Evaluating an AI Tool for Detecting Thyrotoxic States

NCT07017907 | Not Yet Recruiting FDA Device

• 1 other identifier: 01-01-UCSF-001
• Study Type: observational
• Target: 15
• Locations: 0 countries
• Sites: N/A

Brief Summary

This observational study aims to evaluate the performance of a software-based medical device, Glandy HYPER, in detecting the thyrotoxic state in patients with hyperthyroidism. The device utilizes heart rate data collected from commercially available wearable devices and compares it with thyroid function test results. The study will enroll patients diagnosed with Graves' disease, monitoring their heart rate during sleep and correlating these measurements with free T4 levels obtained through serial blood testing. No investigational device output will be disclosed to participants, and the study will not alter standard clinical care.

Conditions

Graves Disease; Hyperthyroidism/Thyrotoxicosis

Keywords

Graves disease; Hyperthyroidism; Thyrotoxicosis; Artificial intelligence; Heart rate; SaMD; wearable device

Outcome Measures

Primary Outcomes (1)

• F1 Score for Detection of Thyrotoxicosis Using the Investigational Software

  The F1 score will be calculated to evaluate the performance of the AI-based investigational software in detecting thyrotoxic states. The device's output, derived from wearable heart rate data and reference data, will be compared against the diagnosis based on serum free T4 concentration at each time point. Each participant contributes multiple data pairs (evaluation-reference combinations) based on serial visits (V2-V5), and the F1 score will be calculated for each case and summarized across all cases.

  At weeks 4, 8, and 12 after baseline (Visit 2), up to 12 weeks total

Secondary Outcomes (2)

• Sensitivity and Specificity of the Software in Detecting Thyrotoxicosis

  At weeks 4, 8, and 12 after baseline (Visit 2), up to 12 weeks total

• Area Under the Receiver Operating Characteristic Curve (AUC) for Thyrotoxicosis Detection

  At weeks 4, 8, and 12 after baseline (Visit 2), up to 12 weeks total

Study Arms (1)

Glandy HYPER Validation Cohort

articipants diagnosed with Graves' disease who are either newly diagnosed or currently under treatment. All participants will wear a commercially available smartwatch (Apple or Samsung) to measure sleep heart rate, and undergo thyroid function testing (free T4 and TSH) at baseline and follow-up visits over 12 weeks. No therapeutic intervention will be applied, and data from wearable devices will be used solely for observational performance evaluation of the investigational software.

Device: Heart rate-based AI software for detecting thyrotoxicosis

Interventions

Heart rate-based AI software for detecting thyrotoxicosis DEVICE

A software-based investigational medical device that uses artificial intelligence to detect the thyrotoxic state in patients with hyperthyroidism. The device analyzes resting heart rate data collected from wearable devices along with thyroid function test results (free T4 and TSH). The device is not FDA-approved and will be used solely for observational performance evaluation without influencing clinical care.

Glandy HYPER Validation Cohort

Eligibility Criteria

• Age: 22 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adults aged 22 years and older with a confirmed diagnosis of Graves' disease, including both newly diagnosed and currently treated individuals. Participants will be recruited from a single center in the United States. All participants must be able to use a wearable device and provide informed consent.

You may qualify if:

• Adults aged 22 years or older, regardless of sex.
• Individuals who are newly diagnosed with Graves' disease or currently undergoing treatment for it.
• Individuals who have received sufficient explanation about the investigational software and are able to use it appropriately.
• Individuals who voluntarily agree to participate in the study and have signed informed consent, either directly or via a legally authorized representative.

You may not qualify if:

• Individuals with cardiac conditions such as arrhythmia or heart failure.
• Individuals taking medications that significantly affect heart rate, including antiarrhythmics or antihistamines. (Intermittent short-acting beta-blockers are allowed.)
• Pregnant or breastfeeding individuals, or those planning pregnancy during the study period or not using appropriate contraception.
• Individuals with significant comorbidities that interfere with follow-up or study compliance.
• Individuals with severe psychiatric disorders, substance use disorder, or alcohol dependence.
• Individuals deemed ineligible at the discretion of the investigator for safety or ethical concerns.

Sponsors & Collaborators

• THYROSCOPE INC.: lead

Related Publications (5)

• Shin K, Kim J, Park J, Oh TJ, Kong SH, Ahn CH, Moon JH, Kim MJ, Moon JH. A machine learning-assisted system to predict thyrotoxicosis using patients' heart rate monitoring data: a retrospective cohort study. Sci Rep. 2023 Nov 30;13(1):21096. doi: 10.1038/s41598-023-48199-x.

  PMID: 38036639 BACKGROUND

• Kim KH, Lee J, Ahn CH, Yu HW, Choi JY, Lee HY, Lee WW, Moon JH. Association between Thyroid Function and Heart Rate Monitored by Wearable Devices in Patients with Hypothyroidism. Endocrinol Metab (Seoul). 2021 Oct;36(5):1121-1130. doi: 10.3803/EnM.2021.1216. Epub 2021 Oct 21.

  PMID: 34674500 BACKGROUND

• Steinberger E, Pilz S, Trummer C, Theiler-Schwetz V, Reichhartinger M, Benninger T, Pandis M, Malle O, Keppel MH, Verheyen N, Grubler MR, Voelkl J, Meinitzer A, Marz W. Associations of Thyroid Hormones and Resting Heart Rate in Patients Referred to Coronary Angiography. Horm Metab Res. 2020 Dec;52(12):850-855. doi: 10.1055/a-1232-7292. Epub 2020 Sep 4.

  PMID: 32886945 BACKGROUND

• Griffith ML, Bischoff LA, Baum HBA. Approach to the Patient With Thyrotoxicosis Using Telemedicine. J Clin Endocrinol Metab. 2020 Aug 1;105(8):dgaa373. doi: 10.1210/clinem/dgaa373.

  PMID: 32525973 BACKGROUND

• Lee JE, Lee DH, Oh TJ, Kim KM, Choi SH, Lim S, Park YJ, Park DJ, Jang HC, Moon JH. Clinical Feasibility of Monitoring Resting Heart Rate Using a Wearable Activity Tracker in Patients With Thyrotoxicosis: Prospective Longitudinal Observational Study. JMIR Mhealth Uhealth. 2018 Jul 13;6(7):e159. doi: 10.2196/mhealth.9884.

  PMID: 30006328 BACKGROUND

Biospecimen

Retention: SAMPLES WITHOUT DNA

Serum samples obtained from venous blood draws will be retained for thyroid function testing, specifically for the measurement of free T4 and TSH levels. Each sample will be centrifuged to isolate serum and stored at ≤ -70°C until analysis. No genetic or genomic testing will be performed on the retained samples.

MeSH Terms

Conditions

Graves Disease; Hyperthyroidism; Thyrotoxicosis

Condition Hierarchy (Ancestors)

Exophthalmos; Orbital Diseases; Eye Diseases; Goiter; Thyroid Diseases; Endocrine System Diseases; Autoimmune Diseases; Immune System Diseases

Study Officials

• Umeshi Masharani, MD

  University of California, San Francisco

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Jun An

CONTACT

‭+82 10-2849-0041‬; jun.an@thyroscope.com

Jae Hoon Moon, MD, PhD

CONTACT

+82-10-5105-9815; jaehoon.moon@thyroscope.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 12 Weeks
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 4, 2025
• First Posted: June 12, 2025
• Study Start: July 1, 2025
• Primary Completion (Estimated): June 30, 2026
• Study Completion (Estimated): December 31, 2026
• Last Updated: June 12, 2025

Record last verified: 2025-06

Data Sharing

• IPD Sharing: Will not share