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.
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.
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.
Adults (≥19 years) with clinically diagnosed TED who are scheduled to initiate active non-surgical treatment at participating ophthalmology sites.
Cohort
Prospective
Smartphone-based AI self-monitoring application (Glandy CAS/EXO/LID)
DeviceA 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.
Agreement between Glandy CAS and clinician-assessed CAS total score
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
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
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.
Longitudinal change in AI-derived TED parameters
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
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
Proportion of participants performing at least weekly home-based facial image capture using the study application.
Feasibility: adherence to symptom reporting
Number and proportion of completed in-app symptom reports (diplopia, VAS pain) relative to expected weekly submissions.
Descriptive analysis of additional image-derived periocular parameters
Ocular surface area (OSA), radial MRD-related parameters, and other eyelid-related image metrics obtained from patient-captured smartphone images.
Exploratory AI-derived trend vs. treatment response
Exploratory assessment of whether AI-derived home-monitoring trends reflect treatment response over the course of non-surgical treatment.
Real-world image data completeness and analyzability
Descriptive characterization of data completeness and AI-analyzable rate of patient-captured smartphone facial images in a real-world treatment setting.
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
