1
|
Wu H, Song Q, Zhang Y, Cheng R, Li Y, Su M, Zhang X, Sun X. Optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) for assessing thyroid-associated ophthalmopathy activity. Photodiagnosis Photodyn Ther 2025; 53:104578. [PMID: 40187512 DOI: 10.1016/j.pdpdt.2025.104578] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2025] [Revised: 03/26/2025] [Accepted: 04/02/2025] [Indexed: 04/07/2025]
Abstract
PURPOSE To explore the role of retinal and choroidal parameters obtained via optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) in predicting thyroid-associated ophthalmopathy (TAO) activity, providing a scientific basis for improved clinical diagnosis and treatment. METHOD This study included 90 active TAO patients (178 eyes), 69 inactive TAO patients (138 eyes), and 66 healthy individuals (132 eyes). It compared choroidal and retinal parameters and magnetic resonance imaging structural differences, analyzed correlations between these parameters, and developed a predictive model for TAO activity. RESULTS Compared to control and inactive groups, active group had thicker subfoveal choroidal thickness (SFCT) and reduced luminal area, stromal area, and total choroidal area. Active group showed reduced vessel density in the foveal and nasal regions versus inactive group, and in the foveal, superior, and nasal regions versus controls. Foveal avascular zone (FAZ) area was larger in active group than in both control and inactive groups. Active group also had larger inner diameters and signal intensity ratio (SIR) of the extraocular muscles than inactive group. SFCT correlated with proptosis, and FAZ correlated with proptosis, maximum extraocular muscle diameter, and SIR. The multivariate model achieved area under the curve values of 0.836 in overall TAO population and 0.855 in hyperlipidemia subgroup, outperforming the univariate model. CONCLUSION Retinal and choroidal parameters, obtained via OCT/OCTA, are keys to developing TAO activity predictive models, with enhanced accuracy in TAO patients with hyperlipidemia.
Collapse
Affiliation(s)
- Huihui Wu
- Department of Ophthalmology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China
| | - Qinglu Song
- Department of Ophthalmology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu, China
| | - Ye Zhang
- Department of Ophthalmology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China
| | - Ruiwen Cheng
- Department of Ophthalmology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China
| | - Yuanyuan Li
- Department of Ophthalmology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China
| | - Mengru Su
- Department of Ophthalmology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
| | - Xiaowen Zhang
- Department of Endocrinology and Metabolism, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
| | - Xinghong Sun
- Department of Ophthalmology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
| |
Collapse
|
2
|
Baczewska N, Alexopoulou O, Constantinescu SM, Daumerie C, Coutel M, Boschi A, Burlacu MC. Factors Associated with Response to Intravenous Glucocorticoids in Active Moderate-to-Severe Thyroid Eye Disease. Thyroid 2025; 35:424-432. [PMID: 40053436 DOI: 10.1089/thy.2024.0629] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/09/2025]
Abstract
Background: Intravenous glucocorticoids (IVGCs) are the first-line treatment for active moderate-to-severe thyroid eye disease (TED) in many countries worldwide, mainly because of their anti-inflammatory efficacy. Methods: Retrospective cohort study of 64 patients with active moderate-to-severe TED, without dysthyroid optic neuropathy, treated between 2003 and 2023 at a single tertiary centre with the 12 weeks IVGC EUGOGO (European Group on Graves Orbitopathy) protocol. All patients were evaluated for response to IVGC according to the clinical judgment (CL) and 44/64 (69%) patients were also evaluated with the EUGOGO 2021 revised composite index (CI). Results: The mean patients' age at IVGC initiation was 51.7 ± 11 years, 47/64 (73.5%) were women, 56/64 (87.5%) were Caucasians, and 33/64 (51.5%) were active