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.

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.

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.

Adults (≥19 years) with clinically diagnosed TED who are scheduled to initiate active non-surgical treatment at participating ophthalmology sites.

The dataset includes patient-captured smartphone facial photographs, which are inherently identifiable biometric data. Public sharing of individual participant data (IPD) would pose a substantial risk of re-identification that cannot be fully mitigated by standard de-identification of tabular variables alone. The informed consent obtained from participants and the IRB-approved protocol do not authorize broad third-party sharing of these facial images or associated individual-level records. In addition, the study is conducted in the Republic of Korea and is subject to the Personal Information Protection Act (PIPA) and the Bioethics and Safety Act, which restrict external transfer of identifiable health and biometric information. For these reasons, individual-level data will not be shared publicly. Reasonable requests for scientifically justified collaborative analyses may be considered on a case-by-case basis, subject to a data-use agreement, sponsor approval, and applicable ethics appr