Artificial Intelligence in Polypharmacy. Moving Beyond Drug Alerts Toward Patient-Specific Medication Safety

Polypharmacy is an increasing challenge in modern clinical practice, particularly among older adults and patients with multimorbidity, chronic kidney disease, heart failure, diabetes, frailty, or cognitive impairment. Its clinical impact extends beyond the number of prescribed medicines and reflects the interaction between therapeutic burden, comorbidities, organ dysfunction, fragmented care, changing physiological reserve, and multiple prescribers. Traditional medication review remains essential but may be limited by incomplete medication histories, time constraints, fragmented records, and the difficulty of identifying clinically meaningful drug–drug, drug–disease, and drug–patient interactions. Artificial intelligence (AI) may support safer medication management by integrating prescribing data with diagnoses, laboratory values, clinical events, and patterns of healthcare use. Potential applications include medication reconciliation, prioritization of clinically relevant interactions, renal dose adjustment, adverse drug event prediction, recognition of prescribing cascades, and identification of patients most likely to benefit from structured medication review or deprescribing. However, the value of AI in polypharmacy management should not be measured by the number of alerts generated. Its most useful role may be to help clinicians distinguish theoretical medication-related risks from those that are likely to be clinically important for an individual patient. This requires transparent recommendations, reliable data, local validation, integration into clinical workflow, and clear professional accountability. This narrative clinical viewpoint discusses the opportunities, limitations, and ethical implications of AI in polypharmacy management. It argues that AI should function as a human-centered clinical decision-support tool that improves prioritization, supports multidisciplinary medication review, and preserves clinicianled and patient-centered prescribing decisions