Related Experiment Video
Updated: Dec 26, 2025
A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
Published on: May 10, 2022
LLMonFHIR: A Physician-Validated, Large Language Model-Based Mobile Application for Querying Patient Electronic
Paul Schmiedmayer1, Adrit Rao1, Philipp Zagar1
1Stanford Mussallem Center for Biodesign, Stanford University, Stanford, California, USA.
Background:
To improve healthcare quality and empower patients, federal legislation requires nationwide interoperability of electronic health records (EHRs) through Fast Healthcare Interoperability Resources (FHIR) application programming interfaces. Nevertheless, key barriers to patient EHR access-limited functionality, English, and health literacy-persist, impeding equitable access to these benefits.
Objectives:
This study aimed to develop and evaluate a digital health solution to address barriers preventing patient engagement with personal health information, focusing on individuals managing chronic cardiovascular conditions.
Methods:
We present LLMonFHIR, an open-source mobile application that uses large language models (LLMs) to allow users to "interact" with their health records at any degree of complexity, in various languages, and with bidirectional text-to-speech functionality. In a pilot evaluation, physicians assessed LLMonFHIR responses to queries on 6 SyntheticMass FHIR patient datasets, rating accuracy, understandability, and relevance on a 5-point Likert scale.
Results:
A total of 210 LLMonFHIR responses were evaluated by physicians, receiving high median scores for accuracy (5/5), understandability (5/5), and relevance (5/5). Challenges summarizing health conditions and retrieving lab results were noted, with variability in responses and occasional omissions underscoring the need for precise preprocessing of data.
Conclusions:
LLMonFHIR's ability to generate responses in multiple languages and at varying levels of complexity, along with its bidirectional text-to-speech functionality, give it the potential to empower individuals with limited functionality, English, and health literacy to access the benefits of patient-accessible EHRs.
Related Concept Videos
01:20Infection
The chain begins with pathogens: bacteria, viruses, fungi, prions, or parasites such as protozoa helminths. These can be present on the skin as transient or resident flora, or they can be acquired from the environment. Identifying and treating the type of infection and...
01:17Antidotes
Specific antidotes operate by inhibiting the enzymes that control biochemical pathways, reducing the production of harmful metabolites.
An example of an antidote is atropine, which counteracts the detrimental effects of cholinesterase inhibitors. It achieves this by deactivating muscarinic receptors,...
01:13Amnesia
The severity and duration of memory loss vary depending on the type and underlying cause. Amnesia is classified into two main types: retrograde and anterograde.
Retrograde amnesia is marked by the loss of memories formed before the onset of the condition. Patients may recall distant past events but often forget those occurring shortly before the incident.
Anterograde...
01:16Interference and Decay
Interference occurs when competing memories hinder the retrieval of particular information. It can be classified into two types: proactive and retroactive interference. Proactive...
01:27Panic Disorder
01:18Steps in Outbreak Investigation