{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:31:41Z","timestamp":1783009901652,"version":"3.54.5"},"reference-count":43,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["PZ00P3_186101"],"award-info":[{"award-number":["PZ00P3_186101"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["JOR Spine"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate computation of radiological parameters related to spinal alignment is clinically crucial for diagnosing and managing conditions, such as adolescent idiopathic scoliosis and adult spinal deformities. Key parameters, including sacral slope, pelvic tilt, pelvic incidence, and lumbar lordosis, are required to assess lumbosacral alignment. Artificial Intelligence (AI) has demonstrated strong potential in automating these assessments, reducing clinician workload and improving consistency. However, AI models require large, diverse, high\u2010quality datasets to perform reliably across different clinical settings. Privacy concerns and data ownership issues often hinder data sharing, limiting the creation of centralized datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we demonstrate that federated learning (FL) enables the training of deep learning models across four hospitals without compromising patient privacy. In particular, we compared FL against a centralized approach, where data from all the hospitals are pooled together and a model is trained on them, and a local approach consisting of training individual models exclusively on data from each respective hospital, resulting in distinct hospital\u2010specific models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>FL achieved performance comparable to centralized training (errors ~5\u00b0), where data is pooled, and consistently outperformed models trained on data from individual hospitals, both in internal (~8\u00b0) and external (~10\u00b0) testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This work highlights FL as a viable solution for collaborative AI development in spinal imaging, facilitating the use of diverse, multi\u2010institutional data while circumventing privacy barriers and complex data\u2010sharing agreements. Additionally, FL demonstrates particular benefits for smaller hospitals, enabling them to achieve superior model performance by effectively leveraging data from hospitals with larger datasets.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jsp2.70120","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T19:32:26Z","timestamp":1760643146000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Simulating Federated Learning to Enable Multi\u2010Hospital Collaboration for Lumbopelvic Alignment Estimation"],"prefix":"10.1002","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6016-6200","authenticated-orcid":false,"given":"Andrea","family":"Cina","sequence":"first","affiliation":[{"name":"Department of Health Sciences and Technology (D\u2010HEST), ETH Zurich Universit\u00e4tstrasse 2  Z\u00fcrich Switzerland"},{"name":"Schulthess Clinic, Department of Teaching, Research and Development  Z\u00fcrich Switzerland"},{"name":"Swiss Institute of Bioinformatics (SIB)  Lausanne Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miklovana","family":"Tuci","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology (D\u2010HEST), ETH Zurich Universit\u00e4tstrasse 2  Z\u00fcrich Switzerland"},{"name":"Spinal Cord Injury Center University Hospital Balgrist, University of Z\u00fcrich  Z\u00fcrich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0644-7757","authenticated-orcid":false,"given":"Ferran","family":"Pellis\u00e9","sequence":"additional","affiliation":[{"name":"Spine Research Unit Vall d'Hebron Research Institute  Barcelona Spain"},{"name":"Spine Surgery Unit Vall d'Hebron University Hospital  Barcelona Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caglar","family":"Yilgor","sequence":"additional","affiliation":[{"name":"Department of Orthopedics and Traumatology Acibadem University  Istanbul Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet","family":"Alanay","sequence":"additional","affiliation":[{"name":"Department of Orthopedics and Traumatology Acibadem University  Istanbul Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Pizones","sequence":"additional","affiliation":[{"name":"Spine Surgery Unit La Paz University Hospital  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Kleinst\u00fcck","sequence":"additional","affiliation":[{"name":"Spine Center Division Schulthess Clinic  Zurich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ibrahim","family":"Obeid","sequence":"additional","affiliation":[{"name":"Spine Surgery Unit Bordeaux University Hospital  Bordeaux France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yann Philippe","family":"Charles","sequence":"additional","affiliation":[{"name":"Department of Spine Surgery University Hospital of Strasbourg  Strasbourg France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Richner\u2010Wunderlin","sequence":"additional","affiliation":[{"name":"Schulthess Clinic, Department of Teaching, Research and Development  