Journaling with large language models: a novel UX paradigm for AI-driven personal health management
IntroductionThe integration of large language models (LLMs) into personal health management presents transformative potential, but faces critical challenges in user experience (UX) design, ethical implementation, and clinical integration.MethodThis paper introduces a novel AI-driven journaling appli...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2025.1567580/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849706206809030656 |
|---|---|
| author | Birger Moëll Fredrik Sand Aronsson Fredrik Sand Aronsson |
| author_facet | Birger Moëll Fredrik Sand Aronsson Fredrik Sand Aronsson |
| author_sort | Birger Moëll |
| collection | DOAJ |
| description | IntroductionThe integration of large language models (LLMs) into personal health management presents transformative potential, but faces critical challenges in user experience (UX) design, ethical implementation, and clinical integration.MethodThis paper introduces a novel AI-driven journaling application, a functional prototype available open source, designed to encourage patient engagement through a natural language interface. This approach, termed “AI-assisted health journaling,” enables users to document health experiences in their own words while receiving real-time, context-aware feedback from an LLM. The prototype combines a personal health record with an LLM assistant, allowing for reflective self-monitoring and aiming to combine patient-generated data with clinical insights. Key innovations include a three-panel interface for seamless journaling, AI dialogue, and longitudinal tracking, alongside specialized modes for interacting with simulated healthcare expert personas.ResultPreliminary insights from persona-based evaluations highlight the system's capacity to enhance health literacy through explainable AI responses while maintaining strict data localization and privacy controls. We propose five design principles for patient-centric AI health tools: (1) decoupling core functionality from LLM dependencies, (2) layered transparency in AI outputs, (3) adaptive consent for data sharing, (4) clinician-facing data summarization, and (5) compliance-first architecture.DiscussionBy transforming unstructured patient narratives into structured insights through natural language processing, this approach demonstrates how journaling interfaces could serve as a critical middleware layer in healthcare ecosystems-empowering patients as active partners in care while preserving clinical oversight. Future research directions emphasize the need for rigorous trials evaluating impacts on care continuity, patient-provider communication, and long-term health outcomes across diverse populations. |
| format | Article |
| id | doaj-art-1a4effa12d074be3aa131cbf9a06c679 |
| institution | DOAJ |
| issn | 2624-8212 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj-art-1a4effa12d074be3aa131cbf9a06c6792025-08-20T03:16:15ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-06-01810.3389/frai.2025.15675801567580Journaling with large language models: a novel UX paradigm for AI-driven personal health managementBirger Moëll0Fredrik Sand Aronsson1Fredrik Sand Aronsson2Division of Speech, Music and Hearing, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, SwedenDivision of Speech and Language Pathology, Department of Clinical Science, Intervention and Technology, Karolinska Institutet, Stockholm, SwedenTheme Womens Health and Allied Health Professionals, Section of Speech and Language Pathology, Karolinska University Hospital, Stockholm, SwedenIntroductionThe integration of large language models (LLMs) into personal health management presents transformative potential, but faces critical challenges in user experience (UX) design, ethical implementation, and clinical integration.MethodThis paper introduces a novel AI-driven journaling application, a functional prototype available open source, designed to encourage patient engagement through a natural language interface. This approach, termed “AI-assisted health journaling,” enables users to document health experiences in their own words while receiving real-time, context-aware feedback from an LLM. The prototype combines a personal health record with an LLM assistant, allowing for reflective self-monitoring and aiming to combine patient-generated data with clinical insights. Key innovations include a three-panel interface for seamless journaling, AI dialogue, and longitudinal tracking, alongside specialized modes for interacting with simulated healthcare expert personas.ResultPreliminary insights from persona-based evaluations highlight the system's capacity to enhance health literacy through explainable AI responses while maintaining strict data localization and privacy controls. We propose five design principles for patient-centric AI health tools: (1) decoupling core functionality from LLM dependencies, (2) layered transparency in AI outputs, (3) adaptive consent for data sharing, (4) clinician-facing data summarization, and (5) compliance-first architecture.DiscussionBy transforming unstructured patient narratives into structured insights through natural language processing, this approach demonstrates how journaling interfaces could serve as a critical middleware layer in healthcare ecosystems-empowering patients as active partners in care while preserving clinical oversight. Future research directions emphasize the need for rigorous trials evaluating impacts on care continuity, patient-provider communication, and long-term health outcomes across diverse populations.https://www.frontiersin.org/articles/10.3389/frai.2025.1567580/fulllarge language models (LLMs)AI-driven journalingpatient engagementhealth literacyexplainable AIdata privacy |
| spellingShingle | Birger Moëll Fredrik Sand Aronsson Fredrik Sand Aronsson Journaling with large language models: a novel UX paradigm for AI-driven personal health management Frontiers in Artificial Intelligence large language models (LLMs) AI-driven journaling patient engagement health literacy explainable AI data privacy |
| title | Journaling with large language models: a novel UX paradigm for AI-driven personal health management |
| title_full | Journaling with large language models: a novel UX paradigm for AI-driven personal health management |
| title_fullStr | Journaling with large language models: a novel UX paradigm for AI-driven personal health management |
| title_full_unstemmed | Journaling with large language models: a novel UX paradigm for AI-driven personal health management |
| title_short | Journaling with large language models: a novel UX paradigm for AI-driven personal health management |
| title_sort | journaling with large language models a novel ux paradigm for ai driven personal health management |
| topic | large language models (LLMs) AI-driven journaling patient engagement health literacy explainable AI data privacy |
| url | https://www.frontiersin.org/articles/10.3389/frai.2025.1567580/full |
| work_keys_str_mv | AT birgermoell journalingwithlargelanguagemodelsanoveluxparadigmforaidrivenpersonalhealthmanagement AT fredriksandaronsson journalingwithlargelanguagemodelsanoveluxparadigmforaidrivenpersonalhealthmanagement AT fredriksandaronsson journalingwithlargelanguagemodelsanoveluxparadigmforaidrivenpersonalhealthmanagement |