{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:24:30Z","timestamp":1780392270909,"version":"3.54.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T00:00:00Z","timestamp":1664409600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T00:00:00Z","timestamp":1664409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The purpose of this study was to introduce a new machine learning approach for differentiation of a pachychoroid from a healthy choroid based on enhanced depth-optical coherence tomography (EDI-OCT) imaging. This study included EDI-OCT images of 103 eyes from 82 patients with central serous chorioretinopathy or pachychoroid pigment epitheliopathy, and 103 eyes from 103 age- and sex-matched healthy subjects. Choroidal features including choroidal thickness (CT), choroidal area (CA), Haller layer thickness (HT), Sattler-choriocapillaris thickness (SCT), and the choroidal vascular index (CVI) were extracted. The Haller ratio (HR) was obtained by dividing HT by CT. Multivariate TwoStep cluster analysis was performed with a preset number of two clusters based on a combination of different choroidal features. Clinical criteria were developed based on the results of the cluster analysis, and two independent skilled retina specialists graded a separate testing dataset based on the new clinical criteria. TwoStep cluster analysis achieved a sensitivity of 1.000 (95-CI: 0.938\u20131.000) and a specificity of 0.986 (95-CI: 0.919\u20131.000) in the differentiation of pachy- and healthy choroid. The best result for identification of pachychoroid was obtained for a combination of CT, HR, and CVI, with a correct classification rate of 0.993 (95-CI: 0.980\u20131.000). Based on the relative variable importance (RVI), the cluster analysis prioritized the choroidal features as follows: HR (RVI: 1.0), CVI (RVI: 0.87), CT (RVI: 0.70), CA (RVI: 0.59), and SCT (RVI: 0.27). After performing a receiver operating characteristic curve analysis on the cluster membership variable, a cutoff point of 389\u00a0\u00b5m and 0.79 was determined for CT and HR, respectively. Based on these clinical criteria, a sensitivity of 0.793 (95-CI: 0.611\u20130.904) and a specificity of 0.786 (95-CI: 0.600\u20130.900) and 0.821 (95-CI: 0.638\u20130.924) were achieved for each grader. Cohen's kappa of inter-rater reliability was 0.895. Based on an unsupervised machine learning approach, a combination of the Haller ratio and choroidal thickness is the most valuable factor in the differentiation of pachy- and healthy choroids in a clinical setting.<\/jats:p>","DOI":"10.1038\/s41598-022-20749-9","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T18:04:30Z","timestamp":1664474670000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Differentiating a pachychoroid and healthy choroid using an unsupervised machine learning approach"],"prefix":"10.1038","volume":"12","author":[{"given":"Reza","family":"Mirshahi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masood","family":"Naseripour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Shojaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohsen","family":"Heirani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sayyed Amirpooya","family":"Alemzadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farzan","family":"Moodi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pasha","family":"Anvari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khalil Ghasemi","family":"Falavarjani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,29]]},"reference":[{"key":"20749_CR1","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1038\/s41433-018-0158-4","volume":"33","author":"CMG Cheung","year":"2019","unstructured":"Cheung, C. M. G. et al. Pachychoroid disease. Eye 33, 14\u201333 (2019).","journal-title":"Eye"},{"key":"20749_CR2","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1007\/s00417-020-04940-0","volume":"259","author":"V Castro-Navarro","year":"2021","unstructured":"Castro-Navarro, V. et al. Pachychoroid: Current concepts on clinical features and pathogenesis. Graefe\u2019s Arch. Clin. Exp. Ophthalmol. 259, 1385\u20131400 (2021).","journal-title":"Graefe\u2019s Arch. Clin. Exp. Ophthalmol."