AI-written plain-language discharge summaries for people with blood and other cancers
Prospective Randomized Controlled Trial to Evaluate Locally Implemented Large Language Models (LLMs) for Simplifying Patient Communication in Hematology and Oncology
This project tests whether AI-written plain-language discharge letters help adults with hematologic or other cancers understand their diagnosis, treatment, and next steps better than the usual medical letter.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 150 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Technical University of Munich Academic / other |
| Locations | 1 site (Munich, Bavaria) |
| Trial ID | NCT07519811 on ClinicalTrials.gov |
What this trial studies
This single-center, prospective randomized controlled trial at the Technical University of Munich randomizes hematology and oncology inpatients 2:1 to receive an AI-simplified discharge letter plus the standard letter or the standard letter alone. An on-premise large language model automatically simplifies key sections of the discharge letter and a study physician reviews and approves the simplified text before patient delivery. Patients with limited German proficiency are enrolled in a separate, nonrandomized translation arm where letters are simplified and translated. The primary outcome is a 5-item Likert-based comprehension score with questionnaires completed after patients read their letters.
Who should consider this trial
Good fit: Adult inpatients of the Department of Medicine III (Hematology/Oncology) at Klinikum rechts der Isar who receive a routine discharge letter containing the specified sections and are able to give informed consent.
Not a fit: Patients with significant cognitive impairment, those whose discharge letters lack the targeted sections, or people unable to read the simplified language may not gain benefit from the intervention.
Why it matters
Potential benefit: If successful, patients could better understand their care plans and follow-up instructions, which may improve adherence and reduce post-discharge confusion.
How similar studies have performed: Prior technical and observational work shows LLMs can produce accurate plain-language medical summaries, but randomized trials testing clinical benefit in oncology discharge care are lacking.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age 18 years or older * Inpatient of the Department of Medicine III (Hematology/Oncology) at TUM University Hospital (Klinikum rechts der Isar), Munich, Germany * Receipt of a discharge letter including the sections Current Status, Medical History, Epicrisis, and Further Management as part of routine clinical care * Capacity to provide informed consent * Written informed consent following the consent procedure Exclusion Criteria: * Cognitive impairment precluding independent assessment of comprehension (e.g., dementia, severe encephalopathy) * Participation in another study with potential influence on the study endpoints * Lack of capacity to provide informed consent * Refusal to participate in the study
Where this trial is running
Munich, Bavaria
- Technical University Munich — Munich, Bavaria, Germany (Recruiting)
Study contacts
- Study coordinator: Krischan Braitsch, MD
- Email: krischan.braitsch@tum.de
- Phone: +49 089 4140 1268
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.