LLM-Generated Plain-Language Patient Synopses to Improve Comprehension in Hematology and Oncology (oncOPAL)
Trial statusRecruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
Age18+
SponsorTechnical University of Munich
About this trial
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.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
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
Disqualifiers
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
Trial design
Design model
Parallel
Treatments tested in this trial
LLM-Generated Plain-Language Patient Synopsis
Other interventionA 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.
Treatment groups
150 Participants
are divided into 2 treatment groupsGroup A: Intervention: LLM-Simplified SynopsisExperimental treatment 1 intervention
Group B: Control: Standard SynopsisNo intervention 0 interventions
Trial outcomes
Primary outcomes
1
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).
Time frame
At the time of hospital discharge (Day 0), assessed immediately after reading the synopsis (approximately 15-30 minutes after receipt)Secondary outcomes
1
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)
Time frame
Day 0, assessed immediately after reading the synopsis2
Subjective Uncertainty Reduction
Single-item measure on a 0-10 scale, administered before and after reading the synopsis
Time frame
Day 0, before and after reading the synopsis3
Patient Preference for Synopsis Format
Categorical variable assessing which synopsis format the patient preferred
Time frame
Day 0, assessed immediately after reading the synopsis4
Physician Review Time
Time in minutes required for the study physician to review and approve the LLM-generated synopsis
Time frame
Day 0, recorded at time of physician reviewSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov