Recruiting OBSERVATIONAL NCT07017907

AI medical trial: detecting thyrotoxicosis from consumer-wearable heart rate with AI (Thyroscope, Glandy HYPER)

THYROSCOPE INC. Updated 2026-06-01

An observational study evaluating whether the AI software device "Glandy HYPER" can detect a thyrotoxic state in hyperthyroidism (Graves' disease) using heart-rate data from commercial wearables, correlated with thyroid function tests (free T4).

Trial overview (primary data)

  • StatusRecruiting
  • ConditionsGraves Disease, Hyperthyroidism/Thyrotoxicosis
  • InterventionsDEVICE: Heart rate-based AI software for detecting thyrotoxicosis
  • SponsorTHYROSCOPE INC.
  • Target enrollment15 participants
  • Period2026-01-09 〜 2026-12-31

Key points

  • Detects thyrotoxicosis (Graves' disease) from consumer-wearable heart rate + AI
  • Evaluates the software medical device "Glandy HYPER" (observational)
  • Correlates sleep heart rate with thyroid function tests (free T4)
  • Device output is not disclosed to participants; standard care is unchanged
  • Small early-stage study (15 participants), 2026, recruiting
  • Heart rate during sleep is measured on a consumer wearable and correlated with free T4 from serial sampling, with output withheld from participants.

1Hyperthyroidism meets wearables

Thyroscope's observational study (NCT07017907) evaluates an AI software medical device, "Glandy HYPER," that uses heart rate from a commercial wearable to detect an overactive thyroid (thyrotoxicosis).

2Evaluated as software as a medical device

Per the registry summary, this observational study aims to evaluate the performance of the software-based medical device "Glandy HYPER" in detecting the thyrotoxic state in patients with hyperthyroidism. The device uses heart-rate data from commercially available wearables and compares it with thyroid function test results.

The study enrolls patients diagnosed with Graves' disease, monitoring their heart rate during sleep and correlating it with serial free-T4 levels obtained by blood testing. Importantly, no investigational device output is disclosed to participants, and the study does not alter standard clinical care. Target enrollment 15; 2026; recruiting.

3The digital biomarker idea

In hyperthyroidism (e.g., Graves' disease), metabolism is elevated, causing palpitations, rapid heart rate, and weight loss; worsening thyrotoxicosis strains the heart. Because heart rate can be measured continuously and easily with consumer smartwatches, combining it with AI to flag signs of a thyrotoxic state could help with deciding when to seek care or with monitoring. Note this is an early, small (15-participant) observational study.

4Matching everyday recordings against laboratory values

The idea of a digital biomarker is to catch signs of a disease state from signals available in daily life. Here, how that matching is done is written into the design.

  1. 1Measure with a consumer wearableHeart rate is monitored continuously during sleep
  2. 2AI analyses itSigns of a thyrotoxic state are detected
  3. 3Match against blood testsCorrelated with free T4 values from serial blood sampling
  4. 4Do not disclose the resultThe device output is withheld from participants and standard care is unchanged

In hyperthyroidism metabolism accelerates, producing palpitations, tachycardia and weight loss. Heart rate can be measured continuously and easily on a consumer smartwatch, so combining that with AI to catch signs of a thyrotoxic state could help with when to seek care and with follow-up. This is an early observational study targeting 15 cases.

Why it matters

Consumer wearables plus AI as "digital biomarkers" to flag disease signs is a globally watched area. As smartwatch health use spreads, such studies show how their validity is being tested (note this is an early, small study).

FAQ

What is thyrotoxicosis?
An overactive-thyroid state with excess thyroid hormone, causing palpitations, rapid heart rate, and weight loss. Graves' disease is a common cause.
Can a smartwatch diagnose it?
This is an early observational study (15 participants) evaluating whether heart rate + AI can flag signs. It is not a replacement for diagnosis.

Sources (primary)

Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.

#Medical AI#Clinical trial#Wearable#Thyroid#Digital biomarker#Heart rate
Disclaimer: This site independently summarizes and classifies information based on official data sources. Always verify the latest and accurate information with the official sources. Content on finance, health, legal, and security is information, not advice. This site is not an official website of the U.S. government.