{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:31:06Z","timestamp":1775251866386,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,11]],"date-time":"2021-12-11T00:00:00Z","timestamp":1639180800000},"content-version":"vor","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001869","name":"Academia Sinica","doi-asserted-by":"publisher","award":["40-05-GMM and AS-GC-110-MD02"],"award-info":[{"award-number":["40-05-GMM and AS-GC-110-MD02"]}],"id":[{"id":"10.13039\/501100001869","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Rheumatoid arthritis (RA) and systemic lupus erythematous (SLE) are autoimmune rheumatic diseases that share a complex genetic background and common clinical features. This study\u2019s purpose was to construct machine learning (ML) models for the genomic prediction of RA and SLE.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>A total of 2,094 patients with RA and 2,190 patients with SLE were enrolled from the Taichung Veterans General Hospital cohort of the Taiwan Precision Medicine Initiative. Genome-wide single nucleotide polymorphism (SNP) data were obtained using Taiwan Biobank version 2 array. The ML methods used were logistic regression (LR), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and extreme gradient boosting (XGB). SHapley Additive exPlanation (SHAP) values were calculated to clarify the contribution of each SNPs. Human leukocyte antigen (HLA) imputation was performed using the HLA Genotype Imputation with Attribute Bagging package.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Compared with LR (area under the curve [AUC] = 0.8247), the RF approach (AUC = 0.9844), SVM (AUC = 0.9828), GTB (AUC = 0.9932), and XGB (AUC = 0.9919) exhibited significantly better prediction performance. The top 20 genes by feature importance and SHAP values included HLA class II alleles. We found that imputed HLA-DQA1*05:01, DQB1*0201 and DRB1*0301 were associated with SLE; HLA-DQA1*03:03, DQB1*0401, DRB1*0405 were more frequently observed in patients with RA.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>We established ML methods for genomic prediction of RA and SLE. Genetic variations at HLA-DQA1, HLA-DQB1, and HLA-DRB1 were crucial for differentiating RA from SLE. Future studies are required to verify our results and explore their mechanistic explanation.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s13040-021-00284-5","type":"journal-article","created":{"date-parts":[[2021,12,11]],"date-time":"2021-12-11T13:02:38Z","timestamp":1639227758000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Machine learning approaches for the genomic prediction of rheumatoid arthritis and systemic lupus erythematosus"],"prefix":"10.1186","volume":"14","author":[{"given":"Chih-Wei","family":"Chung","sequence":"first","affiliation":[]},{"given":"Tzu-Hung","family":"Hsiao","sequence":"additional","affiliation":[]},{"given":"Chih-Jen","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Yen-Ju","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hsin-Hua","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ching-Heng","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Seng-Cho","family":"Chou","sequence":"additional","affiliation":[]},{"given":"Tzer-Shyong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yu-Fang","family":"Chung","sequence":"additional","affiliation":[]},{"given":"Hwai-I","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yi-Ming","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,11]]},"reference":[{"key":"284_CR1","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1136\/annrheumdis-2019-215533","volume":"79","author":"Y Wang","year":"2020","unstructured":"Wang Y, Chen S, Chen J, Xie X, Gao S, Zhang C, et al. Germline genetic patterns underlying familial rheumatoid arthritis, systemic lupus