smokers. At 6 months after IVGC, 48 out of 64 (75%) patients evaluated with CL and 32 out of 44 (73%) patients evaluated with EUGOGO CI responded to the treatment. Nonresponders tended to be older than responders (56.6 ± 10.2 vs. 50.1 ± 10.8 years, p = 0.040 for CL and 56.5 ± 11.9 vs. 50.3 ± 11.6 years, p = 0.131 for EUGOGO CI) and had higher clinical activity score (CAS) before IVGC (5.0 ± 1.1 vs.4.2 ± 1.1, p = 0.022 for CL and 4.7 ± 0.6 vs. 3.1 ± 0.8, p < 0.001 for EUGOGO CI). In patients evaluated with CL or EUGOGO CI, respectively, multivariable logistic regression identified age at IVGC initiation (odds ratio [OR] = 0.92 [95% confidence interval (CI) 0.86-0.99], p = 0.024 and OR = 0.88 [CI 0.77-0.99], p = 0.046) and CAS before IVGC (OR = 0.53 [CI 0.31-0.90], p = 0.021 and OR= 0.08 [CI 0.01-0.38], p = 0.001) but not active smoking as independent factors associated with response to IVGC. The optimal cut-off associated with poorer response to IVGC was CAS ≥4.5/7 (66.7% specificity, 56.3% sensitivity; Area Under the Curve [AUC] = 0.689 [CI 0.54-0.83], p = 0.010) in patients evaluated with CL and CAS ≥3.5/5 (65.6% specificity, 91.7% sensitivity; AUC = 0.910 [CI 0.80-1.01], p < 0.001) in patients evaluated with EUGOGO CI. Conclusion: Older age and higher CAS before treatment were associated with poorer response to IVGC. Patients with these characteristics could be offered other immunotherapies as a first-line treatment for active moderate-to-severe TED.
Collapse
Affiliation(s)
- Natalia Baczewska
- Department of Endocrinology and Nutrition, Cliniques Universitaires Saint-Luc, Université Catholique de Louvain, Brussels, Belgium
| | - Orsalia Alexopoulou
- Department of Endocrinology and Nutrition, Cliniques Universitaires Saint-Luc, Université Catholique de Louvain, Brussels, Belgium
| | - Stefan M Constantinescu
- Department of Endocrinology and Nutrition, Cliniques Universitaires Saint-Luc, Université Catholique de Louvain, Brussels, Belgium
| | - Chantal Daumerie
- Department of Endocrinology and Nutrition, Cliniques Universitaires Saint-Luc, Université Catholique de Louvain, Brussels, Belgium
| | - Maëlle Coutel
- Department of Ophthalmology, Cliniques Universitaires Saint-Luc, Université Catholique de Louvain, Brussels, Belgium
| | - Antonella Boschi
- Department of Ophthalmology, Cliniques Universitaires Saint-Luc, Université Catholique de Louvain, Brussels, Belgium
| | - Maria-Cristina Burlacu
- Department of Endocrinology and Nutrition, Cliniques Universitaires Saint-Luc, Université Catholique de Louvain, Brussels, Belgium
| |
Collapse
|
3
|
Wang Y, Yang S, Zeng C, Xie Y, Shen Y, Li J, Huang X, Wei R, Chen Y. Evaluating the performance of ChatGPT in patient consultation and image-based preliminary diagnosis in thyroid eye disease. Front Med (Lausanne) 2025; 12:1546706. [PMID: 40041459 PMCID: PMC11876178 DOI: 10.3389/fmed.2025.1546706] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2024] [Accepted: 01/27/2025] [Indexed: 03/06/2025] Open
Abstract
Background The emergence of Large Language Model (LLM) chatbots, such as ChatGPT, has great promise for enhancing healthcare practice. Online consultation, accurate pre-diagnosis, and clinical efforts are of fundamental importance for the patient-oriented management system. Objective This cross-sectional study aims to evaluate the performance of ChatGPT in inquiries across ophthalmic domains and to focus on Thyroid Eye Disease (TED) consultation and image-based preliminary diagnosis in a non-English language. Methods We obtained frequently consulted clinical inquiries from a published reference based on patient consultation data, titled A Comprehensive Collection of Thyroid Eye Disease Knowledge. Additionally, we collected facial and Computed Tomography (CT) images from 16 patients with a definitive diagnosis of TED. From 18 to 30 May 2024, inquiries about the TED consultation and preliminary diagnosis were posed to ChatGPT using a new chat for each question. Responses to questions from ChatGPT-4, 4o, and an experienced ocular professor were compiled into three questionnaires, which were