Facial expression of patients with Graves' orbitopathy.
Deep learning
Facial expression
Graves’ orbitopathy
Patient-reported outcome
Quality of life
Journal
Journal of endocrinological investigation
ISSN: 1720-8386
Titre abrégé: J Endocrinol Invest
Pays: Italy
ID NLM: 7806594
Informations de publication
Date de publication:
Oct 2023
Oct 2023
Historique:
received:
18
01
2023
accepted:
27
02
2023
medline:
25
9
2023
pubmed:
4
4
2023
entrez:
3
4
2023
Statut:
ppublish
Résumé
Patients with Graves' orbitopathy (GO) have characteristic facial expressions that are different from those of healthy individuals due to the combination of somatic and psychiatric symptoms. However, the facial expressions of GO patients have not yet been described and analyzed systematically. Thus, the present study aimed to present the facial expressions of GO patients and explore their applications in clinical practice. Facial image and clinical data of 943 GO patients were included, and 126 patients answered quality of life (GO-QOL) questionnaires. Each patient was labeled for one facial expression. Then, a portrait was drawn for every facial expression. Logistic and linear regression was performed to analyze the correlation between facial expression and clinical indicators, including QOL, disease activity and severity. The VGG-19 network model was utilized to discriminate facial expressions automatically. Two groups, i.e., the non-negative emotion (neutral, happy) and the negative emotion (disgust, angry, fear, sadness, surprise), and seven expressions of GO patients were systematically analyzed. Facial expression was statistically associated with GO activity (P = 0.002), severity (P < 0.001), QOL visual functioning subscale scores (P = 0.001), and QOL appearance subscale score (P = 0.012). The deep learning model achieved satisfactory results (accuracy 0.851, sensitivity 0.899, precision 0.899, specificity 0.720, F1 score 0.899, and AUC 0.847). As a novel clinical sign, facial expression holds the potential to be incorporated into GO assessment system in the future. The discrimination model may assist clinicians in real-life patient care.
Identifiants
pubmed: 37005981
doi: 10.1007/s40618-023-02054-y
pii: 10.1007/s40618-023-02054-y
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2055-2066Subventions
Organisme : the National Key R&D Program of China
ID : 2018YFC1106100
Organisme : the National Key R&D Program of China
ID : 2018YFC1106101
Organisme : School of Medicine, Shanghai Jiao Tong University
ID : ZH2018QNA07
Organisme : School of Medicine, Shanghai Jiao Tong University
ID : ZH2018ZDA12
Organisme : the Science and Technology Commission of Shanghai
ID : 19410761100
Organisme : the Science and Technology Commission of Shanghai
ID : 19DZ2331400
Organisme : Cross disciplinary Research Fund of Shanghai Ninth People's Hospital, Shanghai JiaoTong university School of Medicine
ID : JYJC202115
Organisme : Innovative Research Team of High-Level Local Universities in Shanghai
ID : SHSMU-ZDCX20210901
Organisme : Shanghai Key Clinical Specialty, Shanghai Eye Disease Research Center
ID : 2022ZZ01003
Informations de copyright
© 2023. The Author(s), under exclusive licence to Italian Society of Endocrinology (SIE).
