{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T17:14:02Z","timestamp":1788369242759,"version":"build-2803163510"},"reference-count":27,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100011033","name":"Agencia Estatal de Investigaci\u00f3n","doi-asserted-by":"publisher","award":["PID2023-147198NB-I00"],"award-info":[{"award-number":["PID2023-147198NB-I00"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Proc Inst Mech Eng H"],"abstract":"<jats:p>\n                    Osteoporosis is a prevalent condition with substantial health and economic implications. Although physical activity is associated with bone health, the specific temporal activity patterns related to bone mineral status remain insufficiently understood. This proof-of-concept study evaluated whether convolutional neural networks (CNNs) applied to Gramian Angular Field (GAF) representations of MIMS-derived wrist accelerometry data could predict femoral neck T-score and classify normal bone status versus osteopenia\/osteoporosis. Data from 2504 participants in NHANES 2013\u20132014 were analyzed, including DXA-derived femoral neck measures, age, sex, body mass, and 7\u2009days of wrist-worn accelerometry. Minute-level MIMS data were averaged into 10-min intervals and transformed into seven-channel GAF images. VGG-like and ResNet-like CNNs were trained from scratch using an internal validation set for early stopping and evaluated on a held-out test set. In classification, the VGG model achieved the best CNN performance, with test accuracy of 71.3%, sensitivity of 61.5%, specificity of 77.5%,\n                    <jats:italic toggle=\"yes\">F<\/jats:italic>\n                    1-score of 0.625, and ROC-AUC of 0.780. In regression, the VGG model also performed best among CNNs, with test\n                    <jats:italic toggle=\"yes\">R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    of 0.305, MSE of 1.095, RMSE of 1.047, and MAE of 0.789. Demographic-only baseline models showed comparable or slightly better performance, indicating that age, sex, and body mass carried substantial predictive information. These findings support the feasibility of GAF-CNN modeling of accelerometry-derived activity patterns for bone-health research, while emphasizing the exploratory nature of the approach and the need for further validation.\n                  <\/jats:p>","DOI":"10.1177\/09544119261484225","type":"journal-article","created":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T17:13:55Z","timestamp":1788110035000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning approaches to predict femoral neck T-score and osteopenia\/osteoporosis status from wrist accelerometry data"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1830-8236","authenticated-orcid":false,"given":"Horacio","family":"Sanchez-Trigo","sequence":"first","affiliation":[{"name":"Physical Education and Sports Department, University of Seville, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vahid","family":"Farrahi","sequence":"additional","affiliation":[{"name":"Institute for Sports and Sport Science, TU Dortmund University, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo","family":"Gamboa","sequence":"additional","affiliation":[{"name":"Laborat\u00f3rio de Instrumenta\u00e7\u00e3o, Engenharia Biom\u00e9dica e F\u00edsica da Radia\u00e7\u00e3o (LIBPhys-UNL), Departamento de F\u00edsica, Faculdade de Ci\u00eancias e Tecnologia, Universidade Nova de Lisboa, Caparica, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Solis-Mart\u00edn","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, University of Seville, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,8,30]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: report of a WHO study group","author":"World Health Organisation","year":"1994","unstructured":"World Health Organisation. Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: report of a WHO study group. World Health Organisation, 1994."},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Hernlund E Svedbom A Iverg\u00e5rd M et al. Osteoporosis in the European Union: medical management epidemiology and economic burden. A report prepared in collaboration with the International Osteoporosis Foundation (IOF) and the European Federation of Pharmaceutical Industry Associations (EFPIA). Arch Osteoporos 2013; 8: 136. https:\/\/doi.org\/10.1007\/s11657-013-0136-1","DOI":"10.1007\/s11657-013-0136-1"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Lewiecki EM Ortendahl JD Vanderpuye-Orgle J et al. Healthcare policy changes in osteoporosis can improve outcomes and reduce costs in the United States. JBMR Plus 2019; 3: e10192. https:\/\/doi.org\/10.1002\/jbm4.10192","DOI":"10.1002\/jbm4.10192"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Warburton DER Nicol CW Bredin SSD. Health benefits of physical activity: the evidence. Can Med Assoc J 2006; 174: 801\u2013809. https:\/\/doi.org\/10.1503\/cmaj.051351","DOI":"10.1503\/cmaj.051351"},{"key":"e_1_3_2_6_2","unstructured":"Frost HM. A 2003 update of bone physiology and Wolff\u2019s Law for Clinicians. Angle Orthod 2004; 74: 3\u201315. https:\/\/doi.org\/10.1043\/0003-3219(2004)074<2.0.CO;2"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Turner CH Robling AG. Mechanisms by which exercise improves bone strength. J Bone Miner Metab 2005; 23Suppl: 16\u201322. https:\/\/doi.org\/10.1007\/BF03026318\/METRICS","DOI":"10.1007\/BF03026318"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Turner CH Robling AG. Designing exercise regimens to increase bone strength. Exerc Sport Sci Rev 2003; 31: 45\u201350. https:\/\/doi.org\/10.1097\/00003677-200301000-00009","DOI":"10.1097\/00003677-200301000-00009"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Nikander R Siev\u00e4nen H Heinonen A et al. Targeted exercise against osteoporosis: a systematic review and meta-analysis for optimising bone strength throughout life. BMC Med 2010; 8: 47. https:\/\/doi.org\/10.1186\/1741-7015-8-47","DOI":"10.1186\/1741-7015-8-47"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Migueles JH Cadenas-Sanchez C Ekelund U et al. Accelerometer data collection and processing criteria to assess physical