Mohamed A. Ismail
Abstract Peripartum mental health disorders (PMHDs) constitute a substantial enormous population health problem, affecting an estimated 10% of pregnant women worldwide and 13% of women in the postpartum period. Their diagnosis and treatment at this crucial time are often hampered by a lack of precision. This review describes a framework for precision perinatal psychiatry that integrates pharmacogenomics (PGx), multi-omics, and artificial intelligence/machine learning (AI/ML). This review highlights the essential role of therapeutic drug monitoring (TDM) with PGx to manage control the expected oscillations in drug clearance during the perinatal period. AI/ML approaches may enable integration of multi-omics datasets to improve drug safety prediction and facilitate early PMHD risk identification, culminating in a proposed Precision Dosing Framework that utilizes AI/ML-informed PBPK modeling for dynamic, individualized dose adjustments across gestation and lactation. This review identifies critical translational-level challenges, including the need for very large longitudinal cohorts, solid methodological approaches, explainable AI (xAI), and ethical considerations, and outlines directions for addressing these issues to facilitate clinical implementation. This roadmap has the potential to pave the way for highly personalized, efficacious, and safe interventions, all of which may ultimately improve perinatal outcomes for mothers and infants.