Références
Smith TJ, Hegedüs L (2016) Graves’ disease. N Engl J Med 375(16):1552–1565
doi: 10.1056/NEJMra1510030
pubmed: 27797318
Taylor PN et al (2020) New insights into the pathogenesis and nonsurgical management of Graves orbitopathy. Nat Rev Endocrinol 16(2):104–116
doi: 10.1038/s41574-019-0305-4
pubmed: 31889140
Dalm V, Paridaens D, Peeters RP (2018) Graves’ orbitopathy: the ongoing search for new treatment strategies. Lancet Diabetes Endocrinol 6(4):261–263
doi: 10.1016/S2213-8587(18)30022-6
pubmed: 29396248
Davies TF et al (2020) Graves’ disease. Nat Rev Dis Primers 6(1):52
doi: 10.1038/s41572-020-0184-y
pubmed: 32616746
Neag EJ, Smith TJ (2022) 2021 update on thyroid-associated ophthalmopathy. J Endocrinol Invest 45(2):235–259
doi: 10.1007/s40618-021-01663-9
pubmed: 34417736
Salvador AF, de Lima KA, Kipnis J (2021) Neuromodulation by the immune system: a focus on cytokines. Nat Rev Immunol 21(8):526–541
doi: 10.1038/s41577-021-00508-z
pubmed: 33649606
Estcourt S, Quinn AG, Vaidya B (2011) Quality of life in thyroid eye disease: impact of quality of care. Eur J Endocrinol 164(5):649–655
doi: 10.1530/EJE-11-0055
pubmed: 21367964
Wickwar S et al (2015) The psychosocial and clinical outcomes of orbital decompression surgery for thyroid eye disease and predictors of change in quality of life. Ophthalmology 122(12):2568–76.e1
doi: 10.1016/j.ophtha.2015.08.030
pubmed: 26421706
Bartalena L et al (2021) The 2021 European Group on Graves’ orbitopathy (EUGOGO) clinical practice guidelines for the medical management of Graves’ orbitopathy. Eur J Endocrinol 185(4):G43-g67
doi: 10.1530/EJE-21-0479
pubmed: 34297684
Trimarchi F, Martino E, Bartalena L (2020) Graves’ orbitopathy represented as feature of a state of mind. J Endocrinol Invest 43(9):1343–1344
doi: 10.1007/s40618-020-01250-4
pubmed: 32306295
Terwee CB et al (1998) Development of a disease specific quality of life questionnaire for patients with Graves’ ophthalmopathy: the GO-QOL. Br J Ophthalmol 82(7):773–779
doi: 10.1136/bjo.82.7.773
pubmed: 9924370
pmcid: 1722683
Ekman P, Friesen WV (1971) Constants across cultures in the face and emotion. J Pers Soc Psychol 17(2):124–129
doi: 10.1037/h0030377
pubmed: 5542557
Ekman P, Hager JC (2002) Facial action coding system, 2nd edn. Research Nexus eBook, Salt Lake City
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR, 2014. abs/1409.1556.
Zhou B et al (2016) Learning deep features for discriminative localization. IEEE Conf Comput Vis Pattern Recogn (CVPR) 2015:2921–2929
Jeon J, et al (2016) A real-time facial expression recognizer using deep neural network. In: Proceedings of the 10th International Conference on Ubiquitous Information Management and Communication p. 1–4
Ali MR et al (2021) Facial expressions can detect Parkinson’s disease: preliminary evidence from videos collected online. NPJ Digit Med 4(1):129
doi: 10.1038/s41746-021-00502-8
pubmed: 34480109
pmcid: 8417264
de la Torre-Luque A et al (2022) Relationships between social withdrawal and facial emotion recognition in neuropsychiatric disorders. Prog Neuropsychopharmacol Biol Psychiatry 113:110463
doi: 10.1016/j.pnpbp.2021.110463
pubmed: 34718073
Coulter I et al (2007) Psychological implications of Graves’ orbitopathy. Eur J Endocrinol 157(2):127–131
doi: 10.1530/EJE-07-0205
pubmed: 17656589
JM RJFD (1997) The psychology of facial expression. Cambridge University Press, Cambridge
Bruscolini A et al (2018) Quality of life and neuropsychiatric disorders in patients with Graves’ Orbitopathy: current concepts. Autoimmun Rev 17(7):639–643
