Related Experiment Video
Updated: Jun 24, 2026
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Characterising 'Watch and Wait' prescribing patterns in paediatric otitis media using large language models and
Jessica Pourian1,2, Ben Michaels3, Anh Vo4
1Division of Clinical Informatics and Digital Transformation, University of California, San Francisco, San Francisco, California, USA jessica.pourian@ucsf.edu.
BMJ Health & Care Informatics
|June 22, 2026
Summary
Safety-net antibiotic prescriptions (SNAPs) for acute otitis media in children showed varied prescribing across demographics but similar dispensing. This highlights inequities in antibiotic stewardship needing further investigation.
Area of Science:
- Pediatric infectious diseases
- Antimicrobial stewardship
- Health informatics
Background:
- Acute otitis media (AOM) is a common childhood illness and a major driver of antibiotic use.
- Safety-net antibiotic prescriptions (SNAPs) are recommended for AOM to promote antibiotic stewardship.
- Current data capture methods limit understanding of SNAP prescribing and dispensing patterns.
Purpose of the Study:
- To evaluate SNAP prescribing and dispensing patterns in pediatric AOM encounters.
- To identify demographic and clinical factors associated with SNAP use.
- To assess the utility of large language models (LLMs) in analyzing clinical notes for prescription classification.
Main Methods:
- Retrospective cross-sectional study of 4370 AOM encounters (ages 6 months-<18 years) from 2021-2024.
- An LLM classified prescriptions as immediate (TTPs) or delayed (SNAPs) by reviewing clinician notes.
- Dispensing data were linked from electronic health records.
Main Results:
- 23.4% of AOM encounters received SNAPs, while 76.6% received immediate treatment today prescriptions (TTPs).
- Patients speaking non-English languages and those in lower socioeconomic quartiles were less likely to receive SNAPs.
- SNAPs were less likely to be filled compared to TTPs, with no significant difference in dispensing time for SNAPs across patient groups.
Conclusions:
- SNAP prescribing for pediatric AOM is influenced by patient demographics, indicating potential inequities in antibiotic stewardship.
- Dispensing patterns for filled SNAPs were consistent across different patient groups.
- Further research is needed to understand prescribing variations and ensure equitable antibiotic stewardship practices.
Related Concept Videos
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
01:12Analysis of Population Pharmacokinetic Data
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
01:14Model Approaches for Pharmacokinetic Data: Compartment Models
Compartmental analysis is a widely adopted approach to characterizing drug pharmacokinetics. It uses compartment models that conceptualize the body as a collection of reversibly communicating compartments, each representing a group of tissues exhibiting similar drug distribution characteristics. The movement rate of the drug between these compartments is typically described by first-order kinetics.
Two primary types of compartment models are recognized: mammillary and catenary. The more...
Two primary types of compartment models are recognized: mammillary and catenary. The more...
01:20Pharmacokinetic Models: Overview
Pharmacokinetic models utilize mathematical analysis to achieve a detailed quantitative understanding of a drug's life cycle within the body. They are instrumental in simulating a drug's pharmacokinetic parameters, predicting drug concentrations over time, optimizing dosage regimens, linking concentrations with pharmacologic activity, and estimating potential toxicity.
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal assumptions,...
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal assumptions,...
00:59Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
Noncompartmental analyses offer an alternative method for describing drug pharmacokinetics without relying on a specific compartmental model. In this approach, the drug's pharmacokinetics are assumed to be linear, with the terminal phase log-linear. This assumption allows for simplified analysis and interpretation of the drug's behavior in the body.
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This relationship...
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This relationship...
01:15Impact of Pharmacokinetic–Pharmacodynamic Models: Regulatory Decisions
PK–PD modeling has significantly influenced FDA regulatory decisions, particularly drug approval, dosage optimization, and labeling. These models integrate pharmacokinetics (PK) and pharmacodynamics (PD) to predict drug behavior and effects, aiding in optimizing dosing regimens and enhancing the probability of clinical trial success.One notable example is Nesiritide (Natrecor®), a recombinant human brain natriuretic peptide for treating acute decompensated congestive heart failure (CHF).