Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content Analysis

Abstract BackgroundThere is growing interest in applying generative artificial intelligence (GenAI) to respond to electronic patient portal messages, particularly in primary care where message volumes are highest. However, evaluations of GenAI as an inbox communication tool ar...

Full description

Saved in:
Bibliographic Details
Main Authors: Natalie S Lee, Nathan Richards, Jodi Grandominico, Robert M Cronin, Amanda K Hendricks, Ravi S Tripathi, Daniel E Jonas
Format: Article
Language:English
Published: JMIR Publications 2025-07-01
Series:JMIR Formative Research
Online Access:https://formative.jmir.org/2025/1/e71966
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850033049631195136
author Natalie S Lee
Nathan Richards
Jodi Grandominico
Robert M Cronin
Amanda K Hendricks
Ravi S Tripathi
Daniel E Jonas
author_facet Natalie S Lee
Nathan Richards
Jodi Grandominico
Robert M Cronin
Amanda K Hendricks
Ravi S Tripathi
Daniel E Jonas
author_sort Natalie S Lee
collection DOAJ
description Abstract BackgroundThere is growing interest in applying generative artificial intelligence (GenAI) to respond to electronic patient portal messages, particularly in primary care where message volumes are highest. However, evaluations of GenAI as an inbox communication tool are limited. Qualitative analysis of when and how often GenAI responses achieve communication goals can inform estimates of impact and guide continuous improvement. ObjectiveThis study aims to evaluate GenAI responses to primary care messages using a medical communication framework. MethodsThis was a descriptive quality improvement study of 201 GenAI replies to a purposively sampled, diverse pool of real primary care patient messages in a large midwestern academic medical center. Two physician reviewers (NSL and NR) used a hybrid deductive-inductive approach to qualitatively identify and define themes, guided by constructs from the “best practice” medical communication framework. After achieving thematic saturation, the reviewers assessed the presence or absence of identified communication themes, both independently and collaboratively. Discrepant observations were reconciled via discussion. Frequencies of identified themes were tallied. ResultsThemes in strengths and limitations emerged across 5 communication domains. In the domain of rapport buildinginformation gatheringinformation deliveryfacilitate next stepsresponding to emotionrapport buildingfacilitating next stepsinformation deliveryinformation gatheringresponding to emotion ConclusionsGenAI response quality on behalf of primary care physicians and advanced practice providers may vary by communication function. Expressions of respect or descriptions of common next steps may be appropriate, but gathering and delivering appropriate information, or responding to emotion, may be limited. While communication standards were often met, they were also often compromised. Understanding these strengths and limitations can inform decisions about whether, when, and how to apply GenAI as a tool for primary care inbox communication.
format Article
id doaj-art-e6ce8a1960f74f9f822f98268af36551
institution DOAJ
issn 2561-326X
language English
publishDate 2025-07-01
publisher JMIR Publications
record_format Article
series JMIR Formative Research
spelling doaj-art-e6ce8a1960f74f9f822f98268af365512025-08-20T02:58:21ZengJMIR PublicationsJMIR Formative Research2561-326X2025-07-019e71966e7196610.2196/71966Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content AnalysisNatalie S Leehttp://orcid.org/0000-0002-6335-7934Nathan Richardshttp://orcid.org/0009-0003-0687-6791Jodi Grandominicohttp://orcid.org/0009-0000-1746-4731Robert M Croninhttp://orcid.org/0000-0003-1916-6521Amanda K Hendrickshttp://orcid.org/0009-0007-6027-0458Ravi S Tripathihttp://orcid.org/0000-0003-1873-6836Daniel E Jonashttp://orcid.org/0000-0003-1964-8731 Abstract BackgroundThere is growing interest in applying generative artificial intelligence (GenAI) to respond to electronic patient portal messages, particularly in primary care where message volumes are highest. However, evaluations of GenAI as an inbox communication tool are limited. Qualitative analysis of when and how often GenAI responses achieve communication goals can inform estimates of impact and guide continuous improvement. ObjectiveThis study aims to evaluate GenAI responses to primary care messages using a medical communication framework. MethodsThis was a descriptive quality improvement study of 201 GenAI replies to a purposively sampled, diverse pool of real primary care patient messages in a large midwestern academic medical center. Two physician reviewers (NSL and NR) used a hybrid deductive-inductive approach to qualitatively identify and define themes, guided by constructs from the “best practice” medical communication framework. After achieving thematic saturation, the reviewers assessed the presence or absence of identified communication themes, both independently and collaboratively. Discrepant observations were reconciled via discussion. Frequencies of identified themes were tallied. ResultsThemes in strengths and limitations emerged across 5 communication domains. In the domain of rapport buildinginformation gatheringinformation deliveryfacilitate next stepsresponding to emotionrapport buildingfacilitating next stepsinformation deliveryinformation gatheringresponding to emotion ConclusionsGenAI response quality on behalf of primary care physicians and advanced practice providers may vary by communication function. Expressions of respect or descriptions of common next steps may be appropriate, but gathering and delivering appropriate information, or responding to emotion, may be limited. While communication standards were often met, they were also often compromised. Understanding these strengths and limitations can inform decisions about whether, when, and how to apply GenAI as a tool for primary care inbox communication.https://formative.jmir.org/2025/1/e71966
spellingShingle Natalie S Lee
Nathan Richards
Jodi Grandominico
Robert M Cronin
Amanda K Hendricks
Ravi S Tripathi
Daniel E Jonas
Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content Analysis
JMIR Formative Research
title Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content Analysis
title_full Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content Analysis
title_fullStr Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content Analysis
title_full_unstemmed Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content Analysis
title_short Use of a Medical Communication Framework to Assess the Quality of Generative Artificial Intelligence Replies to Primary Care Patient Portal Messages: Content Analysis
title_sort use of a medical communication framework to assess the quality of generative artificial intelligence replies to primary care patient portal messages content analysis
url https://formative.jmir.org/2025/1/e71966
work_keys_str_mv AT natalieslee useofamedicalcommunicationframeworktoassessthequalityofgenerativeartificialintelligencerepliestoprimarycarepatientportalmessagescontentanalysis
AT nathanrichards useofamedicalcommunicationframeworktoassessthequalityofgenerativeartificialintelligencerepliestoprimarycarepatientportalmessagescontentanalysis
AT jodigrandominico useofamedicalcommunicationframeworktoassessthequalityofgenerativeartificialintelligencerepliestoprimarycarepatientportalmessagescontentanalysis
AT robertmcronin useofamedicalcommunicationframeworktoassessthequalityofgenerativeartificialintelligencerepliestoprimarycarepatientportalmessagescontentanalysis
AT amandakhendricks useofamedicalcommunicationframeworktoassessthequalityofgenerativeartificialintelligencerepliestoprimarycarepatientportalmessagescontentanalysis
AT ravistripathi useofamedicalcommunicationframeworktoassessthequalityofgenerativeartificialintelligencerepliestoprimarycarepatientportalmessagescontentanalysis
AT danielejonas useofamedicalcommunicationframeworktoassessthequalityofgenerativeartificialintelligencerepliestoprimarycarepatientportalmessagescontentanalysis