Graves Ophthalmopathy, Thyroid Associated Ophthalmopathies, Thyroid Eye Disease (TED)
Conditions
Keywords
Thyroid eye disease, TED, Graves orbitopathy, Artificial intelligence, Smartphone, Self-monitoring, Clinical Activity Score, CAS, Exophthalmometry, MRD1, MRD2, Remote monitoring, Digital health, Telemedicine
Brief summary
This prospective observational study evaluates the feasibility and clinical utility of a smartphone-based artificial intelligence (AI) self-monitoring system in adults with thyroid eye disease (TED) undergoing non-surgical treatment. Eligible participants will use their own smartphones and the study application (Glandy) to perform at least weekly home monitoring consisting of a symptom questionnaire (diplopia, pain on visual analog scale) and a standardized frontal facial photograph. AI-derived outputs (Glandy CAS, Glandy EXO, Glandy LID) obtained at routine clinic visits will be compared with standard clinician assessments (CAS total score, Hertel exophthalmometry, MRD1/MRD2). AI outputs will not be used for real-time clinical decision-making during the study.
Detailed description
Thyroid eye disease (TED) is an autoimmune inflammatory disorder most commonly associated with Graves' disease. Clinical manifestations include conjunctival injection, eyelid swelling, eyelid retraction, proptosis, diplopia, and altered ocular appearance. TED typically progresses through an active inflammatory phase of approximately 6-12 months before transitioning to a relatively inactive phase, although interval worsening may occur. Because treatment response can change dynamically, timely assessment of disease activity and severity is important for monitoring. In current practice, TED activity and severity are primarily assessed during in-person visits using the Clinical Activity Score (CAS), Hertel exophthalmometry, and eyelid measurements (MRD1/MRD2). These assessments are episodic and may not capture interval change between visits. Recent advances in AI have enabled image-based quantification of TED-related features from facial or periocular photographs. The AI-based monitoring system evaluated here has three analytic components: Glandy CAS (CAS-related outputs from photographs + symptom input), Glandy EXO (image-based exophthalmometric estimate), and Glandy LID (eyelid-related parameters including MRD measurements). This prospective observational study will enroll approximately 200 adults with TED scheduled to initiate non-surgical treatment (intravenous methylprednisolone, oral corticosteroids, radiotherapy, or biologic therapy). Participants will perform at least weekly home-based self-monitoring (symptom entry + standardized frontal facial image) using their own smartphones and the study application. Baseline and end-of-treatment data will be required. At routine clinic visits, app-based image capture and symptom entry will also be performed to create clinic-matched assessments; AI-derived outputs will be compared with clinician-assessed TED parameters obtained the same day. At least two clinic-matched assessments per participant will be required for longitudinal evaluation. AI-generated outputs will not be used for real-time clinical decision-making.
Interventions
DEVICESmartphone-based AI self-monitoring application (Glandy CAS/EXO/LID)
A smartphone application through which participants complete a symptom questionnaire (diplopia; pain by visual analog scale) and capture a standardized frontal facial photograph at least weekly during the treatment course, and additionally at each routine clinic visit. Submitted images are transmitted to a central analysis system for AI-based processing that generates three analytic outputs: * Glandy CAS - CAS-related output derived from periocular signs and symptom input * Glandy EXO - image-based exophthalmometric estimate (surrogate of Hertel) * Glandy LID - eyelid-related parameters including MRD1/MRD2 equivalents AI outputs are used for research analysis only and are NOT returned to the treating clinician for real-time decision-making during the study.
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 19 years or older with a clinical diagnosis of thyroid eye disease (TED). * Patients with TED scheduled to initiate active non-surgical treatment, including but not limited to intravenous methylprednisolone, oral corticosteroids, radiotherapy, or biologic therapy. * Able to undergo baseline clinical assessment prior to initiation of the planned treatment course and expected routine follow-up evaluation during treatment, including an end-of-treatment assessment. * Able and willing to use their own smartphone to complete the study application-guided symptom questionnaire and capture standardized frontal facial images throughout the study period. * Willing to perform at least weekly home-based image capture and symptom reporting during the treatment course. * Able to participate in routine in-person follow-up visits and expected to provide at least two clinic-matched assessments, including baseline and at least one post-baseline assessment. * Voluntarily provides written informed consent to participate in the study.