},{"key":"20749_CR3","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1097\/IAE.0000000000003256","volume":"42","author":"TM Aslam","year":"2021","unstructured":"Aslam, T. M. et al. Image analysis of optical coherence tomography scans to explore established and novel choroidal features in patients with central serous chorioretinopathy. Retina 42, 88 (2021).","journal-title":"Retina"},{"key":"20749_CR4","doi-asserted-by":"publisher","first-page":"21090","DOI":"10.1038\/srep21090","volume":"6","author":"R Agrawal","year":"2016","unstructured":"Agrawal, R. et al. Choroidal vascularity index as a measure of vascular status of the choroid: Measurements in healthy eyes from a population-based study. Sci. Rep. 6, 21090 (2016).","journal-title":"Sci. Rep."},{"key":"20749_CR5","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1016\/j.oret.2020.08.009","volume":"4","author":"TDL Keenan","year":"2020","unstructured":"Keenan, T. D. L. The Hitchhiker\u2019s guide to cluster analysis: Multi Pertransibunt et Augebitur Scientia. Ophthalmol. Retina 4, 1125\u20131128 (2020).","journal-title":"Ophthalmol. Retina"},{"key":"20749_CR6","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1111\/jdi.12398","volume":"7","author":"MC Amato","year":"2016","unstructured":"Amato, M. C., Pizzolanti, G., Torregrossa, V., Pant\u00f2, F. & Giordano, C. Phenotyping of type 2 diabetes mellitus at onset on the basis of fasting incretin tone: Results of a two-step cluster analysis. J. Diabetes Invest. 7, 219\u2013225 (2016).","journal-title":"J. Diabetes Invest."},{"key":"20749_CR7","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2021-319343","author":"P Yang","year":"2021","unstructured":"Yang, P. et al. Development of revised diagnostic criteria for Fuchs\u2019 uveitis syndrome in a Chinese population. Br. J. Ophthalmol. https:\/\/doi.org\/10.1136\/bjophthalmol-2021-319343 (2021).","journal-title":"Br. J. Ophthalmol."},{"key":"20749_CR8","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.ajo.2020.01.031","volume":"213","author":"RM Gilbert","year":"2020","unstructured":"Gilbert, R. M. et al. Differentiating multifocal choroiditis and punctate inner choroidopathy: A cluster analysis approach. Am. J. Ophthalmol. 213, 244\u2013251 (2020).","journal-title":"Am. J. Ophthalmol."},{"key":"20749_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.joco.2019.08.005","author":"M Heirani","year":"2019","unstructured":"Heirani, M., HeravianShandiz, J., Shojaei, A. & Narooie-Noori, F. Choroidal thickness profile in normal Iranian eyes with different refractive status by spectral-domain optical coherence tomography. J. Curr. Ophthalmol. https:\/\/doi.org\/10.1016\/j.joco.2019.08.005 (2019).","journal-title":"J. Curr. Ophthalmol."},{"key":"20749_CR10","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1097\/IAE.0000000000000998","volume":"36","author":"Y-R Chung","year":"2016","unstructured":"Chung, Y.-R., Kim, J. W., Kim, S. W. & Lee, K. Choroidal thickness in patients with central serous chorioretinopathy. Retina 36, 1652\u20131657 (2016).","journal-title":"Retina"},{"key":"20749_CR11","doi-asserted-by":"publisher","first-page":"18852","DOI":"10.1038\/s41598-020-75816-w","volume":"10","author":"J Yoon","year":"2020","unstructured":"Yoon, J. et al. Optical coherence tomography-based deep-learning model for detecting central serous chorioretinopathy. Sci. Rep. 10, 18852 (2020).","journal-title":"Sci. Rep."},{"key":"20749_CR12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0244469","volume":"16","author":"Y Aoyama","year":"2021","unstructured":"Aoyama, Y. et al. Diagnosis of central serous chorioretinopathy by deep learning analysis of en face images of choroidal vasculature: A pilot study. PLoS ONE 16, e0244469 (2021).","journal-title":"PLoS ONE"},{"key":"20749_CR13","doi-asserted-by":"publisher","unstructured":"Wen, Y. et al. On automatic detection of central serous chorioretinopathy and central exudative chorioretinopathy in fundus images. in 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 1161\u20131165. https:\/\/doi.org\/10.1109\/BIBM49941.2020.9313274 (IEEE, 2020).","DOI":"10.1109\/BIBM49941.2020.9313274"},{"key":"20749_CR14","doi-asserted-by":"publisher","first-page":"204","DOI":"10.2337\/dc20-2806","volume":"45","author":"A