activity and other outcomes: a systematic review and practical considerations. Sports Med 2017; 47: 1821\u20131845. https:\/\/doi.org\/10.1007\/s40279-017-0716-0","DOI":"10.1007\/s40279-017-0716-0"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Esliger DW Copeland JL Barnes JD et al. Standardizing and optimizing the use of accelerometer data for free-living physical activity monitoring. J Phys Act Health 2005; 2: 366\u2013383. https:\/\/doi.org\/10.1123\/JPAH.2.3.366","DOI":"10.1123\/jpah.2.3.366"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Farrahi V Niemel\u00e4 M Kangas M et al. Calibration and validation of accelerometer-based activity monitors: a systematic review of machine-learning approaches. Gait Posture 2019; 68: 285\u2013299. https:\/\/doi.org\/10.1016\/j.gaitpost.2018.12.003","DOI":"10.1016\/j.gaitpost.2018.12.003"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"LeCun Y Bengio Y Hinton G. Deep learning. Nature 2015; 521: 436\u2013444. https:\/\/doi.org\/10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_14_2","first-page":"3939","volume-title":"IJCAI international joint conference on artificial intelligence 2015","author":"Wang Z","unstructured":"Wang Z, Oates T. Imaging time-series to improve classification and imputation. IJCAI international joint conference on artificial intelligence 2015, January 2015, pp.3939\u20133945."},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Farrahi V Muhammad U Rostami M et al. AccNet24: a deep learning framework for classifying 24-hour activity behaviours from wrist-worn accelerometer data under free-living environments. Int J Med Inform 2023; 172: 105004. https:\/\/doi.org\/10.1016\/j.ijmedinf.2023.105004","DOI":"10.1016\/j.ijmedinf.2023.105004"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Suh B Yu H Kim H et al. Interpretable deep-learning approaches for osteoporosis risk screening and individualized feature analysis using large population-based data: model development and performance evaluation. J Med Internet Res 2023; 25: e40179. https:\/\/doi.org\/10.2196\/40179","DOI":"10.2196\/40179"},{"key":"e_1_3_2_17_2","unstructured":"Koffman L III Muschelli J Crainiceanu C. Walking fingerprinting using wrist accelerometry during activities of daily living in NHANES [Preprint]. ArXiv 2025. https:\/\/doi.org\/10.48550\/arXiv.2506.17160"},{"key":"e_1_3_2_18_2","unstructured":"Centers for Disease Control and Prevention. National health and nutrition examination survey: data documentation codebook and frequencies for 2013\u20132014 survey cycle https:\/\/wwwn.cdc.gov\/nchs\/nhanes\/continuousnhanes\/default.aspx?BeginYear=2013 (2014 accessed 5 July 2026)."},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Looker AC Wahner HW Dunn WL et al. Updated data on proximal femur bone mineral levels of US adults. Osteoporos Int 1998; 8: 468\u2013489. https:\/\/doi.org\/10.1007\/S001980050093\/METRICS","DOI":"10.1007\/s001980050093"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"John D Tang Q Albinali F et al. An open-source monitor-independent movement summary for accelerometer data processing. J Meas Phys Behav 2019; 2: 268\u2013281. https:\/\/doi.org\/10.1123\/jmpb.2018-0068","DOI":"10.1123\/jmpb.2018-0068"},{"key":"e_1_3_2_21_2","unstructured":"Simonyan K Zisserman A. 2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556 2014."},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S et al. Deep residual learning for image recognition. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition 2016 December 2016 pp.770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Stampfler T Elgendi M Fletcher RR et al. The use of deep learning for smartphone-based human activity recognition. Front Public Health 2023; 11: 1086671. https:\/\/doi.org\/10.3389\/fpubh.2023.1086671","DOI":"10.3389\/fpubh.2023.1086671"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Kim SU Kim JY. Improving human activity recognition through 1D-ResNet: a wearable wristband for 14 workout movements. Processes 2025; 13: 207. https:\/\/doi.org\/10.3390\/pr13010207","DOI":"10.3390\/pr13010207"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Abu M Zahri NAH Amir A et al. A comprehensive performance analysis of transfer learning optimization in visual field defect classification. Diagnostics 2022; 12: 1258. https:\/\/doi.org\/10.3390\/diagnostics12051258","DOI":"10.3390\/diagnostics12051258"},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Alsaad LN Abdulameer JA Akolaa EA et al. Bone mineral density and its determinants: a systematic review of risk factors and prevention strategies. Biomed Pharmacol J 2023; 16: 1791\u20131796. https:\/\/doi.org\/10.13005\/bpj\/2758","DOI":"10.13005\/bpj\/2758"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Ni J Zhao Z Shen C et al. Harnessing vision models for time series analysis: a survey. In: Proceedings of the thirty-fourth international joint conference on artificial intelligence 2025 pp.10612\u201310620. https:\/\/doi.org\/10.24963\/ijcai.2025\/1178","DOI":"10.24963\/ijcai.2025\/1178"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Mikkil\u00e4 S Handeg\u00e5rd BH Johansson J et al. Cross-sectional associations between accelerometer-measured physical activity and hip bone mineral density: the Troms\u00f8 Study 2015-2016. JBMR Plus 2024; 8: ziae061. https:\/\/doi.org\/10.1093\/jbmrpl\/ziae061","DOI":"10.1093\/jbmrpl\/ziae061"}],"container-title":["Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09544119261484225","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/09544119261484225","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09544119261484225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T16:27:26Z","timestamp":1788366446000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/09544119261484225"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,30]]},"references-count":27,"alternative-id":["10.1177\/09544119261484225"],"URL":"https:\/\/doi.org\/10.1177\/09544119261484225","relation":{},"ISSN":["0954-4119","2041-3033"],"issn-type":[{"value":"0954-4119","type":"print"},{"value":"2041-3033","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,30]]},"article-number":"09544119261484225"}}