{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:45:51Z","timestamp":1790268351433,"version":"4.1.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82260455"],"award-info":[{"award-number":["82260455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82260455"],"award-info":[{"award-number":["82260455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82260455"],"award-info":[{"award-number":["82260455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Energy expenditure (EE) assessment is crucial in both sports science and health management. However, current EE prediction models often overlook individual differences and lack dynamic correlation analysis between multi-modal data and EE. Building upon previous research, this study proposes a personalized dynamic-static feature fusion framework, which integrates two types of information to improve energy expenditure (EE) prediction during incremental load exercise: dynamic signals (physiological signals recorded continuously during exercise, such as tri-axial acceleration and electrocardiography [ECG]) and static physiological metrics (stable individual traits measured at rest, such as BMI, body-fat percentage, resting heart rate, and resting oxygen uptake [VO<jats:sub>2<\/jats:sub>]). These two feature sets were combined through a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) neural network architecture. CNN layers extract local temporal patterns from dynamic signals, and LSTM layers model temporal dependencies over longer intervals. The model prediction performance was evaluated using root mean square error (RMSE), coefficient of determination (R\u00b2), mean absolute error (MAE) and Bland-Altman plots, and the results show that the CNN\u2009+\u2009LSTM model significantly outperforms both the traditional autoregressive (AR) linear model and the LSTM model that uses only a single modality (acceleration or ECG). Analysis of feature values and SHAP values revealed that accelerometer features played a dominant role in EE prediction during moderate-to-high intensity exercise. As exercise intensity increased, the contribution of ECG features gradually increased, with ECG features dominating during high-intensity exercise, demonstrating the complementary effect and dual contribution of these two types of features in EE prediction at different exercise intensities. This study demonstrates that personalized dynamic-static feature fusion can effectively predict EE during incremental exercise tests and analyzes the dynamic changes in the contribution of different features across different intensity ranges, providing a theoretical basis and methodological reference for related research.<\/jats:p>","DOI":"10.1038\/s41598-025-20195-3","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:56:35Z","timestamp":1760612195000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Interpretable deep learning for personalized energy expenditure prediction using ECG and acceleration signals in incremental exercise"],"prefix":"10.1038","volume":"15","author":[{"given":"Yingzhe","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingnan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangfang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"20195_CR1","doi-asserted-by":"crossref","unstructured":"Kang, K. H., Shin, S. H., Jung, J. & Kim, Y. T. Estimation of a physical activity energy expenditure with a patch-type sensor module using artificial neural network. Concurr Comput. Pract. Exp 33 (2021).","DOI":"10.1002\/cpe.5455"},{"key":"20195_CR2","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1007\/s00421-017-3641-x","volume":"117","author":"KR Westerterp","year":"2017","unstructured":"Westerterp, K. R. Doubly labelled water assessment of energy expenditure: principle, practice, and promise. Eur. J. Appl. Physiol. 117, 1277\u20131285 (2017).","journal-title":"Eur. J. Appl. Physiol."},{"key":"20195_CR3","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1139\/apnm-2015-0461","volume":"41","author":"JB Correa","year":"2016","unstructured":"Correa, J. B. et al. Evaluation of the ability of three physical activity monitors to predict weight change and estimate energy expenditure. Appl. Physiol. Nutr. Metab. 41, 758\u2013766 (2016).","journal-title":"Appl. Physiol. Nutr. Metab."