doi: 10.1016/j.autrev.2017.12.012
pubmed: 29729448
Zeng P et al (2019) Evaluation of the Graves’ orbitopathy-specific quality of life questionnaire in the mainland Chinese population. J Ophthalmol 2019:7602419
doi: 10.1155/2019/7602419
pubmed: 31011452
pmcid: 6442306
Wang Y et al (2018) A single-center retrospective study of factors related to the effects of intravenous glucocorticoid therapy in moderate-to-severe and active thyroid-associated ophthalmopathy. BMC Endocr Disord 18(1):13
doi: 10.1186/s12902-018-0240-8
pubmed: 29463244
pmcid: 5819263
Chng CL, Seah LL, Khoo DH (2012) Ethnic differences in the clinical presentation of Graves’ ophthalmopathy. Best Pract Res Clin Endocrinol Metab 26(3):249–258
doi: 10.1016/j.beem.2011.10.004
pubmed: 22632362
Lee THB, Sundar G (2020) Quality of life in thyroid eye disease: a systematic review. Ophthalmic Plast Reconstr Surg 36(2):118–126
doi: 10.1097/IOP.0000000000001446
pubmed: 31567783
Fayers T, Dolman PJ (2011) Validity and reliability of the TED-QOL: a new three-item questionnaire to assess quality of life in thyroid eye disease. Br J Ophthalmol 95(12):1670–1674
doi: 10.1136/bjophthalmol-2011-300487
pubmed: 21951566
Bartalena L, Wiersinga WM (2020) Proposal for standardization of primary and secondary outcomes in patients with active. moderate-to-severe Graves’ orbitopathy. Eur Thyroid J 9(Suppl 1):3–16
doi: 10.1159/000510700
pubmed: 33511081
pmcid: 7802435
Cao J et al (2022) The risk factors for Graves’ ophthalmopathy. Graefes Arch Clin Exp Ophthalmol 260(4):1043–1054
doi: 10.1007/s00417-021-05456-x
pubmed: 34787691
Wickwar S et al (2018) Patients’ expectations for the functional and psychosocial outcomes of orbital decompression surgery for thyroid eye disease: a qualitative study. Psychol Health Med 23(4):475–484
doi: 10.1080/13548506.2017.1356930
pubmed: 28738723
Wiersinga WM (2012) Quality of life in Graves’ ophthalmopathy. Best Pract Res Clin Endocrinol Metab 26(3):359–370
doi: 10.1016/j.beem.2011.11.001
pubmed: 22632371
Barrett LF et al (2019) Emotional expressions reconsidered: challenges to inferring emotion from human facial movements. Psychol Sci Public Interest 20(1):1–68
doi: 10.1177/1529100619832930
pubmed: 31313636
pmcid: 6640856
Gavrilescu M, Vizireanu N (2019) Predicting depression, anxiety, and stress levels from videos using the facial action coding system. Sensors 19:17
doi: 10.3390/s19173693
Polli E et al (2012) Facial action coding system (FACS): an instrument for the objective evaluation of facial expression and its potential applications to the study of schizophrenia. Riv Psichiatr 47(2):126–138
pubmed: 22622249
Song X et al (2021) Artificial intelligence CT screening model for thyroid-associated ophthalmopathy and tests under clinical conditions. Int J Comput Assist Radiol Surg 16(2):323–330
doi: 10.1007/s11548-020-02281-1
pubmed: 33146848
Lin C et al (2021) Detection of active and inactive phases of thyroid-associated ophthalmopathy using deep convolutional neural network. BMC Ophthalmol 21(1):39
doi: 10.1186/s12886-020-01783-5
pubmed: 33446163
pmcid: 7807896
Yoo H et al (2020) Validation of a deep learning algorithm for the detection of malignant pulmonary nodules in chest radiographs. JAMA Netw Open 3(9):e2017135
doi: 10.1001/jamanetworkopen.2020.17135
pubmed: 32970157
pmcid: 7516603
Lin S et al (2020) Feasibility of using deep learning to detect coronary artery disease based on facial photo. Eur Heart J 41(46):4400–4411
doi: 10.1093/eurheartj/ehaa640
pubmed: 32818267