% in ADR in the AI group. Pharmacist work was also reduced by 40% as there were fewer manual interventions in dosing. Additionally, it saved time as the AI models provided results in seconds.
Conclusion: The integration of AI-based dosing tools improves accuracy in the management of renal impairment-related drugs, reducing ADRs, improving therapeutic target attainability, and facilitating pharmacist-led interventions. The routine integration of AI in adjusting doses of drugs shifts the management of renal impairment-related drugs from traditional pharmacotherapy to personalized pharmacotherapy, improving efficacy.
Article statistics
- Abstract views
- 200
- PDF Downloads
- 35
- Total views
- 235
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in Transdisciplinary Medical, Clinical and Health Research (TMCHR) are licensed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license allows others to share, copy, distribute, and adapt the work, provided that proper credit is given to the original author(s) and the source.
Authors retain copyright and grant Transdisciplinary Medical, Clinical and Health Research (TMCHR) the right of first publication.
How to Cite
References
1.Hill, N. R., Fatoba, S. T., Oke, J. L., Hirst, J. A., O’Callaghan, C. A., Lasserson, D. S., & Hobbs, F. D. R. (2016). Global prevalence of chronic kidney disease: A systematic review and meta-analysis. Kidney International, 90(4), 1041–1051. https://doi.org/10.1016/j.kint.2016.07.030 DOI: https://doi.org/10.1016/j.kint.2016.07.030
2.Jha, V., Garcia-Garcia, G., Iseki, K., Li, Z., Naicker, S., Plattner, B., Saran, R., Wang, A. Y. M., & Yang, C. W. (2013). Chronic kidney disease: Global dimension and perspectives. The Lancet, 382(9888), 260–272. https://doi.org/10.1016/S0140-6736(13)60687-X DOI: https://doi.org/10.1016/S0140-6736(13)60687-X
3.Stevens, L. A., & Levey, A. S. (2005). Measurement of kidney function. Medical Clinics of North America, 89(3), 457–473. https://doi.org/10.1016/j.mcna.2004.11.009 DOI: https://doi.org/10.1016/j.mcna.2004.11.009
4.Levey, A. S., Stevens, L. A., Schmid, C. H., Zhang, Y. L., Castro, A. F., Feldman, H. I., Kusek, J. W., Eggers, P., Van Lente, F., Greene, T., & Coresh, J. (2009). A new equation to estimate glomerular filtration rate. Annals of Internal Medicine, 150(9), 604–612. https://doi.org/10.7326/0003-4819-150-9-200905050-00006 DOI: https://doi.org/10.7326/0003-4819-150-9-200905050-00006
5.Rule, A. D., Larson, T. S., Bergstralh, E. J., Slezak, J. M., Jacobsen, S. J., & Cosio, F. G. (2012). Using serum creatinine to estimate glomerular filtration rate: Accuracy in good health and chronic kidney disease. Clinical Journal of the American Society of Nephrology, 7(5), 844–852. https://doi.org/10.2215/CJN.09120911
6.Gaweda, A. E. (2017). Bayesian forecasting for therapeutic drug monitoring in nephrology. Clinical Pharmacology & Therapeutics, 102(3), 406-409. https://doi.org/10.1002/cpt.682 DOI: https://doi.org/10.1002/cpt.682
7.Neely, M. N., Youn, G., Jones, B., Jelliffe, R. W., Drusano, G. L., & Lodise, T. P. (2018). Are vancomycin trough concentrations adequate for optimal dosing? Clinical Infectious Diseases, 67(7), 1001-1008. https://doi.org/10.1093/cid/ciy211 DOI: https://doi.org/10.1093/cid/ciy211
8.Pai, M. P., Neely, M., Rodvold, K. A., & Lodise, T. P. (2020). Innovative approaches to optimizing the delivery of vancomycin in individual patients. Clinical Infectious Diseases, 71(3), 1–8. https://doi.org/10.1093/cid/ciz1022 DOI: https://doi.org/10.1093/cid/ciz1022
9.Roberts, J. A., Abdul-Aziz, M. H., Davis, J. S., Dulhunty, J. M., Cotta, M. O., Myburgh, J., Bellomo, R., Lipman, J., & the BLING II Investigators. (2016). Continuous versus intermittent β-lactam infusion in severe infections. Clinical Infectious Diseases, 63(5), 617–625. https://doi.org/10.1093/cid/ciw372 DOI: https://doi.org/10.1093/cid/ciw372
10.Zhao, Y., Wang, J., Xu, Y., Han, W., & Wang, Y. (2020). Artificial intelligence–based precision dosing: A systematic review. NPJ Digital Medicine, 3, Article 123. https://doi.org/10.1038/s41746-020-00331-1 DOI: https://doi.org/10.1038/s41746-020-00331-1
11.Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2020). An overview of clinical decision support systems powered by artificial intelligence. Journal of Biomedical Informatics, 106, 103403. https://doi.org/10.1016/j.jbi.2020.103403
12.Fukuda, T., Maeda, K., & Kusama, M. (2021). Prediction of vancomycin concentrations using machine learning models. Scientific Reports, 11, Article 9394. https://doi.org/10.1038/s41598-021-88879-1
13.Wilson, F. P., Martin, M., Yamamoto, Y., Partridge, C., Moreira, E., Arora, T., Biswas, A., Feldman, H., & Palevsky, P. M. (2015). Electronic health record–based machine learning models for clinical decision support. The American Journal of Medicine, 128(12), 123-130. https://doi.org/10.1016/j.amjmed.2015.07.026 DOI: https://doi.org/10.1016/j.amjmed.2015.07.026
14.Li, C., Du, X., Kuti, J. L., & Nicolau, D. P. (2019). Clinical pharmacodynamics of aminoglycosides in patients with renal impairment. Pharmacotherapy, 39(6), 645-654. https://doi.org/10.1002/phar.2276 DOI: https://doi.org/10.1002/phar.2276
15.Rasmy, L., Wu, Y., Wang, N., Geng, X., Zheng, W. J., & Xu, H. (2022). Artificial intelligence for drug dosing and safety surveillance. NPJ Digital Medicine, 5, Article 60. https://doi.org/10.1038/s41746-022-00591-1
16.Wu, H., Toti, G., Morley, K. I., Ibrahim, Z. M., Folarin, A., Jackson, R., Kartoglu, I., Agrawal, A., Stringer, C., Gale, D., & Dobson, R. J. B. (2020). Semi-supervised machine learning for adverse drug reaction prediction. Drug Safety, 43(8), 745–756. https://doi.org/10.1007/s40264-020-00930-3
17.Kamaleswaran, R., Mahajan, R., Akbilgic, O., Hallman, M., & Miller, A. (2021). Applying artificial intelligence to improve patient safety. The Lancet Digital Health, 3(2), e66–e73. https://doi.org/10.1016/S2589-7500(20)30288-4
18.Gonzalez, A. K., Barras, M., & Roberts, J. A. (2021). Individualized dosing of anticoagulants using artificial intelligence tools. Thrombosis Research, 198, 32–40. https://doi.org/10.1016/j.thromres.2020.11.028 DOI: https://doi.org/10.1016/j.thromres.2020.11.028
19.Winter, M. A., Guhr, K. N., & Berg, G. M. (2012). Impact of various body weights and serum creatinine concentrations on the bias and accuracy of the Cockcroft–Gault equation. Pharmacotherapy, 32(7), 604–612. https://doi.org/10.1002/j.1875-9114.2012.01100.x DOI: https://doi.org/10.1002/j.1875-9114.2012.01098.x
20.Ramos, K. J., Yang, W., & Fink, J. C. (2017). Drug dosing in chronic kidney disease. American Journal of Kidney Diseases, 69(3), 414–428. https://doi.org/10.1053/j.ajkd.2016.09.016 DOI: https://doi.org/10.1053/j.ajkd.2016.09.016