EUVIMEDAtrasti EUVIMED
Open access

What’s Going On With Me and How Can I Better Manage My Health? The Potential of GPT-4 to Transform Discharge Letters Into Patient-Centered Letters to Enhance Patient Safety: Prospective, Exploratory Study

Was passiert mit mir und wie kann ich meine Gesundheit besser managen? Das Potenzial von GPT-4, Entlassungsbriefe in patientenzentrierte Briefe zur Verbesserung der Patientensicherheit zu überführen: prospektive, explorative Studie

Felix Eisinger iD, Friederike Holderried iD, Moritz Mahling iD, Christian Stegemann-Philipps iD, Anne Herrmann-Werner iD, Eric Nazarenus iD, Alessandra Sonanini iD, Martina Guthoff iD, Carsten Eickhoff iD, Martin Holderried iD

Journal of Medical Internet Research · 2025-01-21 · 27 · e67143

DOI: 10.2196/67143 ↗

Auf einen Blick

GPT-4 übertrug die meisten patientensicherheitsrelevanten Inhalte aus Entlassungsbriefen in patientenzentrierte Briefe. Einige wichtige Inhalte fehlten dennoch, und in einem kleinen Teil der Sätze traten medizinische Fehler auf.

Fragestellung

Wie gut überführt GPT-4 patientensicherheitsrelevante Informationen aus Entlassungsbriefen in patientenzentrierte Briefe?

Methode

Prospektive, explorative Studie mit 3 erstellten Entlassungsbriefen und 72 „learning objectives“; Analyse der erzeugten Patientenbriefe auf medizinische Richtigkeit, Patientenzentrierung und Vollständigkeit.

Ergebnisse

GPT-4 adressierte 56/72 (78 %) der learning objectives. 11/72 (15 %) fehlten in der Mehrheit der Patientenbriefe. Medizinische Fehler fanden sich in 31/787 (3,9 %) Sätzen. Die Lesbarkeit war besser als in den Entlassungsbriefen.

Schlussfolgerung der Autor:innen

GPT-4 hat Potenzial, Entlassungsbriefe in patientenzentrierte Kommunikation zu überführen. Die Briefe waren lesbarer und patientenzentrierter, deckten aber nicht alle patientensicherheitsrelevanten Inhalte ab.

Kernaussagen

  • 56/72 (78 %) learning objectives wurden adressiert
  • 11/72 (15 %) fehlten in der Mehrheit der Patientenbriefe
  • 31/787 (3,9 %) Sätze enthielten medizinische Fehler

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Journal article in Journal of Medical Internet Research, published online on 2025-01-21. Written by Felix Eisinger and 9 co-authors. Institution: Department of Diabetology, Endocrinology, Nephrology, University of Tübingen, Tübingen, Germany. Major MEDLINE topics: Patient Safety, Patient Discharge, Patient-Centered Care. Cited 22 times so far (Crossref); 39 references. The full text is freely available in PubMed Central.

Auf einen BlickSantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Background

For hospitalized patients, the discharge letter serves as a crucial source of medical information, outlining important discharge instructions and health management tasks. However, these letters are often written in professional jargon, making them difficult for patients with limited medical knowledge to understand. Large language models, such as GPT, have the potential to transform these discharge summaries into patient-friendly letters, improving accessibility and understanding.

Objective

This study aims to use GPT-4 to convert discharge letters into more readable patient-centered letters. We evaluated how effectively and comprehensively GPT-4 identified and transferred patient safety–relevant information from the discharge letters to the transformed patient letters.

Methods

Three discharge letters were created based on common medical conditions, containing 72 patient safety–relevant pieces of information, referred to as “learning objectives.” GPT-4 was prompted to transform these discharge letters into patient-centered letters. The resulting patient letters were analyzed for medical accuracy, patient centricity, and the ability to identify and translate the learning objectives. Bloom’s taxonomy was applied to analyze and categorize the learning objectives.

Results

GPT-4 addressed the majority (56/72, 78%) of the learning objectives from the discharge letters. However, 11 of the 72 (15%) learning objectives were not included in the majority of the patient-centered letters. A qualitative analysis based on Bloom’s taxonomy revealed that learning objectives in the “Understand” category (9/11) were more frequently omitted than those in the “Remember” category (2/11). Most of the missing learning objectives were related to the content field of “prevention of complications.” By contrast, learning objectives regarding “lifestyle” and “organizational” aspects were addressed more frequently. Medical errors were found in a small proportion of sentences (31/787, 3.9%). In terms of patient centricity, the patient-centered letters demonstrated better readability than the discharge letters. Compared with discharge letters, they included fewer medical terms (132/860, 15.3%, vs 165/273, 60/4%), fewer abbreviations (43/860, 5%, vs 49/273, 17.9%), and more explanations of medical terms (121/131, 92.4%, vs 0/165, 0%).

Conclusions

Our study demonstrates that GPT-4 has the potential to transform discharge letters into more patient-centered communication. While the readability and patient centricity of the transformed letters are well-established, they do not fully address all patient safety–relevant information, resulting in the omission of key aspects. Further optimization of prompt engineering may help address this issue and improve the completeness of the transformation.

Subjects

MeSH terms (MEDLINE)

Patient SafetyPatient DischargePatient-Centered CareHumansProspective Studies

Author keywords

GPT-4artificial intelligencehealth care communicationpatient educationpatient letterspatient safety

Authors and institutions

  • Department of Diabetology, Endocrinology, Nephrology, University of Tübingen, Tübingen, Germany.
  • Tübingen Institute for Medical Education, University of Tübingen, Tübingen, Germany.
  • Department of Medical Strategy, Process and Quality Management, University Hospital Tübingen, Tübingen, Germany.
  • Institute for Bioinformatics and Medical Informatics, University of Tübingen, Tübingen, Germany.

ORCID profiles: Felix Eisinger, Friederike Holderried, Moritz Mahling, Christian Stegemann-Philipps, Anne Herrmann-Werner, Eric Nazarenus, Alessandra Sonanini, Martina Guthoff, Carsten Eickhoff, Martin Holderried

Cite

APA

Eisinger, F., Holderried, F., Mahling, M., Stegemann-Philipps, C., Herrmann-Werner, A., Nazarenus, E., Sonanini, A., Guthoff, M., Eickhoff, C., & Holderried, M. (2025). What’s Going On With Me and How Can I Better Manage My Health? The Potential of GPT-4 to Transform Discharge Letters Into Patient-Centered Letters to Enhance Patient Safety: Prospective, Exploratory Study. Journal of Medical Internet Research, 27, e67143. https://doi.org/10.2196/67143

Vancouver

Eisinger F, Holderried F, Mahling M, Stegemann-Philipps C, Herrmann-Werner A, Nazarenus E, et al. What’s Going On With Me and How Can I Better Manage My Health? The Potential of GPT-4 to Transform Discharge Letters Into Patient-Centered Letters to Enhance Patient Safety: Prospective, Exploratory Study. Journal of Medical Internet Research. 2025;27:e67143. doi:10.2196/67143

BibTeX
@article{Eisinger2025,
  author = {Eisinger, Felix and Holderried, Friederike and Mahling, Moritz and Stegemann-Philipps, Christian and Herrmann-Werner, Anne and Nazarenus, Eric and Sonanini, Alessandra and Guthoff, Martina and Eickhoff, Carsten and Holderried, Martin},
  title = {What’s Going On With Me and How Can I Better Manage My Health? The Potential of GPT-4 to Transform Discharge Letters Into Patient-Centered Letters to Enhance Patient Safety: Prospective, Exploratory Study},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e67143},
  doi = {10.2196/67143}
}
Start for free →