Sharma","year":"2022","unstructured":"Sharma, A. et al. Cluster analysis of cardiovascular phenotypes in patients with type 2 diabetes and established atherosclerotic cardiovascular disease: A potential approach to precision medicine. Diabetes Care 45, 204\u2013212 (2022).","journal-title":"Diabetes Care"},{"key":"20749_CR15","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.rmed.2013.10.016","volume":"108","author":"SL Harrison","year":"2014","unstructured":"Harrison, S. L. et al. Can we identify patients with different illness schema following an acute exacerbation of COPD: A cluster analysis. Respir. Med. 108, 319\u2013328 (2014).","journal-title":"Respir. Med."},{"key":"20749_CR16","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1080\/09114300.2018.1451613","volume":"41","author":"M Yamamoto","year":"2018","unstructured":"Yamamoto, M. et al. Predicting therapeutic response in IgG4-related disease based on cluster analysis. Immunol. Med. 41, 30\u201333 (2018).","journal-title":"Immunol. Med."},{"key":"20749_CR17","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1183\/09031936.00032314","volume":"44","author":"L Ye","year":"2014","unstructured":"Ye, L. et al. The different clinical faces of obstructive sleep apnoea: a cluster analysis. Eur. Respir. J. 44, 1600\u20131607 (2014).","journal-title":"Eur. Respir. J."},{"key":"20749_CR18","doi-asserted-by":"publisher","first-page":"4999","DOI":"10.1038\/s41598-021-84650-7","volume":"11","author":"YH Kim","year":"2021","unstructured":"Kim, Y. H., Lee, B., Kang, E. & Oh, J. Clustering of eyes with age-related macular degeneration or pachychoroid spectrum diseases based on choroidal thickness profile. Sci. Rep. 11, 4999 (2021).","journal-title":"Sci. Rep."},{"key":"20749_CR19","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1097\/IAE.0000000000003057","volume":"41","author":"RF Spaide","year":"2021","unstructured":"Spaide, R. F. The ambiguity of pachychoroid. Retina 41, 231\u2013237 (2021).","journal-title":"Retina"},{"key":"20749_CR20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0169152","volume":"12","author":"G Chen","year":"2017","unstructured":"Chen, G. et al. Subfoveal choroidal thickness in central serous chorioretinopathy: A meta-analysis. PLoS ONE 12, e0169152 (2017).","journal-title":"PLoS ONE"},{"key":"20749_CR21","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1097\/IAE.0000000000000287","volume":"35","author":"M Lehmann","year":"2015","unstructured":"Lehmann, M., Bousquet, E., Beydoun, T. & Behar-Cohen, F. Pachychoroid. Retina 35, 10\u201316 (2015).","journal-title":"Retina"},{"key":"20749_CR22","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1097\/IAE.0000000000001502","volume":"38","author":"Y-R Chung","year":"2018","unstructured":"Chung, Y.-R. et al. Subfoveal choroidal thickness and vascular diameter in active and resolved central serous chorioretinopathy. Retina 38, 102\u2013107 (2018).","journal-title":"Retina"},{"key":"20749_CR23","doi-asserted-by":"publisher","first-page":"2309","DOI":"10.1007\/s00417-018-4143-1","volume":"256","author":"J Baek","year":"2018","unstructured":"Baek, J., Lee, J. H., Jung, B. J., Kook, L. & Lee, W. K. Morphologic features of large choroidal vessel layer: Age-related macular degeneration, polypoidal choroidal vasculopathy, and central serous chorioretinopathy. Graefe\u2019s Arch. Clin. Exp. Ophthalmol. 256, 2309\u20132317 (2018).","journal-title":"Graefe\u2019s Arch. Clin. Exp. Ophthalmol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20749-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20749-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20749-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T03:48:59Z","timestamp":1701143339000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-20749-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,29]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["20749"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-20749-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,29]]},"assertion":[{"value":"5 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"16323"}}