erythematosus and primary Sj\u00f6gren\u2019s syndrome highlight T cell-initiated autoimmunity. Ann Rheum Dis. 2020;79:268\u201375.","journal-title":"Ann Rheum Dis"},{"key":"284_CR2","doi-asserted-by":"crossref","unstructured":"Scott D, Wolfe F, Huizinga T. Rheumatoid arthritis. Lancet [Internet]. Elsevier Ltd 2010.","DOI":"10.1016\/S0140-6736(10)60826-4"},{"key":"284_CR3","doi-asserted-by":"crossref","unstructured":"Tsokos GC. Systemic lupus erythematosus. N Engl J Med. 2011 Dec 1; 365:2110\u201321.","DOI":"10.1056\/NEJMra1100359"},{"key":"284_CR4","doi-asserted-by":"crossref","unstructured":"AntoniHGni L, Le Mauff B, Marcelli C, Aouba A, de Boysson H. Rhupus: a systematic literature review. Autoimmun Rev. 2020:102612.","DOI":"10.1016\/j.autrev.2020.102612"},{"key":"284_CR5","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1002\/art.20999","volume":"52","author":"D Alarc\u00f3n-Segovia","year":"2005","unstructured":"Alarc\u00f3n-Segovia D, Alarc\u00f3n\u2010Riquelme ME, Cardiel MH, Caeiro F, Massardo L, Villa AR, et al. Familial aggregation of systemic lupus erythematosus, rheumatoid arthritis, and other autoimmune diseases in 1,177 lupus patients from the GLADEL cohort. Arthritis Rheum. 2005;52:1138\u201347.","journal-title":"Arthritis Rheum"},{"key":"284_CR6","doi-asserted-by":"publisher","first-page":"e1002254","DOI":"10.1371\/journal.pgen.1002254","volume":"7","author":"C Cotsapas","year":"2011","unstructured":"Cotsapas C, Voight BF, Rossin E, Lage K, Neale BM, Wallace C, et al. Pervasive sharing of genetic effects in autoimmune disease. PLoS Genet. 2011;7:e1002254.","journal-title":"PLoS Genet."},{"key":"284_CR7","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.jaut.2013.01.008","volume":"41","author":"Y Cui","year":"2013","unstructured":"Cui Y, Sheng Y, Zhang X. Genetic susceptibility to SLE: recent progress from GWAS. J Autoimmun. 2013;41:25\u201333.","journal-title":"J Autoimmun"},{"key":"284_CR8","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/nrrheum.2012.237","volume":"9","author":"S Viatte","year":"2013","unstructured":"Viatte S, Plant D, Raychaudhuri S. Genetics and epigenetics of rheumatoid arthritis. Nature Reviews Rheumatology. 2013;9:141.","journal-title":"Nature Reviews Rheumatology"},{"key":"284_CR9","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.1136\/ard.2011.150326","volume":"70","author":"BW Higgs","year":"2011","unstructured":"Higgs BW, Liu Z, White B, Zhu W, White WI, Morehouse C, et al. Patients with systemic lupus erythematosus, myositis, rheumatoid arthritis and scleroderma share activation of a common type I interferon pathway. Ann Rheum Dis. 2011;70:2029\u201336.","journal-title":"Ann Rheum Dis"},{"key":"284_CR10","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1056\/NEJM197804202981602","volume":"298","author":"P Stastny","year":"1978","unstructured":"Stastny P. Association of the B-cell alloantigen DRw4 with rheumatoid arthritis. New England journal of medicine. 1978;298:869\u201371.","journal-title":"New England journal of medicine"},{"key":"284_CR11","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1136\/annrheumdis-2018-214125","volume":"78","author":"Z Zhao","year":"2019","unstructured":"Zhao Z, Ren J, Dai C, Kannapell CC, Wang H, Gaskin F, et al. Nature of T cell epitopes in lupus antigens and HLA-DR determines autoantibody initiation and diversification. Ann Rheum Dis. 2019;78:380\u201390.","journal-title":"Ann Rheum Dis"},{"key":"284_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-0229-3","volume":"3","author":"I Stafford","year":"2020","unstructured":"Stafford I, Kellermann M, Mossotto E, Beattie R, MacArthur B, Ennis S. A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases. NPJ digital medicine. 