},{"key":"20195_CR4","doi-asserted-by":"publisher","first-page":"1831","DOI":"10.1249\/MSS.0000000000000298","volume":"46","author":"O Tikkanen","year":"2014","unstructured":"Tikkanen, O. et al. Heart rate, and accelerometer as estimators of energy expenditure in locomotion. Med. Sci. Sports Exerc. 46, 1831\u20131839 (2014).","journal-title":"Med. Sci. Sports Exerc."},{"key":"20195_CR5","doi-asserted-by":"publisher","first-page":"8545","DOI":"10.3390\/s23208545","volume":"23","author":"WJ Wu","year":"2023","unstructured":"Wu, W. J., Yu, H. B., Tai, W. H., Zhang, R. & Hao, W. Y. Validity of actigraph for measuring energy expenditure in healthy adults: A systematic review and Meta-Analysis. Sensors 23, 8545 (2023).","journal-title":"Sensors"},{"key":"20195_CR6","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.jsams.2017.07.022","volume":"21","author":"PB Gastin","year":"2018","unstructured":"Gastin, P. B., Cayzer, C., Dwyer, D. & Robertson, S. Validity of the actigraph GT3X\u2009+\u2009and bodymedia sensewear armband to estimate energy expenditure during physical activity and sport. J. Sci. Med. Sport. 21, 291\u2013295 (2018).","journal-title":"J. Sci. Med. Sport"},{"key":"20195_CR7","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1080\/15568318.2019.1642971","volume":"14","author":"BPY Loo","year":"2020","unstructured":"Loo, B. P. Y., Leung, K. Y. K. & Chan, F. C. H. How short-term cycling training promotes cycling among schoolchildren in high-density cities. Int. J. Sustain. Transp. 14, 872\u2013885 (2020).","journal-title":"Int. J. Sustain. Transp."},{"key":"20195_CR8","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1093\/ajcn\/24.9.1139","volume":"24","author":"RB Andrews","year":"1971","unstructured":"Andrews, R. B. Net heart rate as a substitute for respiratory calorimetry. Am. J. Clin. Nutr. 24, 1139\u20131147 (1971).","journal-title":"Am. J. Clin. Nutr."},{"key":"20195_CR9","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1055\/s-1999-8829","volume":"20","author":"Hiilloskorpi","year":"1999","unstructured":"Hiilloskorpi et al. Factors affecting the relation between heart rate and energy expenditure during exercise. Int. J. Sports Med. 20, 438\u2013443 (1999).","journal-title":"Int. J. Sports Med."},{"key":"20195_CR10","doi-asserted-by":"publisher","first-page":"327","DOI":"10.2165\/11598900-000000000-00000","volume":"42","author":"L Isacco","year":"2012","unstructured":"Isacco, L., Duch\u00e9, P. & Boisseau, N. Influence of hormonal status on substrate utilization at rest and during exercise in the female population. Sports Med. 42, 327\u2013342 (2012).","journal-title":"Sports Med."},{"key":"20195_CR11","doi-asserted-by":"publisher","first-page":"e0224948","DOI":"10.1371\/journal.pone.0224948","volume":"14","author":"M Klass","year":"2019","unstructured":"Klass, M., Faoro, V. & Carpentier, A. Assessment of energy expenditure during high intensity cycling and running using a heart rate and activity monitor in young active adults. PLOS ONE. 14, e0224948 (2019).","journal-title":"PLOS ONE"},{"key":"20195_CR12","doi-asserted-by":"publisher","first-page":"035001","DOI":"10.1088\/1361-6579\/abea25","volume":"42","author":"L Kortelainen","year":"2021","unstructured":"Kortelainen, L. et al. A nonlinear mixed model approach to predict energy expenditure from heart rate. Physiol. Meas. 42, 035001 (2021).","journal-title":"Physiol. Meas."},{"key":"20195_CR13","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.1080\/02640414.2020.1746088","volume":"38","author":"R O\u2019Driscoll","year":"2020","unstructured":"O\u2019Driscoll, R. et al. Improving energy expenditure estimates from wearable devices: A machine learning approach. J. Sports Sci. 38, 1496\u20131505 (2020).","journal-title":"J. Sports Sci."},{"key":"20195_CR14","doi-asserted-by":"publisher","first-page":"12859","DOI":"10.1109\/JSEN.2020.3000772","volume":"20","author":"M Sevil","year":"2020","unstructured":"Sevil, M. et al. Determining physical activity characteristics from wristband data for use in automated insulin delivery systems. IEEE Sens. J. 20, 12859\u201312870 (2020).","journal-title":"IEEE Sens. J."},{"key":"20195_CR15","doi-asserted-by":"publisher","first-page":"8760","DOI":"10.1109\/JIOT.2020.2996578","volume":"7","author":"O Barut","year":"2020","unstructured":"Barut, O., Zhou, L. & Luo, Y. Multitask LSTM model for human activity recognition and intensity Estimation using wearable sensor data. IEEE Internet Things J. 7, 8760\u20138768 (2020).","journal-title":"IEEE Internet Things J."