Overview

Master AI & Machine Learning for 50% Off

Go under the hood of AI — neural networks, real-world applications & more. Designed by UNSW experts.

Explore the intersection of artificial intelligence and clinical pharmacy practice through this course designed to build critical evaluation skills for AI-generated outputs in real-world healthcare settings. Develop the ability to identify and assess the full spectrum of AI tools encountered in pharmacy practice — from clinical decision support systems (CDSS) and AI-integrated electronic health records to pharmacogenomic platforms, Bayesian dosing software, and antimicrobial stewardship tools — while understanding their clinical value and key limitations. Apply pharmacological reasoning to evaluate CDSS alerts and interpret pharmacogenomic AI insights to make precision pharmacotherapy decisions that extend beyond single-gene recommendations. Master the selection of appropriate population pharmacokinetic models within Bayesian dosing software, evaluate AI antimicrobial stewardship recommendations against real-time resistance data, and integrate predictive analytics and telepharmacy AI outputs with direct clinical assessment. Tackle complex, multi-system scenarios by resolving conflicting outputs from disease-specific AI platforms through cross-guideline synthesis. Identify and deprescribe anticholinergic prescribing cascades, and incorporate frailty, falls risk, and patient-centred factors that isolated AI risk scores are unable to assess. Distinguish root-cause medication contributions to drug-induced clinical problems rather than defaulting to AI symptom-management suggestions, and synthesize conflicting outputs from fragmented specialist AI systems into a single, safe, patient-centred medication plan. Demonstrate integrated AI evaluation and clinical override competencies through simulated ICU, oncology, and ambulatory pharmacy scenarios. Apply the assess–verify–decide–document sequence consistently, and develop the judgment to detect AI errors that would cause patient harm if left unaddressed — reinforcing the pharmacist's essential role as a critical evaluator rather than a passive recipient of AI-generated recommendations.

Syllabus

Identify the categories of AI tools encountered in clinical pharmacy practice, explain their clinical value and key limitations, and describe the pharmacist's role in evaluating rather than simply accepting AI-generated outputs.
Apply pharmacological reasoning to evaluate CDSS alerts and AI-integrated EHR workflow outputs and interpret pharmacogenomic AI insights to make precision pharmacotherapy decisions that go beyond the AI's single-gene recommendation.
Apply Bayesian dosing software with appropriate population pharmacokinetic model selection, evaluate AI antimicrobial stewardship recommendations against real-time resistance data, and integrate predictive analytics and telepharmacy AI outputs with direct pharmacist clinical assessment.
Resolve conflicting outputs from disease-specific AI systems using cross-guideline synthesis, identify and deprescribe anticholinergic prescribing cascades, and integrate frailty, falls risk, and patient-centred factors that isolated AI risk scores cannot assess.
Identify root-cause medication contributions to drug-induced clinical problems rather than accepting AI symptom-management suggestions and integrate conflicting outputs from multiple fragmented specialist AI systems into a single, safe, patient-centred medication plan.
Demonstrate integrated AI evaluation and clinical override competencies across simulated ICU, oncology, and ambulatory pharmacy scenarios, applying the assess–verify–decide–document sequence and identifying AI errors that would cause patient harm if undetected.