American Journal of Health-System Pharmacy

With the growth of artificial intelligence or AI tools based on large language models, there is uncertainty on how well they perform clinical tasks such as medication management.

A group of researchers published in American Journal of Health System Pharmacy a report evaluating the performance of a large language model for medication management tasks.

The authors gave OpenAI's GPT-40 model tests on three medication tasks.

identifying available formulations for a given generic drug name, identifying drug-drug interactions for a given medication regimen, and preparing a medication order for a given generic drug name.

Although metolazone has typically been used for this purpose, acetazolamide is another potential option, albeit with less data behind it.

A group of authors sought to investigate this further by conducting a retrospective cohort study which they published in the American Journal of Health System Pharmacy.

Data from a hundred and twenty adult patients receiving adjunctive acetazolamide or metolazone with loop diuretics for volume overload were analyzed.

The primary outcome was cumulative urine output within forty-eight hours.