},{"key":"20195_CR16","doi-asserted-by":"publisher","first-page":"7913","DOI":"10.3390\/s22207913","volume":"22","author":"JM Lopes","year":"2022","unstructured":"Lopes, J. M. et al. Deep Learning-Based energy expenditure Estimation in assisted and Non-Assisted gait using inertial, EMG, and heart rate wearable sensors. Sensors 22, 7913 (2022).","journal-title":"Sensors"},{"key":"20195_CR17","doi-asserted-by":"publisher","first-page":"105381","DOI":"10.1016\/j.bspc.2023.105381","volume":"87","author":"VM Perez Cortes","year":"2024","unstructured":"Perez Cortes, V. M., Chatterjee, A. & Khovalyg, D. Dynamic personalized human body energy expenditure: prediction using time series forecasting LSTM models. Biomed. Signal. Process. Control. 87, 105381 (2024).","journal-title":"Biomed. Signal. Process. Control"},{"key":"20195_CR18","doi-asserted-by":"publisher","first-page":"216","DOI":"10.3390\/ijerph17010216","volume":"17","author":"Y Caballero","year":"2019","unstructured":"Caballero, Y. et al. Simple prediction of metabolic equivalents of daily activities using heart rate monitor without calibration of individuals. Int. J. Environ. Res. Public. Health. 17, 216 (2019).","journal-title":"Int. J. Environ. Res. Public. Health"},{"key":"20195_CR19","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.3390\/s19204509","volume":"19","author":"AK Chowdhury","year":"2019","unstructured":"Chowdhury, A. K., Tjondronegoro, D., Chandran, V., Zhang, J. & Trost, S. G. Prediction of relative physical activity intensity using multimodal sensing of physiological data. Sensors 19, 4509 (2019).","journal-title":"Sensors"},{"key":"20195_CR20","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1080\/02640414.2016.1221520","volume":"35","author":"D Kim","year":"2017","unstructured":"Kim, D. et al. Comparing the standards of one metabolic equivalent of task in accurately estimating physical activity energy expenditure based on acceleration. J. Sports Sci. 35, 1279\u20131286 (2017).","journal-title":"J. Sports Sci."},{"key":"20195_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1113\/jphysiol.1949.sp004363","volume":"109","author":"JB Weir","year":"1949","unstructured":"Weir, J. B. D. V. New methods for calculating metabolic rate with special reference to protein metabolism. J. Physiol. 109, 1\u20139 (1949).","journal-title":"J. Physiol."},{"key":"20195_CR22","doi-asserted-by":"publisher","unstructured":"Breunig, M. M., Kriegel, H. P., Ng, R. T. & Sander, J. LOF: identifying density-based local outliers. in Proceedings of the ACM SIGMOD international conference on Management of data 93\u2013104 (ACM, 2000). https:\/\/doi.org\/10.1145\/342009.335388","DOI":"10.1145\/342009.335388"},{"key":"20195_CR23","doi-asserted-by":"crossref","unstructured":"Xu, L. et al. Comparison of different prediction models for Estimation of walking and running energy expenditure based on a wristwear three-axis accelerometer. Front. Physiol. 14  (2023).","DOI":"10.3389\/fphys.2023.1202737"},{"key":"20195_CR24","doi-asserted-by":"publisher","first-page":"1954","DOI":"10.1249\/MSS.0000000000002002","volume":"51","author":"DP Looney","year":"2019","unstructured":"Looney, D. P. et al. Estimating energy expenditure during level, uphill, and downhill walking. Med. Sci. Sports Exerc. 51, 1954\u20131960 (2019).","journal-title":"Med. Sci. Sports Exerc."},{"key":"20195_CR25","doi-asserted-by":"publisher","first-page":"5092","DOI":"10.3390\/su13095092","volume":"13","author":"M Lee","year":"2021","unstructured":"Lee, M., Park, J. H., Seo, M. W., Kang, S. K. & Lee, J. M. A new equation to estimate energy expenditure using heart rate in children. Sustainability 13, 5092 (2021).","journal-title":"Sustainability"},{"key":"20195_CR26","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1017\/S0007114513000603","volume":"110","author":"K Ishikawa-Takata","year":"2013","unstructured":"Ishikawa-Takata, K., Kaneko, K., Koizumi, K. & Ito, C. Comparison of physical activity energy expenditure in Japanese adolescents assessed by EW4800P triaxial accelerometry and the doubly labelled water method. Br. J. Nutr. 110, 1347\u20131355 (2013).","journal-title":"Br. J. Nutr."