Prescribing decision support — drug interaction alerts

CuratedPilotNo evidence on file

Reviewed for completeness and published to the Library.

Screens new prescriptions against the medication list and patient parameters to alert prescribers to clinically significant drug interactions.

Plain-language summary

Choose an audience and generate a tailored summary on demand. The AI uses only what is on this page.

Clinical context

Clinical problem: Detect a condition
Point of care: Treatment planning
Nature of AI output: An alert
Clinical specialty: Pharmacy
Care setting: Hospital — inpatient
Patient population: Adult inpatients with active prescriptions, with emphasis on polypharmacy and renally-impaired patients.
Intended use: Screens new prescriptions against the medication list and patient parameters to alert prescribers to clinically significant drug interactions.

Technology

Deployment

Regulatory & governance

EU AI Act risk tier: Not assessed
High-risk basis: Not applicable
Medical device: No
EU MDR class: Not a device
CE marking: Not required
FDA status: Not applicable
ISO 14971 risk class: Not assessed
GDPR processing basis: Legal obligation
GDPR DPIA: Not required
Data identifiability: Pseudonymised
Explainability method: Intrinsic
Human oversight model: Interruptive alert at the point of prescribing; the prescriber accepts or overrides with a reason.

NICE evidence standards

Performance summary

Headline metric: Positive predictive value
Value: 0.68
Subgroup performance assessed: No
Known bias signals: High override rate observed for low-severity alerts; tiering of alert severity under review to reduce fatigue.

Looking for close matches in the Library…

Deploying organisation: [demo] Aarhus University Hospital · Hospital / health system · Denmark
AI vendor: —
Product name: —