Exclusion criteria
* Severe eyelid deformities, facial deformities, or other facial/periocular conditions that may interfere with standardized image acquisition or reliable AI-based image analysis. * Unable to use the study application or smartphone-based image capture procedure adequately for protocol-required self-monitoring. * Undergoing or planning to undergo surgical treatment for TED as the primary treatment modality during the study period. * History of ocular, eyelid, or orbital surgery within 3 months prior to enrollment. * Any medical, psychiatric, cognitive, or other condition that, in the investigator's judgment, may compromise protocol compliance, study participation, or data integrity. * Any other condition that the investigator judges to make the patient inappropriate for participation.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Agreement between Glandy CAS and clinician-assessed CAS total score | At each clinic-matched visit (baseline through end-of-treatment, up to 12 months) | Agreement between AI-derived Clinical Activity Score (Glandy CAS) and clinician-assessed CAS total score at clinic-matched visits, using intraclass correlation coefficient (ICC), correlation analysis, and Bland-Altman analysis. |
| Agreement between Glandy EXO and Hertel exophthalmometry | At each clinic-matched visit (baseline through end-of-treatment, up to 12 months) | Agreement between AI-derived image-based exophthalmometric estimate (Glandy EXO, mm) and clinician-measured Hertel exophthalmometry absolute value (mm) at clinic-matched visits, using ICC, correlation, and Bland-Altman analysis. |
| Agreement between Glandy LID and clinician-measured MRD1/MRD2 | At each clinic-matched visit (baseline through end-of-treatment, up to 12 months) | Agreement between AI-derived eyelid parameters (Glandy LID: MRD1 and MRD2 equivalents, mm) and clinician-measured MRD1 and MRD2 (mm) at clinic-matched visits, using ICC, correlation, and Bland-Altman analysis. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Longitudinal change in AI-derived TED parameters | Weekly home monitoring from baseline to end-of-treatment (up to 12 months) | Descriptive longitudinal change in Glandy CAS, Glandy EXO, and Glandy LID obtained from serial home-monitoring data during the non-surgical treatment course. |
| Concordance between AI-derived longitudinal trends and interval clinical change | From baseline to end-of-treatment (up to 12 months) | Concordance between longitudinal AI-derived parameter trends and interval clinical change observed at routine follow-up, analyzed with descriptive paired comparisons and repeated-measures / mixed-effects approaches as appropriate. |
| Feasibility: adherence to weekly home-based image capture | Throughout treatment period (up to 12 months) | Proportion of participants performing at least weekly home-based facial image capture using the study application. |
| Feasibility: adherence to symptom reporting | Throughout treatment period (up to 12 months) | Number and proportion of completed in-app symptom reports (diplopia, VAS pain) relative to expected weekly submissions. |
| Feasibility: completion of clinic-matched assessments | Throughout treatment period (up to 12 months) | Number and proportion of participants completing ≥2 clinic-matched assessments including baseline and at least one post-baseline assessment. |
| Relationship between patient-reported symptoms and AI-derived measurements | Throughout treatment period (up to 12 months) | Association between patient-reported diplopia and VAS pain with AI-derived parameters over time, explored descriptively and with regression / mixed-effects models where appropriate. |
| Clinical utility of serial AI-based monitoring between clinic visits | Throughout treatment period (up to 12 months) | Ability of serial AI-derived monitoring to provide clinically useful adjunctive information regarding early improvement or interval worsening between routine clinic visits (descriptive). |
Countries
United States
Contacts
CONTACTJaemin Park
Outcome results
None listed