2020;3:1\u201311.","journal-title":"NPJ digital medicine"},{"key":"284_CR13","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1007\/s00439-012-1194-y","volume":"131","author":"J Kruppa","year":"2012","unstructured":"Kruppa J, Ziegler A, K\u00f6nig IR. Risk estimation and risk prediction using machine-learning methods. Hum Genet. 2012;131:1639\u201354.","journal-title":"Hum Genet"},{"key":"284_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13075-017-1414-x","volume":"19","author":"YB Joo","year":"2017","unstructured":"Joo YB, Kim Y, Park Y, Kim K, Ryu JA, Lee S, et al. Biological function integrated prediction of severe radiographic progression in rheumatoid arthritis: a nested case control study. Arthritis research & therapy. 2017;19:1\u20139.","journal-title":"Arthritis research & therapy"},{"key":"284_CR15","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1002\/gepi.21608","volume":"36","author":"RT Guy","year":"2012","unstructured":"Guy RT, Santago P, Langefeld CD. Bootstrap Aggregating of Alternating Decision Trees to Detect Sets of SNP s That Associate With Disease. Genet Epidemiol. 2012;36:99\u2013106.","journal-title":"Genet Epidemiol"},{"key":"284_CR16","doi-asserted-by":"publisher","first-page":"e0207926","DOI":"10.1371\/journal.pone.0207926","volume":"13","author":"F Ceccarelli","year":"2018","unstructured":"Ceccarelli F, Sciandrone M, Perricone C, Galvan G, Cipriano E, Galligari A, et al. Biomarkers of erosive arthritis in systemic lupus erythematosus: Application of machine learning models. PLoS One. 2018;13:e0207926.","journal-title":"PLoS One"},{"key":"284_CR17","doi-asserted-by":"publisher","first-page":"2569","DOI":"10.1002\/art.27584","volume":"62","author":"D Aletaha","year":"2010","unstructured":"Aletaha D, Neogi T, Silman AJ, Funovits J, Felson DT, Bingham III CO, et al. 2010 rheumatoid arthritis classification criteria: an American College of Rheumatology\/European League Against Rheumatism collaborative initiative. Arthritis Rheum. 2010;62:2569\u201381.","journal-title":"Arthritis Rheum"},{"key":"284_CR18","doi-asserted-by":"publisher","first-page":"2677","DOI":"10.1002\/art.34473","volume":"64","author":"M Petri","year":"2012","unstructured":"Petri M, Orbai AM, Alarc\u00f3n GS, Gordon C, Merrill JT, Fortin PR, et al. Derivation and validation of the Systemic Lupus International Collaborating Clinics classification criteria for systemic lupus erythematosus. Arthritis Rheum. 2012;64:2677\u201386.","journal-title":"Arthritis Rheum"},{"key":"284_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41525-021-00178-9","volume":"6","author":"C-Y Wei","year":"2021","unstructured":"Wei C-Y, Yang J-H, Yeh E-C, Tsai M-F, Kao H-J, Lo C-Z, et al. Genetic profiles of 103,106 individuals in the Taiwan Biobank provide insights into the health and history of Han Chinese. NPJ genomic medicine. 2021;6:1\u201310.","journal-title":"NPJ genomic medicine"},{"key":"284_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep36671","volume":"6","author":"B Mieth","year":"2016","unstructured":"Mieth B, Kloft M, Rodr\u00edguez JA, Sonnenburg S, Vobruba R, Morcillo-Su\u00e1rez C, et al. Combining multiple hypothesis testing with machine learning increases the statistical power of genome-wide association studies. Sci Rep. 2016;6:1\u201314.","journal-title":"Sci Rep"},{"key":"284_CR21","doi-asserted-by":"publisher","first-page":"e0232103","DOI":"10.1371\/journal.pone.0232103","volume":"15","author":"B-L Romero-Rosales","year":"2020","unstructured":"Romero-Rosales B-L, Tamez-Pena J-G, Nicolini H, Moreno-Trevi\u00f1o M-G, Trevino V. Improving predictive models for Alzheimer\u2019s disease using GWAS data by incorporating misclassified samples modeling. PLoS One. 2020;15:e0232103.","journal-title":"PLoS One"},{"key":"284_CR22","doi-asserted-by":"crossref","unstructured":"Cheng B, Ning Y, Liang C, Li P, Liu L, Cheng S, et al. Genome-Wide Association Analysis Identified ANXA1 Associated with Shoulder Impingement Syndrome in UK Biobank Samples. G3: Genes, Genomes, Genetics. 