evaluated by patients and ophthalmologists on four dimensions: accuracy, comprehensiveness, conciseness, and satisfaction. The preliminary diagnosis of TED was deemed accurate, and the differences in the accuracy rates were further calculated. Results For common TED consultation questions, ChatGPT-4o delivered more accurate information with logical consistency, adhering to a structured format of disease definition, detailed sections, and summarized conclusions. Notably, the answers generated by ChatGPT-4o were rated higher than those of ChatGPT-4 and the professor, with accuracy (4.33 [0.69]), comprehensiveness (4.17 [0.75]), conciseness (4.12 [0.77]), and satisfaction (4.28 [0.70]). The characteristics of the evaluators, the response variables, and other quality scores were all correlated with overall satisfaction levels. Based on several facial images, ChatGPT-4 twice failed to make diagnoses because of lacking characteristic symptoms or a complete medical history, whereas ChatGPT-4o accurately identified the pathologic conditions in 31.25% of cases (95% confidence interval, CI: 11.02-58.66%). Furthermore, in combination with CT images, ChatGPT-4o performed comparably to the professor in terms of diagnosis accuracy (87.5, 95% CI 61.65-98.45%). Conclusion ChatGPT-4o excelled in comprehensive and satisfactory patient consultation and imaging interpretation, indicating the potential to improve clinical practice efficiency. However, limitations in disinformation management and legal permissions remain major concerns, which require further investigation in clinical practice.
Collapse
Affiliation(s)
- Yue Wang
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| | - Shuo Yang
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| | - Chengcheng Zeng
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| | - Yingwei Xie
- Department of Urology, Beijing Tongren Hospital of Capital Medical University, Beijing, China
| | - Ya Shen
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| | - Jian Li
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| | - Xiao Huang
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| | - Ruili Wei
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| | - Yuqing Chen
- Department of Ophthalmology, Changzheng Hospital of Naval Medical University, Shanghai, China
| |
Collapse
|
4
|
Zhang H, Liu Y, Zhang Z, Jiang M, Tao X, Lee XN, Fang Z, Song X, Silkiss RZ, Fan X, Zhou H. Neuroimaging in thyroid eye disease: A systematic review. Autoimmun Rev 2024; 23:103667. [PMID: 39396626 DOI: 10.1016/j.autrev.2024.103667] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2024] [Revised: 10/10/2024] [Accepted: 10/10/2024] [Indexed: 10/15/2024]
Abstract
Thyroid eye disease (TED) is an organ-specific autoimmune disease secondary largely to hyperthyroid Graves' disease, which profoundly affects patients' visual function, appearance, and physical and mental well-being. Emerging neuroimaging studies have reported alterations in the brains of patients with TED, suggesting that the impact of this autoimmune disease may extend beyond the orbit. This systematic review aims to consolidate the neuroimaging evidence that describes the brain alterations of TED. We analyzed information from thirty-one related studies involving 1349 TED patients and 710 healthy controls, employing multimodal neuroimaging techniques such as structural magnetic resonance imaging (MRI), functional MRI, diffusion MRI, and metabolic MRI. These studies define the brain alterations in regions associated with vision, cognition, and emotion regulation, such as gray matter volume changes, altered functional connectivity and activity, and microstructural modifications, revealing the neurological impact of TED beyond the orbit. Notably, there was convergence across these studies indicating predominant abnormalities within the occipital and parietal lobes. This review underscores the critical role of advanced neuroimaging techniques in unraveling the complex neuropathological mechanism of TED, laying a foundation for future research and potential therapeutic targets.
