Artificial Intelligence in Personalized Pharmacotherapy: Integrating Patient Data, Predictive Analytics, and Clinical Decision Support

Certificate: View Certificate

Published Paper PDF: View PDF

Confirmation Letter: View

Dr. Priyanka Sisodia

Prof and DSW

S.D. College of Science,

Atrauli, Aligarh 202280

Orcid id : https://orcid.org/0009-0000-2978-8725

Abstract— Personalized pharmacotherapy seeks to match the right drug and dose to the individual patient, yet clinicians still rely heavily on population-average dosing that ignores genetic, clinical and contextual variability. This study developed and evaluated an integrated artificial intelligence (AI) framework combining pharmacogenomic, laboratory and electronic health record (EHR) data to support three tasks: individualized warfarin dose prediction, adverse drug event (ADE) risk stratification, and clinically prioritized decision-support alerting. Using a retrospective cohort of 8,420 patients and a nine-month prospective deployment across two hospital units, the ensemble dosing model placed 61.4% of predictions within 20% of the stable therapeutic dose versus 47.9% for a linear pharmacogenetic baseline (p < .001). The ADE model reached an AUROC of 0.88, and the prioritized alert layer cut clinically irrelevant alerts by 58.7% while raising alert acceptance from 41.2% to 67.8%. Preventable ADEs fell from 5.9 to 3.4 per 1,000 patient-days. The results indicate that data integration, not any single algorithm, drives the clinical benefit of AI-assisted pharmacotherapy.

Keywords— personalized pharmacotherapy; machine learning; pharmacogenomics; clinical decision support; adverse drug events; predictive analytics

References

1. Ma Z, Wang P, Gao Z, Wang R, Khalighi K. Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose. PLOS ONE. 2018;13(10):e0205872. doi:10.1371/journal.pone.0205872
2. Sharabiani A, Bress A, Douzali E, Darabi H. Revisiting warfarin dosing using machine learning techniques. Computational and Mathematical Methods in Medicine. 2015;2015:560108. doi:10.1155/2015/560108
3. Liu Y, Yella J, Chen J, et al. Machine learning for prediction of stable warfarin dose in US Latinos and Latin Americans. Frontiers in Pharmacology. 2021;12:749786. doi:10.3389/fphar.2021.749786
4. Roche-Lima A, Roman-Santiago A, Feliu-Maldonado R, et al. Machine learning algorithm for predicting warfarin dose in Caribbean Hispanics using pharmacogenetic data. Frontiers in Pharmacology. 2020;10:1550. doi:10.3389/fphar.2019.01550
5. Anaba EA, et al. Automated warfarin dose prediction for Asian, American, and Caucasian populations using a deep neural network. Computers in Biology and Medicine. 2023;153:106556. doi:10.1016/j.compbiomed.2023.106556
6. Ryu JY, Kim HU, Lee SY. Deep learning improves prediction of drug–drug and drug–food interactions. Proceedings of the National Academy of Sciences. 2018;115(18):E4304–E4311. doi:10.1073/pnas.1803294115
7. Wu H, et al. Predicting adverse drug event using machine learning based on electronic health records: a systematic review and meta-analysis. Frontiers in Pharmacology. 2024;15:1497397. doi:10.3389/fphar.2024.1497397
8. Segal G, Segev A, Brom A, Lifshitz Y, Wasserstrum Y, Zimlichman E. Reducing drug prescription errors and adverse drug events by application of a probabilistic, machine-learning based clinical decision support system in an inpatient setting. Journal of the American Medical Informatics Association. 2019;26(12):1560–1565. doi:10.1093/jamia/ocz135
9. Chou E, et al. Ability of machine-learning based clinical decision support system to reduce alert fatigue, wrong-drug errors, and alert users about look alike, sound alike medication. Computer Methods and Programs in Biomedicine. 2024;243:107850. doi:10.1016/j.cmpb.2023.107850
10. Van Dort BA, Baysari MT, et al. Overall performance of a drug–drug interaction clinical decision support system: quantitative evaluation and end-user survey. BMC Medical Informatics and Decision Making. 2022;22:48. doi:10.1186/s12911-022-01783-z
11. Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI. An overview of clinical decision support systems: benefits, risks, and strategies for success. npj Digital Medicine. 2020;3:17. doi:10.1038/s41746-020-0221-y
12. Wasylewicz ATM, van de Burgt BWM, Manten T, et al. Contextualized drug–drug interaction management improves clinical utility compared with basic drug–drug interaction management in hospitalized patients. Clinical Pharmacology & Therapeutics. 2022;112(2):382–390. doi:10.1002/cpt.2624
13. Singhal K, Azizi S, Tu T, et al. Large language models encode clinical knowledge. Nature. 2023;620(7972):172–180. doi:10.1038/s41586-023-06291-2
14. Bates DW, Levine D, Syrowatka A, et al. The potential of artificial intelligence to improve patient safety: a scoping review. npj Digital Medicine. 2021;4:54. doi:10.1038/s41746-021-00423-6
15. Roosan D, Hwang A, Roosan MR. Pharmacogenomics cascade testing (PhaCT): a novel approach for preemptive pharmacogenomics testing to optimize medication therapy. The Pharmacogenomics Journal. 2021;21:1–7. doi:10.1038/s41397-020-00182-9