LLMs Improve Patient Understanding of Ultrasound Reports

Large Language Model Simplification of Ultrasound Reports Improves Patient Understanding

This multicenter, patient-blinded, controlled evaluation assessed whether expert-reviewed artificial intelligence (AI)-simplified ultrasound reports improved patient- or guardian-reported understanding and reading experience compared with standard ultrasound reports. Routine ultrasound reports were completed through existing clinical processes. After completion of the routine report, participants were assigned to view either the standard report or an expert-reviewed plain-language version generated with a large language model workflow.

The simplified report was intended only as a patient-facing communication aid. It did not replace the standard clinical report and did not alter ultrasound acquisition, diagnostic interpretation, treatment decisions, follow-up, or subsequent clinical management. Patient- or guardian-reported outcomes included cognitive workload, comprehension, report perception, and reading time. Expert review assessed whether AI-generated simplified reports preserved source meaning and identified factual errors, omissions, or unsupported additions before patient presentation.

Study Overview

• Status: Active, not recruiting
• Conditions: Patient Understanding of Ultrasound Reports
• Intervention / Treatment: Other: Standard ultrasound report presentation; Other: Expert-reviewed AI-simplified ultrasound report presentation

Detailed Description

Radiology and ultrasound reports are primarily written for communication among clinicians and often contain technical terminology, compressed syntax, measurements, uncertainty statements, and diagnostic language that may be difficult for patients to interpret. Patient access to reports through electronic portals may improve transparency, but access alone does not ensure comprehension. This study evaluated a bounded AI-assisted communication workflow designed to translate completed ultrasound reports into patient-facing plain language while preserving the meaning of the original clinical report.

The study was conducted at three participating centers: Sichuan Cancer Hospital and Institute, Sichuan Provincial Hospital of Integrated Traditional Chinese and Western Medicine, and The First People's Hospital of Liangshan Yi Autonomous Prefecture. Eligible participants were patients receiving an ultrasound report at a participating center. For participants younger than 18 years, a legal guardian provided consent, read the report, and completed the questionnaire.

Routine ultrasound reports were first completed through standard clinical processes. The study workflow began only after the routine report had been finalized. A built-in random-number function determined whether the participant or guardian viewed the standard report or an expert-reviewed AI-simplified report. Participants or guardians were not informed which presentation format they received. The standard clinical report remained the authoritative diagnostic report and the sole report used for clinical communication and care.

For the AI-simplified format, the completed routine report text was submitted to a large language model workflow. The prompt instructed the model to preserve all findings, avoid new diagnoses or recommendations, explain terminology in plain language, and maintain uncertainty expressed in the source report. Before presentation to participants or guardians, the generated simplified report was reviewed against the routine report by paired ultrasound physicians at each center. Experts corrected inaccuracies, omissions, or unsupported additions before patient exposure. The workflow did not generate orders, referrals, follow-up intervals, medication instructions, or treatment recommendations, and no model output was written back into the diagnostic report.

After reading the assigned report format, participants or guardians completed a questionnaire evaluating their immediate reading experience. Patient- or guardian-reported outcomes included cognitive workload, text comprehension, report perception, and approximate reading time. Cognitive workload included mental demand, frustration, and effort, with lower scores indicating a more favorable experience. Comprehension included clarity, readability, and comprehensibility. Report perception included helpfulness, informativeness, and trust, with higher scores indicating more favorable responses.

Expert assessment of AI-generated simplified reports included factual errors, important omissions, unsupported additions, terminology simplification, clinical usefulness, and overall quality. Paired expert ratings were resolved into consensus records for report-level safety summaries. The primary purpose of expert review was to determine whether the AI-generated patient-facing explanation preserved the source meaning and to define the residual need for human oversight before such reports are shown to patients.

The prespecified analysis population included completed evaluations with recorded center and presentation format. Outcomes were analyzed using descriptive statistics, between-format comparisons, and adjusted models including presentation format, age, sex, education, and center. The study was approved by the Medical Ethics Committee of Sichuan Cancer Hospital, and written informed consent was obtained from adult participants or from legal guardians of minors.

• Study Type: Interventional
• Enrollment (Estimated): 660
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Sichuan
    • Chengdu, Sichuan, China, 610041
      • Sichuan Cancer Hospital

Participation Criteria

Eligibility Criteria

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

Description

Inclusion Criteria:

• Patients receiving an ultrasound report at a participating center. Adult participants able to provide written informed consent. For participants younger than 18 years, a legal guardian able to provide written informed consent, read the assigned report, and complete the questionnaire.

Participants or legal guardians able to read one assigned report presentation format and complete the study questionnaire immediately after reading.

Exclusion Criteria:

• Refusal or inability to provide written informed consent by the adult participant or legal guardian.

Inability of the participant or legal guardian to read the assigned report presentation format or complete the questionnaire.

Incomplete evaluation, including missing responses to any of the nine rating items or the reading-time item.

Missing key study information required for analysis, including participating center or assigned report presentation format.

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
Active Comparator: Standard ultrasound report; Participants or legal guardians viewed the standard ultrasound report generated through routine clinical reporting processes	Other: Standard ultrasound report presentation; Presentation of the completed routine ultrasound report to the participant or legal guardian
Experimental: Expert-reviewed AI-simplified ultrasound report; Participants or legal guardians viewed a plain-language ultrasound report generated by an AI workflow after completion of the routine report and reviewed by ultrasound physicians before presentation	Other: Expert-reviewed AI-simplified ultrasound report presentation; Presentation of a patient-facing plain-language ultrasound report generated by an AI workflow and reviewed by ultrasound physicians before participant or guardian exposure. The intervention did not alter ultrasound acquisition, diagnostic interpretation, treatment decisions, follow-up, or clinical management

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Text comprehension composite score	Participant- or guardian-reported text comprehension after reading the assigned ultrasound report format. The composite score was calculated as the arithmetic mean of three seven-point questionnaire items assessing clarity, readability, and comprehensibility. Higher scores indicate better comprehension.	Immediately after reading the assigned report

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Cognitive workload composite score	Participant- or guardian-reported cognitive workload after reading the assigned ultrasound report format. The composite score was calculated as the arithmetic mean of three seven-point items assessing mental demand, frustration, and effort. Lower scores indicate a more favorable reading experience.	Immediately after reading the assigned report
Report perception composite score	Participant- or guardian-reported perception of the assigned ultrasound report format. The composite score was calculated as the arithmetic mean of three seven-point items assessing helpfulness, informativeness, and trust. Higher scores indicate more favorable report perception.	Immediately after reading the assigned report
Reading time	Participant- or guardian-reported approximate time spent reading the assigned ultrasound report format.	Immediately after reading the assigned report

Collaborators and Investigators

• Sponsor: Lu Wang

Study record dates

Study Major Dates

• Study Start (Actual): June 1, 2026
• Primary Completion (Estimated): June 20, 2026
• Study Completion (Estimated): June 30, 2026

Study Registration Dates

• First Submitted: June 9, 2026
• First Submitted That Met QC Criteria: June 12, 2026
• First Posted (Actual): June 15, 2026

Study Record Updates

• Last Update Posted (Actual): June 15, 2026
• Last Update Submitted That Met QC Criteria: June 12, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: Artificial intelligence; Health literacy; Patient communication; Large language model; Plain language; Ultrasound reports; Report comprehension
• Other Study ID Numbers: 2026-AI-US-report

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data will not be shared because the study involves sensitive patient-level clinical data, and the current informed consent and ethics approval do not include permission for external IPD sharing. Study results will be reported in aggregate form.

Drug and device information, study documents

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