Machine learning models to predict the warfarin discharge dosage using clinical information of inpatients from South Korea.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
18 Dec 2023
18 Dec 2023
Historique:
received:
16
06
2023
accepted:
12
12
2023
medline:
18
12
2023
pubmed:
18
12
2023
entrez:
17
12
2023
Statut:
epublish
Résumé
As warfarin has a narrow therapeutic window and obvious response variability among individuals, it is difficult to rapidly determine personalized warfarin dosage. Adverse drug events(ADE) resulting from warfarin overdose can be critical, so that typically physicians adjust the warfarin dosage through the INR monitoring twice a week when starting warfarin. Our study aimed to develop machine learning (ML) models that predicts the discharge dosage of warfarin as the initial warfarin dosage using clinical data derived from electronic medical records within 2 days of hospitalization. During this retrospective study, adult patients who were prescribed warfarin at Asan Medical Center (AMC) between January 1, 2018, and October 31, 2020, were recruited as a model development cohort (n = 3168). Additionally, we created an external validation dataset (n = 891) from a Medical Information Mart for Intensive Care III (MIMIC-III). Variables for a model prediction were selected based on the clinical rationale that turned out to be associated with warfarin dosage, such as bleeding. The discharge dosage of warfarin was used the study outcome, because we assumed that patients achieved target INR at discharge. In this study, four ML models that predicted the warfarin discharge dosage were developed. We evaluated the model performance using the mean absolute error (MAE) and prediction accuracy. Finally, we compared the accuracy of the predictions of our models and the predictions of physicians for 40 data point to verify a clinical relevance of the models. The MAEs obtained using the internal validation set were as follows: XGBoost, 0.9; artificial neural network, 0.9; random forest, 1.0; linear regression, 1.0; and physicians, 1.3. As a result, our models had better prediction accuracy than the physicians, who have difficulty determining the warfarin discharge dosage using clinical information obtained within 2 days of hospitalization. We not only conducted the internal validation but also external validation. In conclusion, our ML model could help physicians predict the warfarin discharge dosage as the initial warfarin dosage from Korean population. However, conducting a successfully external validation in a further work is required for the application of the models.
Identifiants
pubmed: 38105280
doi: 10.1038/s41598-023-49831-6
pii: 10.1038/s41598-023-49831-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
22461Informations de copyright
© 2023. The Author(s).
Références
Pirmohamed, M. Warfarin: Almost 60 years old and still causing problems. Br. J. Clin. Pharmacol. 62, 509 (2006).
doi: 10.1111/j.1365-2125.2006.02806.x
pubmed: 17061959
pmcid: 1885167
Pirmohamed, M., Kamali, F., Daly, A. K. & Wadelius, M. Oral anticoagulation: A critique of recent advances and controversies. Trends Pharmacol. Sci. 36, 153–163 (2015).
doi: 10.1016/j.tips.2015.01.003
pubmed: 25698605
Glurich, I., Burmester, J. K. & Caldwell, M. D. Understanding the pharmacogenetic approach to warfarin dosing. Heart Fail. Rev. 15, 239–248 (2010).
doi: 10.1007/s10741-008-9115-9
pubmed: 18998206
Gage, B. F., Fihn, S. D. & White, R. H. Management and dosing of warfarin therapy. Am. J. Med. 109, 481–488 (2000).
doi: 10.1016/S0002-9343(00)00545-3
pubmed: 11042238
Gage, B. et al. Use of pharmacogenetic and clinical factors to predict the therapeutic dose of warfarin. Clin. Pharmacol. Ther. 84, 326–331 (2008).
doi: 10.1038/clpt.2008.10
pubmed: 18305455
Pavani, A. et al. Artificial neural network-based pharmacogenomic algorithm for warfarin dose optimization. Pharmacogenomics 17, 121–131 (2016).
doi: 10.2217/pgs.15.161
pubmed: 26666467
Roche-Lima, A. et al. Machine learning algorithm for predicting warfarin dose in caribbean hispanics using pharmacogenetic data. Front. Pharmacol. 10, 1550 (2020).
doi: 10.3389/fphar.2019.01550
pubmed: 32038238
pmcid: 6987072
Tong, H. Y. et al. A new pharmacogenetic algorithm to predict the most appropriate dosage of acenocoumarol for stable anticoagulation in a mixed spanish population. PLoS ONE 11, e0150456 (2016).
doi: 10.1371/journal.pone.0150456
pubmed: 26977927
pmcid: 4792430
Grossi, E. et al. Prediction of optimal warfarin maintenance dose using advanced artificial neural networks. Pharmacogenomics 15, 29–37 (2014).
doi: 10.2217/pgs.13.212
pubmed: 24329188
Saleh, M. I. & Alzubiedi, S. Dosage individualization of warfarin using artificial neural networks. Mol. Diagn. Ther. 18, 371–379 (2014).
doi: 10.1007/s40291-014-0090-7
pubmed: 24574079
Hernandez, W. et al. Ethnicity-specific pharmacogenetics: The case of warfarin in African Americans. Pharmacogenom. J. 14, 223–228 (2014).
doi: 10.1038/tpj.2013.34
Alzubiedi, S. & Saleh, M. I. Pharmacogenetic-guided warfarin dosing algorithm in African–Americans. J. Cardiovasc. Pharmacol. 67, 86–92 (2016).
doi: 10.1097/FJC.0000000000000317
pubmed: 26355760
Martes-Martinez, C. et al. Cost-utility study of warfarin genotyping in the Vachs affiliated anticoagulation clinic of Puerto Rico. P. R. Health Sci. J. 36, 165–172 (2017).
pubmed: 28915306
pmcid: 5993426
Hu, Y.-H., Wu, F., Lo, C.-L. & Tai, C.-T. Predicting warfarin dosage from clinical data: A supervised learning approach. Artif. Intell. Med. 56, 27–34 (2012).
doi: 10.1016/j.artmed.2012.04.001
pubmed: 22537823
Johnson, A. et al. Mimic-iii, a freely accessible critical care database sci. Data 3, 10–1038 (2016).