2020;10:3279-84.","DOI":"10.1534\/g3.120.401257"},{"key":"284_CR23","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1007\/s11277-019-06986-8","volume":"111","author":"A Verma","year":"2020","unstructured":"Verma A, Ranga V. Machine learning based intrusion detection systems for IoT applications. Wireless Personal Communications. 2020;111:2287\u2013310.","journal-title":"Wireless Personal Communications"},{"key":"284_CR24","doi-asserted-by":"publisher","first-page":"237","DOI":"10.3389\/fgene.2018.00237","volume":"9","author":"B Li","year":"2018","unstructured":"Li B, Zhang N, Wang Y-G, George AW, Reverter A, Li Y. Genomic prediction of breeding values using a subset of SNPs identified by three machine learning methods. Frontiers in genetics. 2018;9:237.","journal-title":"Frontiers in genetics"},{"key":"284_CR25","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1080\/09599916.2020.1832558","volume":"38","author":"WK Ho","year":"2021","unstructured":"Ho WK, Tang B-S, Wong SW. Predicting property prices with machine learning algorithms. Journal of Property Research. 2021;38:48\u201370.","journal-title":"Journal of Property Research"},{"key":"284_CR26","unstructured":"Lundberg S, Lee S-I. A unified approach to interpreting model predictions. arXiv preprint arXiv:170507874. 2017."},{"key":"284_CR27","doi-asserted-by":"publisher","first-page":"633","DOI":"10.3390\/jcm10040633","volume":"10","author":"E Kang","year":"2021","unstructured":"Kang E, Jang J, Choi CH, Kang SB, Bang KB, Kim TO, et al. Development of a Clinical and Genetic Prediction Model for Early Intestinal Resection in Patients with Crohn\u2019s Disease: Results from the IMPACT Study. Journal of clinical medicine. 2021;10:633.","journal-title":"Journal of clinical medicine"},{"key":"284_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-66907-9","volume":"10","author":"H Behravan","year":"2020","unstructured":"Behravan H, Hartikainen JM, Tengstr\u00f6m M, Kosma VM, Mannermaa A. Predicting breast cancer risk using interacting genetic and demographic factors and machine learning. Sci Rep. 2020;10:1\u201316.","journal-title":"Sci Rep"},{"key":"284_CR29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1002\/sam.11456","volume":"13","author":"LC Jung","year":"2020","unstructured":"Jung LC, Wang H, Li X, Wu C. A machine learning method for selection of genetic variants to increase prediction accuracy of type 2 diabetes mellitus using sequencing data. Statistical Analysis and Data Mining: The ASA Data Science Journal. 2020;13:261\u201381.","journal-title":"Statistical Analysis and Data Mining: The ASA Data Science Journal"},{"key":"284_CR30","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1038\/tpj.2013.18","volume":"14","author":"X Zheng","year":"2014","unstructured":"Zheng X, Shen J, Cox C, Wakefield JC, Ehm MG, Nelson MR, et al. HIBAG\u2014HLA genotype imputation with attribute bagging. The pharmacogenomics journal. 2014;14:192\u2013200.","journal-title":"The pharmacogenomics journal"},{"key":"284_CR31","first-page":"389","volume":"12","author":"H Lu","year":"2021","unstructured":"Lu H, Zhang J, Jiang Z, Zhang M, Wang T, Zhao H, et al. Detection of Genetic Overlap Between Rheumatoid Arthritis and Systemic Lupus Erythematosus Using GWAS Summary Statistics. Frontiers in genetics. 2021;12:389.","journal-title":"Frontiers in genetics"},{"key":"284_CR32","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1056\/NEJMoa073003","volume":"357","author":"EF Remmers","year":"2007","unstructured":"Remmers EF, Plenge RM, Lee AT, Graham RR, Hom G, Behrens TW, et al. STAT4 and the risk of rheumatoid arthritis and systemic lupus erythematosus. New England Journal of Medicine. 