Collapse
Affiliation(s)
- Haiyang Zhang
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yuting Liu
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Zixiang Zhang
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Mengda Jiang
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xiaofeng Tao
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xin Ning Lee
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Zilin Fang
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xuefei Song
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| | - Rona Z Silkiss
- Division of Ophthalmic Plastic Surgery, California Pacific Medical Center, Silkiss Eye Surgery, San Francisco, CA, United States
| | - Xianqun Fan
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| | - Huifang Zhou
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, and Center for Basic Medical Research and Innovation in Visual System Diseases of Ministry of Education, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| |
Collapse
|
5
|
Higgins RC, Lane CF, Goyal N. Otolaryngologist surgical preferences for orbital decompression in thyroid eye disease: A North American survey. Laryngoscope Investig Otolaryngol 2024; 9:e70051. [PMID: 39655097 PMCID: PMC11626485 DOI: 10.1002/lio2.70051] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2024] [Revised: 10/20/2024] [Accepted: 11/13/2024] [Indexed: 12/12/2024] Open
Abstract
Background Orbital decompression is recommended for TED especially in the treatment of severe, refractory cases yet there are no clear guidelines regarding the optimal surgical approach. Previously conducted surveys assessed variations in the management of TED but only amongst ophthalmologists. Our study attempts to better characterize surgical and perioperative preferences amongst otolaryngologists in the management of TED. Methods A survey was administered to the American Rhinologic Society and Canadian Society of Otolaryngology - Head and Neck Surgery via REDCap with 52 total respondents. Respondent demographic information and pre-operative management, procedural specifics, and post-operative management preferences were collected. Results The majority of respondents practiced in a metropolitan (82.7%), academic setting (73.1%) and received subspecialty training in Rhinology & Skull Base Surgery (88.9%). Most elected for corticosteroids (63.5%) and medical management (69.2%) prior to orbital decompression but did not use any classification system (86.5%). Orbital decompression was most often done with ophthalmology collaboration (71.2%). Removal of two bony walls (55.8%) via medial wall (97.9%) and orbital floor (72.3%) removal was most preferred. Removal of one orbital fat aspect (60.6%) via the medial fat pad was most preferred. Combined bone and fat removal (59.6%) completed via an endoscopic approach (71.2% and 97.0%, respectively) was most common. Post-operatively, most patients were not admitted (88.4%) with saline nasal rinses (92.3%) utilized by most respondents. Conclusions This survey completed by otolaryngologists highlights several key distinctions in the preferred surgical approach during orbital decompression and the perioperative management of TED when compared to ophthalmologists and current recommendations. Level of evidence Level 4.
Collapse
Affiliation(s)
- Ryan C. Higgins
- Department of OtolaryngologyUniversity of Nebraska Medical CenterOmahaNebraskaUSA
| | - Ciaran F. Lane
- Department of OtolaryngologyUniversity of ManitobaWinnipegManitobaCanada
| | - Neerav Goyal
- Department of OtolaryngologyThe Pennsylvania State University, College of MedicineHersheyPennsylvaniaUSA
| |
Collapse
|
6
|
Zhang H, Fang L, Cheng Y, Peng Y, Wang H, Jiang M, Zhu L, Li Y, Fang S, Zhou H, Sun J, Song X. Peripheral CD3 +CD4 + T cells as indicators of disease activity in thyroid eye disease: age-dependent significance. Graefes Arch Clin Exp Ophthalmol 2024; 262:2985-2997. [PMID: 38689122 DOI: 10.1007/s00417-024-06496-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Revised: 04/19/2024] [Accepted: 04/25/2024] [Indexed: 05/02/2024] Open
Abstract
PURPOSE To provide an in-depth analysis of the association of peripheral lymphocytes and the disease activity of thyroid eye disease (TED). METHODS This retrospective study enrolled 65 active TED patients and 46 inactive TED patients. Comparative analyses of peripheral lymphocyte subsets were conducted between active and inactive patients. Subgroup analyses were performed based on sex, age, disease duration, and severity. Correlation analyses explored the associations between lymphocyte subsets and TED activity indicators. Prediction models for TED activity were established using objective indicators. RESULTS Significantly elevated levels of CD3+CD4+ T cells were observed in active TED patients compared to inactive patients (P = 0.010). Subgroup analyses further revealed that this disparity was most prominent in females (P = 0.036), patients aged 50 years and younger (P = 0.003), those with long-term disease duration (P = 0.022), and individuals with moderate-to-severe disease (P = 0.021), with age exerting the most substantial impact. Subsequent correlation analysis confirmed the positive association between CD3+CD4+ T cells and the magnetic resonance imaging indicator of TED activity among patients aged 50 years and younger (P = 0.038). The combined prediction models for TED activity, established using objective indicators including CD3+CD4+ T cells, yielded areas under curve of 0.786 for all patients and 0.816 for patients aged 50 years and younger. CONCLUSIONS Peripheral CD3+CD4+ T cells are associated with disease activity of TED, especially in patients aged 50 years and younger. Our study has deepened the understanding of the peripheral T cell profiles in TED patients.
