Related Experiment Video
Updated: Jan 10, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Artificial intelligence-generated draft replies to patient messages in pediatrics
April S Liang1, Shivam Vedak1, Alex Dussaq2
1Division of Hospital Medicine, Department of Medicine, Stanford University School of Medicine, Palo Alto, CA 94304, United States.
Insights
Pediatric clinicians found artificial intelligence (AI)-generated draft responses useful for reducing perceived task load, despite lower utilization rates compared to obstetric clinicians. This AI tool shows promise for improving efficiency in pediatric care.
Area of Science:
- Medical Informatics
- Clinical Practice
- Artificial Intelligence in Healthcare
Background:
- Patient messaging systems in healthcare generate significant clinician workload.
- Artificial intelligence (AI) offers potential solutions for managing communication tasks.
- Understanding clinician experiences with AI tools is crucial for adoption.
Purpose of the Study:
- To evaluate the utilization and experiences of AI-generated draft responses among pediatric ambulatory clinicians.
- To compare pediatric clinician experiences with those of adult specialty clinicians.
- To assess the impact of AI tools on clinician task load and tool recommendation.
Main Methods:
- A prospective pilot study was conducted in pediatric and obstetric clinics.
- Clinicians used an AI feature embedded in the electronic health record to generate draft responses.
- Data collected included AI draft usage rates and clinician-reported task load via surveys.
Main Results:
- Pediatric clinicians utilized 13.3% of AI-generated drafts, less than obstetric clinicians (18.3%).
- Despite lower usage, pediatric clinicians reported a significant reduction in perceived task load.
- Pediatric clinicians were more likely to recommend the AI tool compared to obstetric clinicians.
Conclusions:
- AI-generated draft responses are utilized within expected ranges by pediatric clinicians.
- The AI tool demonstrated utility in reducing perceived task load for pediatric clinicians.
- AI tools hold potential for enhancing efficiency and mitigating workload in pediatric ambulatory care.
Objectives:
This study describes the utilization and experiences of artificial intelligence (AI)-generated draft responses to patient messages in pediatric ambulatory clinicians and contextualizes their experiences in relation to those of adult specialty clinicians.
Materials And Methods:
A prospective pilot was conducted from September 2023 to August 2024 in 2 pediatric clinics (General Pediatric and Adolescent Medicine) and 2 obstetric clinics (Reproductive Endocrinology and Infertility and General Obstetrics) within an academic health system in Northern California. Participants included physician, nurse, and medical assistant volunteers. The intervention involved a feature utilizing large language models embedded in the electronic health record to generate draft responses. Proportion of AI-generated draft used was collected, as were prepilot and follow-up surveys.
Results:
A total of 61 clinicians (26 pediatric, 35 obstetric) enrolled, with 46 (75%) completing both surveys. Pediatric clinicians utilized 13.3% (95% CI, 12.3%-14.4%) of AI-generated drafts, and usage rates when responding to patients vs their proxies was similar (15% vs 12.9%, P = .24). Despite using AI-generated drafts significantly less than obstetric clinicians (18.3% [17.2%-19.5%], P < .0001), pediatric clinicians reported a significant reduction in perceived task load (NASA Task Load Index: 59.9-50.9, P = .04) and were more likely to recommend the tool (LTR: 7.0 vs 5.2, P = .04).
Discussion And Conclusion:
Pediatric clinicians used AI-generated drafts at a rate within previously reported ranges in adult specialties and experienced utility. These findings suggest this tool has potential for enhancing efficiency and reducing task load in pediatric care.
Related Concept Videos
Non-equilibrium in the Cell
Issues And Trends In Healthcare Delivery System
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Patient-centered Care

