Use and Acceptance of Large Language Models for Cancer Shared Decision-Making

Use and Acceptance of Large Language Models in Oncological Shared Decision-Making Among Patients, the Public, and Healthcare Professionals

This study examines how cancer patients, the general public, and healthcare professionals use and perceive large language models (such as ChatGPT) for health-related shared decision-making in oncology. A cross-sectional survey was conducted among 7,151 participants across 30 countries using a questionnaire developed and validated through a two-round Delphi process involving 44 experts. The study assessed current patterns of large language model use for health information, barriers to adoption including concerns about reliability and privacy, future expectations regarding these tools in shared decision-making, and demographic predictors of adoption. Participants were recruited through the Prolific platform between March and May 2025, with stratified sampling across three groups: cancer patients diagnosed within the past five years, general population members from the United States and United Kingdom, and licensed healthcare professionals with active patient contact.

Study Overview

• Status: Completed
• Conditions: Cancer; Artificial Intelligence; Shared Decision Making

Detailed Description

Shared decision-making is a collaborative process in which clinicians support patients in reaching treatment decisions. Despite its importance in oncology, structured shared decision-making remains uncommon in routine clinical practice. Large language models offer a new way for patients to access and understand medical information, yet little is known about how key stakeholders perceive and use these tools for health decisions.

This observational study used a sequential mixed-methods design combining Delphi consensus methodology with cross-sectional survey deployment. A 44-expert panel across eight domains (clinical artificial intelligence, technical development, oncology, psychology, epidemiology, patient advocacy, ethics, and legal expertise) developed and validated the assessment instrument through two Delphi rounds, achieving consensus on 89 items. The final instrument contained 52 quantitative items and 8 qualitative prompts, distinguishing between general and healthcare-specific large language model use.

The study recruited three cohorts: 2,316 cancer patients with self-reported diagnosis within five years, 2,000 general population members from the United States and United Kingdom, and 2,835 licensed healthcare professionals. Quality control included attention checks, completion time monitoring, consistency validation, and verification procedures, resulting in exclusion of 694 responses (8.8%) from an initial 7,845.

Primary analyses included chi-squared testing and ANOVA with Bonferroni correction, multivariable logistic regression with hierarchical model building to identify adoption predictors, and user segmentation through cross-tabulation combined with k-means clustering. The study was approved by the institutional review board of the Technical University of Munich (TUM2024-89-S-SB).

• Study Type: Observational
• Enrollment (Actual): 7151

Contacts and Locations

Study Locations

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

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Three cohorts recruited via the Prolific platform: cancer patients with a diagnosis within five years (n=2,316), general population members from the United States and United Kingdom (n=2,000), and licensed healthcare professionals with active patient contact (n=2,835). Stratified sampling applied quotas for age, gender, ethnicity, and education in the general population cohort.

Description

Inclusion Criteria:

• Age 18 years or older
• English language proficiency
• Regular internet access
• Registered on the Prolific research platform
• For cancer patient cohort: self-reported cancer diagnosis within the past five years
• For healthcare professional cohort: licensed healthcare practitioner with active patient contact
• For general population cohort: resident of the United States or United Kingdom

Exclusion Criteria:

• Failure on embedded attention check questions (4 checks)
• Survey completion time less than 5 minutes or greater than 60 minutes
• Straight-line responding pattern detected by consistency validation algorithms
• Failure of cohort verification procedures

Study Plan

How is the study designed?

Number of groups / cohorts

3

Cohorts and Interventions

Group / Cohort
Cancer Patients; Adults aged 18 years or older with a self-reported cancer diagnosis within the past five years, recruited through the Prolific platform with verification through screening questions about diagnosis date, cancer type, and treatment status. n=2,316.
General Population; Adults aged 18 years or older from the United States and United Kingdom with no specific health condition requirement, recruited through the Prolific platform with stratified sampling quotas for age, gender, ethnicity, and education. n=2,000.
Healthcare Professionals; Licensed healthcare practitioners aged 18 years or older with active patient contact, including physicians and nursing staff, recruited through the Prolific platform from the United States, United Kingdom, and 28 additional countries. n=2,835.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Healthcare-specific large language model usage rate	Proportion of participants reporting use of large language models specifically for health-related information, measured on a 5-point Likert frequency scale and dichotomised as use versus non-use.	At time of survey completion (single assessment, March-May 2025)
Future belief in large language model improvement of shared decision-making	Proportion of participants believing that large language models will improve the quality of shared decision-making in oncology, assessed via Likert-scale response.	At time of survey completion (single assessment, March-May 2025)
Barriers to large language model adoption	Prevalence of concerns regarding large language model use for health decisions, including reliability concerns, privacy concerns, and preference for human interaction, each assessed as binary (present or absent).	At time of survey completion (single assessment, March-May 2025)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Independent predictors of large language model adoption	Odds ratios from hierarchical multivariable logistic regression identifying demographic and health-related predictors of healthcare-specific large language model acceptance, including age, sex, ethnicity, education, digital literacy, and confidence in understanding health information.	At time of survey completion (single assessment, March-May 2025)
User segmentation	Distribution of participants across data-driven user segments derived from cross-tabulation of current usage with perceived benefit, refined through k-means clustering: potential adopters, believing users, resistant non-users, and sceptical users.	At time of survey completion (single assessment, March-May 2025)
Healthcare professional recommendation patterns	Proportion of healthcare professionals who recommend large language models to patients for health information, compared with their personal use rate.	At time of survey completion (single assessment, March-May 2025)

Collaborators and Investigators

• Sponsor: Technical University of Munich

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2025
• Primary Completion (Actual): May 1, 2025
• Study Completion (Actual): May 1, 2025

Study Registration Dates

• First Submitted: April 6, 2026
• First Submitted That Met QC Criteria: April 6, 2026
• First Posted (Actual): April 13, 2026

Study Record Updates

• Last Update Posted (Actual): April 30, 2026
• Last Update Submitted That Met QC Criteria: April 26, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: Oncology; Shared Decision Making; Patient Acceptance; Large Language Models
• Additional Relevant MeSH Terms: Neoplasms
• Other Study ID Numbers: LLM-SDM-2025

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data will not be shared publicly due to data protection regulations. The anonymised survey data supporting the findings of this study are available from the corresponding author upon reasonable request.

Drug and device information, study documents

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