Collapse
Affiliation(s)
- Haiyang Zhang
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Lianfei Fang
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Yumeng Cheng
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Yuhang Peng
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Hui Wang
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Mengda Jiang
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Ling Zhu
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yinwei Li
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Sijie Fang
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Huifang Zhou
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China.
| | - Jing Sun
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China.
| | - Xuefei Song
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China.
| |
Collapse
|
7
|
Shin K, Choung H, Lee MJ, Kim J, Lee GM, Kim S, Kim JH, Oh R, Park J, Lee SM, Park J, Kim N, Moon JH. A Preliminary Evaluation of the Diagnostic Performance of a Smartphone-Based Machine Learning-Assisted System for Evaluation of Clinical Activity Score in Digital Images of Thyroid-Associated Orbitopathy. Thyroid 2024; 34:744-752. [PMID: 38623815 DOI: 10.1089/thy.2023.0621] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 04/17/2024]
Abstract
Background: We previously developed a machine learning (ML)-assisted system for predicting the clinical activity score (CAS) in thyroid-associated orbitopathy (TAO) using digital facial images taken by a digital single-lens reflex camera in a studio setting. In this study, we aimed to apply this system to smartphones and detect active TAO (CAS ≥3) using facial images captured by smartphone cameras. We evaluated the performance of our system on various smartphone models and compared it with the performance of ophthalmologists with varying clinical experience. Methods: We applied the preexisting ML architecture to classify photos taken with smartphones (Galaxy S21 Ultra, iPhone 12 pro, iPhone 11, iPhone SE 2020, Galaxy M20, and Galaxy A21S). The performance was evaluated with smartphone-captured images from 100 patients with TAO. Three ophthalmology residents, three general ophthalmologists with <5 years of clinical experience, and three oculoplastic specialists independently interpreted the same set of images taken under a studio environment and compared their results with those generated by the smartphone-based ML-assisted system. Reference CAS was determined by a consensus of three oculoplastic specialists. Results: Active TAO (CAS ≥3) was identified in 28 patients. Smartphone model used in capturing facial images influenced active TAO detection performance (F1 score 0.59-0.72). The smartphone-based system showed 74.5% sensitivity, 84.8% specificity, and F1 score 0.70 on top three smartphones. On images from all six smartphones, average sensitivity, specificity, and F1 score were 71.4%, 81.6%, and 0.66, respectively. Ophthalmology residents' values were 69.1%, 55.1%, and 0.46. General ophthalmologists' values were 61.9%, 79.6%, and 0.55. Oculoplastic specialists' values were 73.8%, 90.7%, and 0.75. This smartphone-based ML-assisted system predicted CAS within 1 point of reference CAS in 90.7% using facial images from smartphones. Conclusions: Our smartphone-based ML-assisted system shows reasonable accuracy in detecting active TAO, comparable with oculoplastic specialists and outperforming residents and general ophthalmologists. It may enable reliable self-monitoring for disease activity, but confirmatory research is needed for clinical application.
