LLM-Generated Plain-Language Patient Synopses to Improve Comprehension in Hematology and Oncology (oncOPAL) (oncOPAL)

Prospective Randomized Controlled Trial to Evaluate Locally Implemented Large Language Models (LLMs) for Simplifying Patient Communication in Hematology and Oncology

This study tests whether patients with blood cancer or other cancers better understand their medical information when it is rewritten in plain language by an artificial intelligence (AI) system.

When patients are discharged from the hospital, they receive a medical letter summarizing their diagnosis, treatment, and next steps. These letters are often written in technical language that is difficult for patients to understand. In this study, an AI language model running on the hospital's own secure servers rewrites parts of this letter into simpler language. A physician checks the simplified version before the patient receives it.

Patients are randomly assigned to one of two groups. One group receives both the standard medical letter and the AI-simplified version. The other group receives the standard letter only. A separate group of patients who do not speak German well will receive a simplified and translated version.

After reading their letter, all participants fill out a short questionnaire about how well they understood the information. The study takes place at TUM University Hospital (Klinikum rechts der Isar) in Munich, Germany.

Study Overview

• Status: Recruiting
• Conditions: Hematologic Neoplasms; Oncologic Disorders
• Intervention / Treatment: Other: LLM-Generated Plain-Language Patient Synopsis

Detailed Description

Background:

Studies show that up to 40-80% of medical information conveyed during physician consultations is not correctly recalled or understood by patients. This problem is particularly relevant in hematology and oncology, where treatment regimens, prognoses, and side-effect profiles are complex. Large language models (LLMs) have demonstrated the ability to convert medical texts into plain language with high accuracy. However, prospective randomized controlled trials evaluating the clinical benefit of LLM-simplified patient synopses in routine care are lacking.

Study Design:

Prospective, single-center, randomized controlled trial with parallel group design. Randomization is 2:1 (intervention : control) using permuted blocks of variable size (4-6). An additional non-randomized translation arm enrolls patients with insufficient German language proficiency.

Intervention:

The locally implemented LLM system (on-premise, no external data transmission) automatically simplifies the following sections of the discharge letter: Current Status, Medical History, Epicrisis, and Further Management. A study physician reviews and approves the simplified version before it is given to the patient. The system is not classified as a medical device and is not used for diagnosis or treatment decisions.

Endpoints:

The primary endpoint is a comprehension score measured by a 5-item scale (10-point Likert, based on PEMAT), assessing overall comprehension and comprehension of diagnosis, treatment, next steps, and medical terminology. Secondary endpoints include patient satisfaction (EORTC QLQ-INFO25 subscales), subjective uncertainty reduction, format preference, physician review time, correction rate, and translation quality.

Statistical Analysis:

The primary endpoint will be analyzed using a t-test or Mann-Whitney U-test. A clinically relevant difference of 1.5 points on the 10-point scale is assumed. With a standard deviation of 2.5, power of 80%, and alpha of 0.05 (two-sided), 136 randomized patients are required (91 intervention, 45 control). Accounting for a 10% dropout rate, 150 patients will be recruited for the randomized arms, plus 30 for the translation arm (total n=180).

Data Protection:

All data are pseudonymized and stored on secure hospital servers. No patient data are transmitted to external servers or cloud services. The study complies with GDPR.

• Study Type: Interventional
• Enrollment (Estimated): 150
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Krischan Braitsch, MD; Phone Number: +49 089 4140 1268; Email: krischan.braitsch@tum.de
• Study Contact Backup: Name: Lisa C. Adams, MD; Phone Number: +49 089 4140 1084; Email: lisa.adams@tum.de

Study Locations

• Germany
  • Bavaria
    • Munich, Bavaria, Germany, 81675
      • Recruiting
      • Technical University Munich

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

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

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention: LLM-Simplified Synopsis; Participants receive the standard discharge letter synopsis plus an LLM-generated plain-language version of the following sections: Current Status, Medical History, Epicrisis, and Further Management. The simplified version is reviewed and approved by a study physician before being given to the patient.	Other: LLM-Generated Plain-Language Patient Synopsis; A locally implemented large language model (GPT-OSS, on-premise) automatically rewrites selected sections of the hospital discharge letter (Current Status, Medical History, Epicrisis, and Further Management) into plain language. A study physician reviews the output for accuracy before it is provided to the patient. The system is not classified as a medical device and is not used for diagnosis or treatment decisions. No patient data are transmitted to external servers.
No Intervention: Control: Standard Synopsis; Participants receive the standard discharge letter synopsis only, as provided in routine clinical care.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Patient Comprehension Score	Comprehension of the patient synopsis measured using a 5-item scale based on the Patient Education Materials Assessment Tool (PEMAT; scores range from 1 to 10, with higher scores indicating better comprehension), assessing overall comprehension and comprehension of diagnosis, treatment, next steps, and medical terminology. The score is calculated as the mean of all five items (range 0-10; higher scores indicate better comprehension).	At the time of hospital discharge (Day 0), assessed immediately after reading the synopsis (approximately 15-30 minutes after receipt)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Patient Satisfaction with Information Received	Patient satisfaction (European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire - Information Module 25 [EORTC QLQ-INFO25] subscales; scores range from 0 to 100, with higher scores indicating better-perceived information)	Day 0, assessed immediately after reading the synopsis
Subjective Uncertainty Reduction	Single-item measure on a 0-10 scale, administered before and after reading the synopsis	Day 0, before and after reading the synopsis
Patient Preference for Synopsis Format	Categorical variable assessing which synopsis format the patient preferred	Day 0, assessed immediately after reading the synopsis
Physician Review Time	Time in minutes required for the study physician to review and approve the LLM-generated synopsis	Day 0, recorded at time of physician review
Physician Correction Rate	Rate of necessary corrections made by the study physician to the LLM-generated synopsis prior to patient handout	Day 0, recorded at time of physician review

Collaborators and Investigators

• Sponsor: Technical University of Munich

Study record dates

Study Major Dates

• Study Start (Actual): April 1, 2026
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): April 1, 2027

Study Registration Dates

• First Submitted: March 22, 2026
• First Submitted That Met QC Criteria: April 4, 2026
• First Posted (Actual): April 9, 2026

Study Record Updates

• Last Update Posted (Actual): April 16, 2026
• Last Update Submitted That Met QC Criteria: April 13, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: Patient-Provider Communication; Large Language Model; Patient Health Literacy
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Hematologic Diseases; Hemic and Lymphatic Diseases; Hematologic Neoplasms
• Other Study ID Numbers: oncOPAL-V1.0

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data will not be shared. All study data are pseudonymized and stored on secure hospital servers at TUM University Hospital (Klinikum rechts der Isar) in compliance with the General Data Protection Regulation (GDPR). The study protocol does not provide for disclosure of participant-level data to third parties. Aggregate, anonymized data will be made available through publication of results.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No