2007;357:977\u201386.","journal-title":"New England Journal of Medicine"},{"key":"284_CR33","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1002\/art.20771","volume":"52","author":"G Orozco","year":"2005","unstructured":"Orozco G, S\u00e1nchez E, Gonz\u00e1lez-Gay MA, L\u00f3pez\u2010Nevot MA, Torres B, C\u00e1liz R, et al. Association of a functional single\u2010nucleotide polymorphism of PTPN22, encoding lymphoid protein phosphatase, with rheumatoid arthritis and systemic lupus erythematosus. Arthritis & Rheumatism: Official Journal of the American College of Rheumatology. 2005;52:219\u201324.","journal-title":"Arthritis & Rheumatism: Official Journal of the American College of Rheumatology"},{"key":"284_CR34","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1016\/S0022-2836(03)00750-2","volume":"331","author":"PA Reche","year":"2003","unstructured":"Reche PA, Reinherz EL. Sequence variability analysis of human class I and class II MHC molecules: functional and structural correlates of amino acid polymorphisms. J Mol Biol. 2003;331:623\u201341.","journal-title":"J Mol Biol"},{"key":"284_CR35","doi-asserted-by":"crossref","unstructured":"Dietterich TG. Ensemble methods in machine learning. International workshop on multiple classifier systems;2000:Springer;2000. p.\u00a01-15.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"284_CR36","doi-asserted-by":"publisher","first-page":"e1008092","DOI":"10.1371\/journal.pgen.1008092","volume":"15","author":"JE Molineros","year":"2019","unstructured":"Molineros JE, Looger LL, Kim K, Okada Y, Terao C, Sun C, et al. Amino acid signatures of HLA Class-I and II molecules are strongly associated with SLE susceptibility and autoantibody production in Eastern Asians. PLoS Genet. 2019;15:e1008092.","journal-title":"PLoS Genet"},{"key":"284_CR37","doi-asserted-by":"publisher","first-page":"e0150283","DOI":"10.1371\/journal.pone.0150283","volume":"11","author":"K Kim","year":"2016","unstructured":"Kim K, Bang S-Y, Yoo DH, Cho S-K, Choi C-B, Sung Y-K, et al. Imputing variants in HLA-DR beta genes reveals that HLA-DRB1 is solely associated with rheumatoid arthritis and systemic lupus erythematosus. PLoS One. 2016;11:e0150283.","journal-title":"PLoS One"},{"key":"284_CR38","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1002\/art.39504","volume":"68","author":"ME Alarc\u00f3n-Riquelme","year":"2016","unstructured":"Alarc\u00f3n-Riquelme ME, Ziegler JT, Molineros J, Howard TD, Moreno\u2010Estrada A, S\u00e1nchez\u2010Rodr\u00edguez E, et al. Genome\u2010wide association study in an Amerindian ancestry population reveals novel systemic lupus erythematosus risk loci and the role of European admixture. Arthritis & rheumatology. 2016;68:932\u201343.","journal-title":"Arthritis & rheumatology"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-021-00284-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-021-00284-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-021-00284-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,11]],"date-time":"2021-12-11T13:03:36Z","timestamp":1639227816000},"score":1,"resource":{"primary":{"URL":"https:\/\/biodatamining.biomedcentral.com\/articles\/10.1186\/s13040-021-00284-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["284"],"URL":"https:\/\/doi.org\/10.1186\/s13040-021-00284-5","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"13 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study has been carried out in accordance with The Code of Ethics of the World Medical Association (Declaration of Helsinki). The Ethics Committee of Taichung Veterans General Hospital reviewed and approved our study (SF19153A), and informed consent was obtained from each participant.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no conflicts of interest to declare.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"52"}}