Graves Disease, Hyperthyroidism/Thyrotoxicosis
Conditions
Keywords
Graves disease, Hyperthyroidism, Thyrotoxicosis, Artificial intelligence, Heart rate, SaMD, wearable device
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.
Detailed description
This is a single-center, prospective observational study designed to validate the performance of Glandy HYPER, a software medical device that analyzes sleep heart rate data from wearable devices in conjunction with thyroid function test (TFT) results to detect thyrotoxicosis. The study targets adults aged 22 or older with newly diagnosed or currently treated Graves' disease. Each participant will wear a smartwatch (Apple or Samsung, depending on their smartphone OS) to measure heart rate during sleep over a 12-week period. Blood samples for TFTs will be collected at four separate visits (baseline and at 4, 8, and 12 weeks). The primary endpoint is the F1 score between the investigational device's output and the diagnosis of thyrotoxicosis based on free T4 values. Secondary endpoints include sensitivity, specificity, and area under the curve (AUC) of the device's performance. Data from the wearable device and TFTs will be used to create multiple evaluation-reference data pairs per patient, enabling within-subject validation across different time points. The study does not involve any investigational treatment or alteration to standard care and is classified as non-significant risk (NSR). The output of the software device will not influence clinical decisions during the trial. The study also aims to assess the generalizability of the software's performance by comparing results from this U.S.-based cohort with prior studies conducted in Korea.
Interventions
DEVICEHeart rate-based AI software for detecting thyrotoxicosis
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.
Sponsors
THYROSCOPE INC.
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
22 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* 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.
Exclusion criteria
* 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.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| F1 Score for Detection of Thyrotoxicosis Using the Investigational Software | At weeks 4, 8, and 12 after baseline (Visit 2), up to 12 weeks total | 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. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity and Specificity of the Software in Detecting Thyrotoxicosis | At weeks 4, 8, and 12 after baseline (Visit 2), up to 12 weeks total | The sensitivity and specificity of the investigational AI software will be calculated by comparing its output to the diagnosis of thyrotoxicosis based on serum free T4 levels. Results will be computed for each evaluation-reference data pair and summarized across all participants, with 95% confidence intervals. |
| 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 | The AUC will be calculated to assess the diagnostic performance of the investigational software in distinguishing thyrotoxicosis from euthyroid and hypothyroid states, using free T4 levels as the reference. The AUC will be calculated per case and summarized across all evaluable cases. |
Countries
United States
Contacts
CONTACTJun An
CONTACTJae Hoon Moon, MD, PhD
PRINCIPAL_INVESTIGATORUmeshi Masharani, MD
University of California, San Francisco
Outcome results
None listed