Collapse
Affiliation(s)
- Kyubo Shin
- AI Research Center, THYROSCOPE INC., Ulsan, Republic of Korea
| | - Hokyung Choung
- Department of Ophthalmology, Seoul Metropolitan Government Seoul National University Boramae Medical Center and Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Min Joung Lee
- Department of Ophthalmology, Hallym University Sacred Heart Hospital and Hallym University College of Medicine, Anyang, Republic of Korea
| | - Jongchan Kim
- AI Research Center, THYROSCOPE INC., Ulsan, Republic of Korea
| | - Gyeong Min Lee
- Department of Ophthalmology, Dongguk University Ilsan Medical Center, Gyeonggi-do, Republic of Korea
| | - Seongmi Kim
- Department of Ophthalmology, Seoul National University Bundang Hospital and Seoul National University College of Medicine, Seongnam, Republic of Korea
| | - Jae Hyuk Kim
- Department of Ophthalmology, Seoul National University Hospital and Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Richul Oh
- Department of Ophthalmology, Seoul National University Hospital and Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Jisun Park
- Department of Ophthalmology, Seoul National University Hospital and Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Sang Muk Lee
- Department of Ophthalmology, Hallym University Sacred Heart Hospital and Hallym University College of Medicine, Anyang, Republic of Korea
| | - Jaemin Park
- AI Research Center, THYROSCOPE INC., Ulsan, Republic of Korea
| | - Namju Kim
- Department of Ophthalmology, Seoul National University Bundang Hospital and Seoul National University College of Medicine, Seongnam, Republic of Korea
| | - Jae Hoon Moon
- AI Research Center, THYROSCOPE INC., Ulsan, Republic of Korea
- Department of Internal Medicine, Seoul National University Bundang Hospital and Seoul National University College of Medicine, Seongnam, Republic of Korea
- Center for Artificial Intelligence in Healthcare, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
| |
Collapse
|
8
|
Rana K, Garg D, Yong LSS, Leyden J, Patel S, Slattery J, Davis G, Chan WO, Selva D. Asymmetric proptosis in thyroid eye disease. Int Ophthalmol 2024; 44:206. [PMID: 38678129 PMCID: PMC11055760 DOI: 10.1007/s10792-024-03141-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Accepted: 04/11/2024] [Indexed: 04/29/2024]
Abstract
PURPOSE Patients with thyroid eye disease (TED) can present with asymmetric disease. The purpose of this study was to evaluate the prevalence of asymmetric TED in an Australian cohort and investigate clinical, biochemical, and radiological associations of asymmetric TED. METHODS This was a retrospective study of patients with TED who underwent Hertel exophthalmometry and orbital computed tomography (CT) scans. Asymmetry was defined as a difference in the globe protrusion of ≥ 3 mm using Hertel exophthalmometry. Data was collected on patient demographics, clinical disease presentation, thyroid function tests and antibody levels. Muscles volumes were determined by manually segmenting the extraocular muscles on CT scans using a commercially available software. RESULTS 172 orbits from 86 patients were included in the study. 28 (33%) patients had asymmetric TED. No significant differences were observed in age, gender, thyroid hormone status, anti-thyroid peroxidase levels, thyroid stimulating hormone receptor antibodies, disease activity status, or dysthyroid optic neuropathy between the asymmetric and non-asymmetric groups. The extraocular muscle volumes were significantly higher in the asymmetric orbit compared to its contralateral orbit. CONCLUSION Asymmetric TED is a reasonably common occurrence in the course of TED. It is associated with higher extraocular muscle volumes, suggesting muscle enlargement as one of the underlying contributors to asymmetric proptosis. Thyroid eye disease should be considered in the differential of asymmetric orbital inflammatory disease.
Collapse
Affiliation(s)
- Khizar Rana
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia.
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia.
| | - Devanshu Garg
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| | - Lee Shien S Yong
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| | - James Leyden
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| | - Sandy Patel
- Department of Medical Imaging, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| | - James Slattery
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| | - Garry Davis
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| | - Weng Onn Chan
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| | - Dinesh Selva
- Department of Ophthalmology and Visual Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5000, Australia
- South Australian Institute of Ophthalmology, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia
| |
Collapse
|