Implementing AI-Assisted, Patient-Friendly Imaging Report Summaries to Enhance Oncology Care Delivery

The implementation of the AI-assisted radiology summary tool into clinical workflows is being conducted as part of a standard-of-care quality improvement (QI) initiative at UW Health. The evaluation of this tool's impact via structured feedback from patients and providers is being undertaken as a prospective research study.

Study Overview

• Status: Recruiting
• Conditions: Oncology

Detailed Description

Patient groups: Mixed-method approach to evaluate patient understanding of, and anxiety about, imaging results and communication experience regarding the results before and after implementation of AI-assisted, patient-friendly imaging report summaries that accompany the imaging results.

Provider group: Quasi-experimental staircase approach to sequentially roll out the tool to three provider cohorts. All hematology/oncology and gynecology oncology attending providers will be randomized by disease group into three relatively similar-sized cohorts based on group-level scan volumes, regardless of individual provider characteristics or communication style. Subsequent cohorts will be added every two months.

Surveys will be the main method of feedback collection at baseline and after implementation of the AI-assisted, patient-friendly imaging report summaries. Interviews will be conducted in a small subset of subjects.

Primary Objective:

• To evaluate patient comprehension of, and anxiety about, imaging results and communication experience regarding the results before and after implementation of AI-assisted, patient-friendly imaging report summaries that accompany the imaging results.

Secondary Objective(s):

• Patient Baseline Survey Objective: To evaluate comprehension of, and anxiety about, imaging results and communication experience regarding the results before the implementation of the AI-assisted, patient-friendly imaging report summaries that accompany the imaging results.
• Patient Summary Feedback Survey Objective: To evaluate comprehension of, and anxiety about, imaging results and communication experience regarding the results after the implementation of the AI-assisted, patient-friendly imaging report summaries that accompany the imaging results.
• Patient Interview Objectives: To understand the imaging result communication process from the patient's perspective.
• Provider Surveys Objective: The Baseline Survey will assess communication habits and preferences (frequency, method, timing), and perceived impact of the AI-Assisted, Patient-Friendly Imaging Report Summaries on clinical workload, and the Post-Implementation Surveys will evaluate changes in workload perception, satisfaction with the AI-Assisted, Patient-Friendly Imaging Report Summaries, the effectiveness of scan result communication with patients, and attitudes toward the use of AI-assisted material in patient care.

• Study Type: Observational
• Enrollment (Estimated): 2000

Contacts and Locations

• Study Contact: Name: Supportive Oncology; Phone Number: 608-263-6002; Email: supportiveoncology@uwcarbone.wisc.edu

Study Locations

• United States
  • Wisconsin
    • Madison, Wisconsin, United States, 53792
      • Recruiting
      • UW Health

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Cancer patients undergoing imaging studies as part of their routine clinical care at UW Health and providers who have access to the scan summary tool.

Description

Inclusion Criteria (Patient Participants):

• Age 18 years or older
• Having a current or prior cancer diagnosis (any cancer type)
• Has active access to the UW Health MyChart patient portal.
• Receiving care at UW Health within the Division of Hematology, Medical Oncology and Palliative Care or Department of Gynecologic Oncology.
• Undergoing imaging studies (such as CT, MRI, or PET scans) as part of routine cancer care.
• Willing and able to complete electronic REDCap surveys.
• For interview participation: willing to participate in a 30-45-minute phone or video interview.

Inclusion Criteria (Provider Participants): Cancer care providers will be eligible to participate in this study if they meet all of the following criteria:

• Faculty physician (MD or DO) practicing in the Division of Hematology, Medical Oncology and Palliative Care or Department of Gynecologic Oncology at UW Health.
• Involved in reviewing, discussing, or sharing imaging results with patients.
• Planned to gain access to the AI-assisted, patient-friendly imaging summary tool as part of clinical implementation.
• Willing and able to complete electronic surveys or participate in a brief interview (~30 minutes).

Exclusion Criteria (Patients):

• Are unable to provide informed consent due to cognitive impairment or other limitations, as determined by the clinical or study team.
• Enrolled in an active interventional clinical trial. Patients on biospecimen, registry, or non-interventional studies are eligible.
• For the Patient Interview group only: Patients with radiographic disease progression will be excluded.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
Patient Participants; Patient Baseline Survey (pre-implementation, at least 330 participants, up to 1900); Patient Interviews (10-20 participants); Patient Summary Feedback Survey (post-implementation, at least 330 participants, up to 1900)
Provider Participants; Provider Surveys (baseline, 1 month and 3 month post-implementation, 60 participants); Provider Interviews (up to 20 participants)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of Patient Participants who report the information presented in their results is "Somewhat easy to understand" or "Very easy to understand" when reviewed by themselves	Baseline data collected in a 10-15 minute survey from patient participants pre-implementation and in a 10-15 minute survey from patient participants post-implementation.	up to 15 minutes
Perceived impact of scan-result-related patient queries on Provider Participant workload	Scored from 1 (no impact) to 5 (very frequently), higher scores indicate higher impact on workload. Data collected at baseline (pre-implementation) and 3 months (post-implementation).	baseline, 3 months

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of Patient Participants who report that reviewing scans increases their anxiety	Baseline data collected in a 10-15 minute survey from patient participants pre-implementation and in a 10-15 minute survey from patient participants post-implementation.	up to 15 minutes
Proportion of Patient Participants who report that they were "somewhat" or "very" satisfied with how scan results were shared and explained	Baseline data collected in a 10-15 minute survey from patient participants pre-implementation and in a 10-15 minute survey from patient participants post-implementation.	up to 15 minutes
Proportion of Patient Participants who report that they "almost always" or "often" contact their provider to ask questions regarding their scan results prior to their follow-up visit	Baseline data collected in a 10-15 minute survey from patient participants pre-implementation and in a 10-15 minute survey from patient participants post-implementation.	up to 15 minutes
Provider Participant-reported frequency of scan-result-related patient queries	Scored from 1 (never) to 5 (very frequently), higher scores indicate higher frequency. Data collected at baseline (pre-implementation) and 3 months (post-implementation).	baseline, 3 months

Collaborators and Investigators

• Sponsor: University of Wisconsin, Madison
• Investigators: Principal Investigator: Hamid Emamekhoo, MD, UW School of Medicine and Public Health

Study record dates

Study Major Dates

• Study Start (Actual): February 1, 2026
• Primary Completion (Estimated): January 1, 2027
• Study Completion (Estimated): January 1, 2027

Study Registration Dates

• First Submitted: April 8, 2026
• First Submitted That Met QC Criteria: April 8, 2026
• First Posted (Actual): April 15, 2026

Study Record Updates

• Last Update Posted (Actual): April 30, 2026
• Last Update Submitted That Met QC Criteria: April 28, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: Imaging; Artificial Intelligence; Radiology; AI; Patient Care; Patient Communication; Summary Reports
• Additional Relevant MeSH Terms: Neoplasms
• Other Study ID Numbers: 2025-1716; UW25122 (Other Identifier: OnCore ID); SMPH/DOM Hemato Med Onc (Other Identifier: UW Madison); Protocol Version 4/9/26 (Other Identifier: UW Madison)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

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