RCT of NLP-Based Feedback for Improving SDM in Men With Localized Prostate Cancer (NLP RCT)

Natural Language Processing-Based Feedback to Improve Physician Risk Communication and Informed Shared Decision Making in Men With Clinically Localized Prostate Cancer

The purpose of the research is to assess the impact of a natural language processing + artificial intelligence (NLP+AI)-based risk communication feedback system to improve quality of risk communication of key tradeoffs during prostate cancer consultations among physicians and to improve patient decision making. In this cluster randomized trial, an evaluable 259 patients with newly diagnosed clinically localized prostate cancer will be cluster randomized within an evaluable 24 physicians to:

1. a control arm, in which patients will receive standard of care treatment consultations along with AUA-endorsed educational materials on treatment risks and benefits (for patients) and on SDM (for physicians) or
2. an experimental arm, in which patients and participating physicians will receive NLP+AI-based feedback on what was said about key tradeoffs within approximately 72 hours of the consultation to assist with decision making. Physicians will additionally be provided with grading of their risk communication for each visit based on an a priori defined framework for quality of risk communication and recommendations for improvement.

In both study arms, there will be an audio-recorded follow-up phone or video call between the physician and patient to allow for further discussion of risk and clarifying any areas of ambiguity, which will be qualitatively analyzed to see if areas of poor communication were rectified. After the follow-up phone call, patients and participating physicians will be asked to complete a very brief survey about their experience.

The study plans to test whether receiving NLP+AI-based feedback improves decisional conflict, shared decision making, and appropriateness of treatment choice over the standard of care in patients undergoing treatment consultations for prostate cancer. Study staff will also test whether providing feedback and grading of risk communication to physicians affects quality of physician risk communication, since providing feedback will promote more accountability for the quality of information provided to patients. The study will also analyze data from the control arm of the randomized controlled trial to understand variation in risk communication of key tradeoffs in relevant subgroups of tumor risk (low-, intermediate-, and high-risk), provider specialty (Urology, Radiation Oncology, Medical Oncology), and patient sociodemographics.

Study Overview

• Status: Recruiting
• Conditions: Prostate Cancer; Shared Decision Making; Risk Communication
• Intervention / Treatment: Other: NLP+AI Report

• Study Type: Interventional
• Enrollment (Estimated): 283
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Timothy Daskivich, MD; Phone Number: 310-423-4700; Email: Timothy.Daskivich@cshs.org
• Study Contact Backup: Name: Ella Tetrault, AB; Phone Number: 424-315-1311; Email: Ella.Tetrault@cshs.org

Study Locations

• United States
  • California
    • Los Angeles, California, United States, 90048
      • Recruiting
      • Cedars Sinai Medical Center

Participation Criteria

Eligibility Criteria

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

Description

Inclusion Criteria:

Physician Inclusion Criteria

(1) Physicians who typically counsel prostate cancer patients (Urology, Radiation Oncology, Medical Oncology)

Patient Inclusion Criteria

1. Patients undergoing initial treatment consultation for clinically localized prostate cancer;
2. Patients with upgraded prostate cancer on active surveillance considering conversion to definitive local therapy;
3. Ability to read and write in English.

Patient Exclusion Criteria:

1. Under 18 years of age;
2. Subjects with difficulty communicating or dementia;
3. Non-English speakers, given that our NLP-based tools cannot be used with languages other than English;
4. Patients with locally advanced or metastatic prostate cancer;
5. Patients who have already been treated for clinically localized prostate cancer.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Supportive Care
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: NLP-Based Feedback Arm	Other: NLP+AI Report; A NLP model will extract key content from consultations and AI (Chat GPT) will summarize that information. Reports including the top sentences by NLP probability for key content areas will be generated and will be provided to patients and providers within approximately 72 hours after each case. In both arms, a follow up phone call will allow for clarification any concepts that was inadequately communicated during the consultation. This call will be audio recorded and qualitatively assessed to determine whether deficiencies in risk communication observed in the consultation were rectified.
No Intervention: Standard of Care Arm; patients will receive standard of care treatment consultations along with AUA-endorsed educational materials on treatment risks and benefits (for patients) and on SDM (for physicians)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Decisional conflict	Decisional conflict is a patient-level outcome between intervention and control and will be measured using the validated Decisional Conflict Scale (DCS) questionnaire, where participants will list if they strongly agree, agree, neither, disagree, or strongly disagree with the provided statements	2-4 weeks (from diagnosis and enrollment through the completion of post feedback survey)
Shared decision-making	Shared decision making will be patient-reported and measured using the validated SDMP-4 questionnaire.	2-4 weeks (from diagnosis and enrollment through the completion of post feedback survey
Appropriateness of treatment choice	Appropriateness of treatment choice will be determined a priori based on previously published measures determined by treatment guidelines.	2-4 weeks (from diagnosis and enrollment through the completion of post feedback survey)
Quality of risk communication	Physician level outcome-that will measure the difference in composite quality of physician risk communication between the experimental and control arms. Quality of physician risk communication will be measured using a previously published hierarchical scale that is specific to communication of cancer prognosis, life expectancy, and treatment-related side effects.	6-9 months (post study analysis)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Improvement of risk communication	Physician level outcome- improvement of risk communication in areas of deficiency in follow up calls between doctors and patients in the experimental arm. All of this information will be assessed retrospectively by qualitative analysis of treatment consultation transcripts.	6-9 months (post study analysis)
Risk Perception and Patient Satisfaction	Patients will fill out a REDCap questionnaire assessing risk perception and patient satisfaction with the intervention.	6-9 months (post study analysis)

Collaborators and Investigators

• Sponsor: Cedars-Sinai Medical Center
• Collaborators: National Cancer Institute (NCI)

Study record dates

Study Major Dates

• Study Start (Actual): October 22, 2025
• Primary Completion (Estimated): May 1, 2029
• Study Completion (Estimated): December 1, 2029

Study Registration Dates

• First Submitted: February 14, 2025
• First Submitted That Met QC Criteria: February 26, 2025
• First Posted (Actual): March 4, 2025

Study Record Updates

• Last Update Posted (Actual): December 11, 2025
• Last Update Submitted That Met QC Criteria: December 5, 2025
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Keywords: communication; prostate cancer; artificial intelligence; risk; AI; NLP; decision; natural language processing; cluster; randomize; shared; physician risk; chatGPT
• Additional Relevant MeSH Terms: Urogenital Diseases; Genital Diseases; Genital Neoplasms, Male; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Genital Diseases, Male; Prostatic Diseases; Male Urogenital Diseases; Behavior; Prostatic Neoplasms; Communication
• Other Study ID Numbers: STUDY00003620; 1R01CA290559-01A1 (U.S. NIH Grant/Contract)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Concerns regarding identification of participating individuals with raw consultation transcripts.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No