Pharmacogenomics and Precision Medicine: From Genetic Testing to Individualized Pharmacotherapy

Abstract

Artificial intelligence (AI), including natural language processing, machine learning, and generative models, can assist pharmacovigilance by finding and structuring safety information across individual case safety reports (ICSRs), clinical records, scientific literature, and other sources. This narrative review examines how such tools support adverse drug reaction (ADR) detection and signal management, the evidence for operational use, and the safeguards required for responsible deployment. Current applications include report intake and duplicate detection, extraction of drugs and events from narrative text, case triage, literature screening, coding support, and prioritization of drug-event pairs for expert assessment. Published studies and a systematic review demonstrate technical feasibility, but evidence is heterogeneous and often task-specific; accuracy on curated datasets does not establish generalizability, causal association, or improved patient outcomes. Spontaneous-report disproportionality remains hypothesis-generating and is vulnerable to underreporting, stimulated reporting, missing denominators, and confounding. AI outputs therefore require documented context of use, representative validation, human review proportionate to risk, privacy protection, bias surveillance, change control, and traceable records. Current expectations include EMA’s 2024 lifecycle reflection paper, the 2025 ICH E2D(R1) guideline effective from 18 March 2026, and FDA–EMA Good AI Practice principles issued in 2026. AI is best positioned as governed decision support within the established signal-management process, with pharmacovigilance professionals retaining responsibility for interpretation and action.

Keywords

Authors & affiliations

Cite this article

Vrushti Shah. Pharmacogenomics and Precision Medicine: From Genetic Testing to Individualized Pharmacotherapy. ClinSphere Journals. 2026;1(1). https://doi.org/10.5281/zenodo.23794745

1. . Council for International Organizations of Medical Sciences (CIOMS). Artificial intelligence in pharmacovigilance: report of the CIOMS Working Group XIV. Geneva: CIOMS; 2025.
2. European Medicines Agency. Reflection paper on the use of Artificial Intelligence (AI) in the medicinal product lifecycle. EMA/CHMP/CVMP/83833/2023. Amsterdam: EMA; 2024.
3. US Food and Drug Administration, European Medicines Agency. Guiding principles of good AI practice in drug development. Silver Spring (MD): FDA; Amsterdam: EMA; 2026 Jan.
4. European Medicines Agency. Guideline on good pharmacovigilance practices (GVP): Module IX—Signal management (Rev 1). EMA/827661/2011 Rev 1. London: EMA; 2017.
5. Bate A, Evans SJW. Quantitative signal detection using spontaneous adverse drug reaction reporting. Pharmacoepidemiol Drug Saf. 2009;18(6):427-436. doi:10.1002/pds.1742.