{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T11:30:40Z","timestamp":1789471840783,"version":"build-2803163510"},"reference-count":32,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J cachexia sarcopenia muscle"],"published-print":{"date-parts":[[2023,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early detection and management of sarcopenia is of clinical importance. We aimed to develop a chest X\u2010ray\u2010based deep learning model to predict presence of sarcopenia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Data of participants who visited osteoporosis clinic at Severance Hospital, Seoul, South Korea, between January 2020 and June 2021 were used as derivation cohort as split to train, validation and test set (65:15:20). A community\u2010based older adults cohort (KURE) was used as external test set. Sarcopenia was defined based on Asian Working Group 2019 guideline. A deep learning model was trained to predict appendicular lean mass (ALM), handgrip strength (HGS) and chair rise test performance from chest X\u2010ray images; then the machine learning model (SARC\u2010CXR score) was built using the age, sex, body mass index and chest X\u2010ray predicted muscle parameters along with estimation uncertainty values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Mean age of the derivation cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a0926; women\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a0700, 76%; sarcopenia\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a0141, 15%) and the external test (\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a0149; women\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a095, 64%; sarcopenia\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a018, 12%) cohort was 61.4 and 71.6\u00a0years, respectively. In the internal test set (a hold\u2010out set,\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a0189, from the derivation cohort) and the external test set (\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a0149), the concordance correlation coefficient for ALM prediction was 0.80 and 0.76, with an average difference of 0.18\u00a0\u00b1\u00a02.71 and 0.21\u00a0\u00b1\u00a02.28, respectively. Gradient\u2010weight class activation mapping for deep neural network models to predict ALM and HGS commonly showed highly weight pixel values at bilateral lung fields and part of the cardiac contour. SARC\u2010CXR score showed good discriminatory performance for sarcopenia in both internal test set [area under the receiver\u2010operating characteristics curve (AUROC) 0.813, area under the precision\u2010recall curve (AUPRC) 0.380, sensitivity 0.844, specificity 0.739, F1\u2010score 0.540] and external test set (AUROC 0.780, AUPRC 0.440, sensitivity 0.611, specificity 0.855, F1\u2010score 0.458). Among SARC\u2010CXR model features, predicted low ALM from chest X\u2010ray was the most important predictor of sarcopenia based on SHapley Additive exPlanations values. Higher estimation uncertainty of HGS contributed to elevate the predicted risk of sarcopenia. In internal test set, SARC\u2010CXR score showed better discriminatory performance than SARC\u2010F score (AUROC 0.813 vs. 0.691,\n                      <jats:italic>P<\/jats:italic>\n                      \u00a0=\u00a00.029).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Chest X\u2010ray\u2010based deep leaning model improved detection of sarcopenia, which merits further investigation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jcsm.13144","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T05:13:08Z","timestamp":1669957988000},"page":"418-428","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Chest X\u2010ray\u2010based opportunistic screening of sarcopenia using deep learning"],"prefix":"10.1002","volume":"14","author":[{"given":"Jin","family":"Ryu","sequence":"first","affiliation":[{"name":"Department of Internal Medicine, Severance Hospital, Endocrine Research Institute Yonsei University College of Medicine  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujeong","family":"Eom","sequence":"additional","affiliation":[{"name":"Department of Biomedical Systems Informatics Yonsei University College of Medicine  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeon Chang","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Systems Informatics Yonsei University College of Medicine  Seoul South Korea"},{"name":"Institute for Innovation in Digital Healthcare Yonsei University  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang Oh","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of Geriatrics, Department of Internal Medicine Yonsei University College of Medicine  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumie","family":"Rhee","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Severance Hospital, Endocrine Research Institute Yonsei University College of Medicine  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seng Chan","family":"You","sequence":"additional","affiliation":[{"name":"Department of Biomedical Systems Informatics Yonsei University College of Medicine  Seoul South Korea"},{"name":"Institute for Innovation in Digital Healthcare Yonsei University  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8246-1956","authenticated-orcid":false,"given":"Namki","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Severance Hospital, Endocrine Research Institute Yonsei University College of Medicine  Seoul South Korea"},{"name":"Institute for Innovation in Digital Healthcare Yonsei University  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,12]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afy106"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1159\/000517099"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2015.02.006"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.12757"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/gerona\/glu012"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afy169"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2019.12.012"},{"key":"e_1_2_7_9_1","first-page":"574","article-title":"Chest radiography in general practice: indications, diagnostic yield and consequences for patient management","volume":"56","author":"Speets AM","year":"2006","journal-title":"Br J Gen Pract"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(21)00146-1"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.7416"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/jbmr.4477"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/sam.11583"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.12048"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2019-031018"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2318-14-33"},{"key":"e_1_2_7_17_1","unstructured":"LakshminarayananB PritzelA BlundellC.Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems.2017;30.https:\/\/doi.org\/10.48550\/arXiv.1612.01474"},{"key":"e_1_2_7_18_1","unstructured":"SimonyanK ZissermanA.Very deep convolutional networks for large\u2010scale image recognition. arXiv preprint arXiv:140915562014.https:\/\/doi.org\/10.48550\/arXiv.1409.1556"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.2307\/2987937"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/bjs.9736"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.k1479"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00367-3"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m1328"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12603-018-1072-y"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/ajcn\/73.4.827"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000012281"},{"key":"e_1_2_7_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12890-020-1155-5"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.12603"},{"key":"e_1_2_7_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF03324942"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2021.101034"}],"container-title":["Journal of Cachexia, Sarcopenia and Muscle"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcsm.13144","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jcsm.13144","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcsm.13144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T08:57:31Z","timestamp":1692435451000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jcsm.13144"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["10.1002\/jcsm.13144"],"URL":"https:\/\/doi.org\/10.1002\/jcsm.13144","archive":["Portico"],"relation":{},"ISSN":["2190-5991","2190-6009"],"issn-type":[{"value":"2190-5991","type":"print"},{"value":"2190-6009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]},"assertion":[{"value":"2022-06-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-31","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}