Willmott, C. J. & Matsuura, K. Advantages of the mean absolute error (mae) over the root mean square error (rmse) in assessing average model performance. Clim. Res. 30, 79–82 (2005).
doi: 10.3354/cr030079
Koo, T. K. & Li, M. Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropr. Med. 15, 155–163 (2016).
doi: 10.1016/j.jcm.2016.02.012
pubmed: 27330520
pmcid: 4913118
Shin, S.-Y. et al. Lessons learned from development of de-identification system for biomedical research in a Korean tertiary hospital. Healthc. Inf. Res. 19, 102–109 (2013).
doi: 10.4258/hir.2013.19.2.102
McDonald, M., Au, N., Wittkowsky, A. & Rettie, A. Warfarin-amiodarone drug-drug interactions: determination of [i] u/ki, u for amiodarone and its plasma metabolites. Clin. Pharmacol. Ther. 91, 709–717 (2012).
doi: 10.1038/clpt.2011.283
pubmed: 22398967
Nutescu, E., Chuatrisorn, I. & Hellenbart, E. Drug and dietary interactions of warfarin and novel oral anticoagulants: An update. J. Thromb. Thrombolysis 31, 326–343 (2011).
doi: 10.1007/s11239-011-0561-1
pubmed: 21359645
Greenblatt, D. J. & von Moltke, L. L. Interaction of warfarin with drugs, natural substances, and foods. J. Clin. Pharmacol. 45, 127–132 (2005).
doi: 10.1177/0091270004271404
pubmed: 15647404
Kean, M., Krueger, K., Parkhurst, B., Berg, R. & Griesbach, S. Assessment of potential drug interactions that may increase the risk of major bleeding events in patients on warfarin maintenance therapy. J. Pharm. Soc. Wis. 21, 44–8 (2018).
Limdi, N. A. et al. Warfarin dosing in patients with impaired kidney function. Am. J. Kidney Dis. 56, 823–831 (2010).
doi: 10.1053/j.ajkd.2010.05.023
pubmed: 20709439
pmcid: 2963672
Gulløv, A. L., Koefoed, B. G. & Petersen, P. Bleeding during warfarin and aspirin therapy in patients with atrial fibrillation: The afasak 2 study. Arch. Intern. Med. 159, 1322–1328 (1999).
doi: 10.1001/archinte.159.12.1322
pubmed: 10386508
Dumo, P. A. & Kielbasa, L. A. Successful anticoagulation and continuation of tramadol therapy in the setting of a tramadol-warfarin interaction. Pharmacother. J. Hum. Pharmacol. Drug Ther. 26, 1654–1657 (2006).
Daly, A. K. Pharmacogenomics of anticoagulants: Steps toward personal dosage. Genome Med. 1, 1–4 (2009).
doi: 10.1186/gm10
Venables, W. N., Ripley, B. D., Venables, W. & Ripley, B. Tree-based methods. Mod. Appl. Stat. S-Plus 303–327 (1999).
Patro, S. & Sahu, K. K. Normalization: A preprocessing stage. arXiv preprint arXiv:1503.06462 (2015).
Jain, A. K., Mao, J. & Mohiuddin, K. M. Artificial neural networks: A tutorial. Computer 29, 31–44 (1996).
doi: 10.1109/2.485891
Yan, X. & Su, X. Linear regression analysis: theory and computing (world scientific, 2009).
Chen, T. & Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785–794 (2016).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
doi: 10.1023/A:1010933404324
LaValle, S. M., Branicky, M. S. & Lindemann, S. R. On the relationship between classical grid search and probabilistic roadmaps. Int. J. Robot. Res. 23, 673–692 (2004).
doi: 10.1177/0278364904045481
James, G., Witten, D., Hastie, T. & Tibshirani, R. An introduction to statistical learning, vol. 112 (Springer, 2013).
Peng, C.-Y.J., Lee, K. L. & Ingersoll, G. M. An introduction to logistic regression analysis and reporting. J. Educ. Res. 96, 3–14 (2002).
doi: 10.1080/00220670209598786
Lundberg, S. M., Erion, G. G. & Lee, S.-I. Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018).
Arrieta, A. B. et al. Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai. Inf. Fusion 58, 82–115 (2020).
doi: 10.1016/j.inffus.2019.12.012
Shrout, P. E. & Fleiss, J. L. Intraclass correlations: uses in assessing rater reliability. Psychol. Bull. 86, 420 (1979).
doi: 10.1037/0033-2909.86.2.420
pubmed: 18839484
Ravvaz, K., Weissert, J. A., Ruff, C. T., Chi, C.-L. & Tonellato, P. J. Personalized anticoagulation: Optimizing warfarin management using genetics and simulated clinical trials. Circ. Cardiovasc. Genet. 10, e001804 (2017).
Li, X. et al. Precision dosing of warfarin: Open questions and strategies. Pharmacogenom. J. 19, 219–229 (2019).
doi: 10.1038/s41397-019-0083-3
Bussey, H. I., Wittkowsky, A. K., Hylek, E. M. & Walker, M. B. Genetic testing for warfarin dosing? Not yet ready for prime time (2008).
Kuruvilla, M. & Gurk-Turner, C. A review of warfarin dosing and monitoring. Baylor Univ. Med. Center Proc. 14, 305–306 (2001).
doi: 10.1080/08998280.2001.11927781