NCT07234539

Brief Summary

This study aims to evaluate the clinical feasibility of adopting artificial intelligence (AI)-based models to improve clinical management of thyroid cancer.

Trial Health

75
On Track

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Enrollment
76

participants targeted

Target at P50-P75 for not_applicable

Timeline
9mo left

Started Oct 2025

Geographic Reach
1 country

2 active sites

Status
enrolling by invitation

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

Study Progress53%
Oct 2025Apr 2027

First Submitted

Initial submission to the registry

September 29, 2025

Completed
3 days until next milestone

Study Start

First participant enrolled

October 2, 2025

Completed
2 months until next milestone

First Posted

Study publicly available on registry

November 18, 2025

Completed
1.4 years until next milestone

Primary Completion

Last participant's last visit for primary outcome

March 31, 2027

Expected
1 month until next milestone

Study Completion

Last participant's last visit for all outcomes

April 30, 2027

Last Updated

July 21, 2026

Status Verified

July 1, 2026

Enrollment Period

1.5 years

First QC Date

September 29, 2025

Last Update Submit

July 17, 2026

Conditions

Thyroid CancerLarge Language Models

Keywords

Thyroid Cancerlarge language modelsLLMsnatural language processingNLP

Outcome Measures

Primary Outcomes (1)

  • Efficiency

    The time required to complete reviewing one set of clinical notes is compared between intervention and non-intervention groups

    Between intervention group and non-intervention group. Cross-over in 4-26 weeks

Secondary Outcomes (2)

  • Accuracy of Cancer Staging and Risk Stratification by Participants Compared with Ground Truth across Intervention and Non-intervention Groups

    Between intervention group and non-intervention group. Cross-over in 4-26 weeks

  • Participants' Confidence in Cancer Staging and Risk Stratification as Assessed by a 0-10 Scale Questionnaire

    Between intervention group and non-intervention group. Cross-over in 4-26 weeks

Study Arms (2)

AI-enabled clinical assistant

EXPERIMENTAL

Participants will provide the caner staging and risk category of each thyroid cancer patient as well as the participants' confidence for the above diagnostic assessments with AI-enabled clinical assistant as the intervention. The AI assistant is powered by LLMs and comprises a clinical dashboard. The clinical dashboard displays the original clinical notes and summarizes cancer staging and risk category of each thyroid cancer patient generated from the backend processing of the clinical assistant. Supporting evidence from original clinical notes is also highlighted for participants' verification.

Other: AI-enabled clinical assistant

Manural chart review

NO INTERVENTION

Participants will provide the caner staging and risk category of each thyroid cancer patient as well as the participants' confidence for the above diagnostic assessments with manual chart review.

Interventions

AI-enabled clinical assistantOTHER

Participants will provide the caner staging and risk category of each thyroid cancer patient as well as the participants' confidence for the above diagnostic assessments with AI-enabled clinical assistant as the intervention. The AI assistant is powered by LLMs and comprises a clinical dashboard. The clinical dashboard displays the original clinical notes and summarizes cancer staging and risk category of each thyroid cancer patient generated from the backend processing of the clinical assistant. Supporting evidence from original clinical notes is also highlighted for participants' verification.

AI-enabled clinical assistant

Eligibility Criteria

Age18 Years+
Sexall
Healthy VolunteersYes
Age GroupsAdult (18-64), Older Adult (65+)

You may qualify if:

  • Consenting medical students
  • Consenting clinicians who are directly involved in the care of thyroid cancer patients, including endocrine surgeons, endocrinologists, oncologists, and pathologists.

You may not qualify if:

  • Medical students and clinicians who had reviewed the clinical notes or were involved in the processing of the clinical notes prior to the commencement of trial

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (2)

Department of Surgery, School of Clinical Medicine, The University of Hong Kong

Hong Kong, Hong Kong

Location

School of Public Health, The University of Hong Kong

Hong Kong, Hong Kong

Location

Related Publications (1)

  • Fung MMH, Tang EHM, Wu T, Luk Y, Au ICH, Liu X, Lee VHF, Wong CK, Wei Z, Cheng WY, Tai ICY, Ho JWK, Wong JWH, Lang BHH, Leung KSM, Wong ZSY, Wu JT, Wong CKH. Developing a named entity framework for thyroid cancer staging and risk level classification using large language models. NPJ Digit Med. 2025 Mar 1;8(1):134. doi: 10.1038/s41746-025-01528-y.

    PMID: 40025285RESULT

MeSH Terms

Conditions

Thyroid Neoplasms

Condition Hierarchy (Ancestors)

Endocrine Gland NeoplasmsNeoplasms by SiteNeoplasmsHead and Neck NeoplasmsEndocrine System DiseasesThyroid Diseases

Study Officials

  • King Ho Carlos Wong

    School of Public Health The University of Hong Kong

    PRINCIPAL INVESTIGATOR

  • Man Him Matrix Fung

    Department of Surgery, School of Clinical Medicine, The University of Hong Kong

    PRINCIPAL INVESTIGATOR

Study Design

Study Type
interventional
Phase
not applicable
Allocation
RANDOMIZED
Masking
SINGLE
Who Masked
OUTCOMES ASSESSOR
Purpose
HEALTH SERVICES RESEARCH
Intervention Model
CROSSOVER
Sponsor Type
OTHER
Responsible Party
PRINCIPAL INVESTIGATOR
PI Title
Honorary Associate Professor

Study Record Dates

First Submitted

September 29, 2025

First Posted

November 18, 2025

Study Start

October 2, 2025

Primary Completion (Estimated)

March 31, 2027

Study Completion (Estimated)

April 30, 2027

Last Updated

July 21, 2026

Record last verified: 2026-07

Data Sharing

IPD Sharing
Will share

Only anonymized IPD used in results publications will be shared so that re-identification of individuals is not possible.

Shared Documents
STUDY PROTOCOL, SAP, ICF, ANALYTIC CODE
Time Frame
The IPD and supporting information will be available upon the completion of study (anticipated date as 30 April 2027) with results dissemination or publication, and will remain unending until required of removal.
Access Criteria
The IPD and supporting information will be available with results dissemination and publication as documents uploads or attachment. Anyone who has access to the articles will be able to access all the documents.

Locations

HK(2)