Z\u00fcrich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1826-9190","authenticated-orcid":false,"given":"Fabio","family":"Galbusera","sequence":"additional","affiliation":[{"name":"Schulthess Clinic, Department of Teaching, Research and Development  Z\u00fcrich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine R.","family":"Jutzeler","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology (D\u2010HEST), ETH Zurich Universit\u00e4tstrasse 2  Z\u00fcrich Switzerland"},{"name":"Swiss Institute of Bioinformatics (SIB)  Lausanne Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"European Spine Study Group","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-818438-7.00002-2"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2022.04.001"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102779"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586\u2010019\u201005944\u2010z"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010021\u201089102\u2010w"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.3171\/2022.5.SPINE22109"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586\u2010023\u201008109\u20101"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742\u20106596\/1187\/4\/042100"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586\u2010022\u201007245\u20104"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_2_8_13_1","unstructured":"A.Kuznetsova H.Rom N.Alldrin et\u00a0al. \u201cThe Open Images Dataset V4: Unified Image Classification Object Detection and Visual Relationship Detection at Scale \u201darXiv [csCV] (2018) http:\/\/arxiv.org\/abs\/1811.00982."},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010009\u20100275\u20104"},{"key":"e_1_2_8_15_1","unstructured":"K.He X.Zhang S.Ren andJ.Sun \u201cDeep Residual Learning for Image Recognition \u201darXiv [csCV] (2015) http:\/\/arxiv.org\/abs\/1512.03385."},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_8_18_1","unstructured":"Y.Wu A.Kirillov F.Massa W. Y.Lo andR.Girshick \u201cDetectron2 \u201d(2019) https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010024\u201018543\u2010y"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30292-2"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1530\/EOR\u201024\u20100019"},{"key":"e_1_2_8_22_1","unstructured":"H. B.McMahan E.Moore D.Ramage S.Hampson andy.Arcas BA \u201cCommunication\u2010Efficient Learning of Deep Networks From Decentralized Data \u201darXiv [csLG] (2016) http:\/\/arxiv.org\/abs\/1602.05629."},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010022\u201033407\u20105"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201051172\u20105"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501296"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13193140"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586\u2010024\u201008172\u20102"},{"key":"e_1_2_8_28_1","unstructured":"S.Reddi Z.Charles M.Zaheer et\u00a0al. \u201cAdaptive Federated Optimization \u201darXiv [csLG] (2020) http:\/\/arxiv.org\/abs\/2003.00295."},{"key":"e_1_2_8_29_1","first-page":"429","volume-title":"Proceedings of Machine Learning and Systems","author":"Li T.","year":"2020"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1097\/BRS.0b013e3181aad219"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clineuro.2015.10.024"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj\u20102023\u2010078378"},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"A.Newell K.Yang andJ.Deng \u201cStacked Hourglass Networks for Human Pose Estimation \u201darXiv [csCV] (2016) http:\/\/arxiv.org\/abs\/1603.06937.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.10.021"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11063\u2010023\u201011212\u20105"},{"key":"e_1_2_8_37_1","unstructured":"A.Nibali Z.He S.Morgan andL.Prendergast \u201cNumerical Coordinate Regression With Convolutional Neural Networks \u201darXiv (2018) http:\/\/arxiv.org\/abs\/1801.07372."},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1177\/21925682231205352"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3412357"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201038569\u20104"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105451"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010021\u201001506\u20103"},{"key":"e_1_2_8_43_1","first-page":"5132","volume-title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","author":"Karimireddy S. P.","year":"2019"},{"key":"e_1_2_8_44_1","first-page":"14068","volume-title":"Advances in Neural Information Processing Systems","author":"He C.","year":"2020"}],"container-title":["JOR SPINE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jsp2.70120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T01:12:08Z","timestamp":1766970728000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jsp2.70120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1002\/jsp2.70120"],"URL":"https:\/\/doi.org\/10.1002\/jsp2.70120","archive":["Portico"],"relation":{},"ISSN":["2572-1143","2572-1143"],"issn-type":[{"value":"2572-1143","type":"print"},{"value":"2572-1143","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"2025-07-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70120"}}