},{"key":"20195_CR27","doi-asserted-by":"publisher","first-page":"2520","DOI":"10.3390\/s24082520","volume":"24","author":"M Vib\u00e6k","year":"2024","unstructured":"Vib\u00e6k, M., Peimankar, A., Wiil, U. K., Arvidsson, D. & Br\u00f8nd, J. C. Energy expenditure prediction from accelerometry data using long Short-Term memory recurrent neural networks. Sensors 24, 2520 (2024).","journal-title":"Sensors"},{"key":"20195_CR28","doi-asserted-by":"publisher","first-page":"4468","DOI":"10.3390\/s24144468","volume":"24","author":"S Andriolo","year":"2024","unstructured":"Andriolo, S., Rummel, M. & Gronwald, T. Relationship of cycling power and Non-Linear heart rate variability from everyday workout data: potential for intensity zone Estimation and monitoring. Sensors 24, 4468 (2024).","journal-title":"Sensors"},{"key":"20195_CR29","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1080\/17461391.2015.1004373","volume":"16","author":"D Saboul","year":"2016","unstructured":"Saboul, D., Balducci, P., Millet, G., Pialoux, V. & Hautier, C. A pilot study on quantification of training load: the use of HRV in training practice. Eur. J. Sport Sci. 16, 172\u2013181 (2016).","journal-title":"Eur. J. Sport Sci."},{"key":"20195_CR30","doi-asserted-by":"publisher","first-page":"1698","DOI":"10.3390\/s17071698","volume":"17","author":"H Park","year":"2017","unstructured":"Park, H., Dong, S. Y., Lee, M. & Youn, I. The role of Heart-Rate variability parameters in activity recognition and Energy-Expenditure Estimation using wearable sensors. Sensors 17, 1698 (2017).","journal-title":"Sensors"},{"key":"20195_CR31","doi-asserted-by":"publisher","first-page":"e0167472","DOI":"10.1371\/journal.pone.0167472","volume":"11","author":"T White","year":"2016","unstructured":"White, T., Westgate, K., Wareham, N. J. & Brage, S. Estimation of physical activity energy expenditure during Free-Living from wrist accelerometry in UK adults. PLOS ONE. 11, e0167472 (2016).","journal-title":"PLOS ONE"},{"key":"20195_CR32","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1136\/bjsports-2014-093546","volume":"48","author":"RP Troiano","year":"2014","unstructured":"Troiano, R. P., McClain, J. J., Brychta, R. J. & Chen, K. Y. Evolution of accelerometer methods for physical activity research. Br. J. Sports Med. 48, 1019\u20131023 (2014).","journal-title":"Br. J. Sports Med."},{"key":"20195_CR33","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1111\/cpf.12127","volume":"35","author":"H V\u00e4h\u00e4-Ypy\u00e4","year":"2015","unstructured":"V\u00e4h\u00e4-Ypy\u00e4, H., Vasankari, T., Husu, P., Suni, J. & Siev\u00e4nen, H. A universal, accurate intensity\u2010based classification of different physical activities using Raw data of accelerometer. Clin. Physiol. Funct. Imaging. 35, 64\u201370 (2015).","journal-title":"Clin. Physiol. Funct. Imaging"},{"key":"20195_CR34","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","volume":"31","author":"Y Yu","year":"2019","unstructured":"Yu, Y., Si, X., Hu, C. & Zhang, J. A. Review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 31, 1235\u20131270 (2019).","journal-title":"Neural Comput."},{"key":"20195_CR35","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1002\/asmb.446","volume":"17","author":"S Lipovetsky","year":"2001","unstructured":"Lipovetsky, S. & Conklin, M. Analysis of regression in game theory approach. Appl. Stoch. Models Bus. Ind. 17, 319\u2013330 (2001).","journal-title":"Appl. Stoch. Models Bus. Ind."},{"key":"20195_CR36","doi-asserted-by":"publisher","first-page":"3224","DOI":"10.1109\/TBME.2022.3163429","volume":"69","author":"Z Ni","year":"2022","unstructured":"Ni, Z., Wu, T., Wang, T., Sun, F. & Li, Y. Deep Multi-Branch Two-Stage regression network for accurate energy expenditure Estimation with ECG and IMU data. IEEE Trans. Biomed. Eng. 69, 3224\u20133233 (2022).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"20195_CR37","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1055\/s-2005-872929","volume":"27","author":"M Buchheit","year":"2006","unstructured":"Buchheit, M. et al. Relationship between very high physical activity energy expenditure, heart rate variability and Self-Estimate of health status in Middle-Aged individuals. Int. J. Sports Med. 27, 697\u2013701 (2006).","journal-title":"Int. J. Sports Med."},{"key":"20195_CR38","doi-asserted-by":"crossref","unstructured":"Michael, S., Graham, K. S. & Davis, G. M. Cardiac autonomic responses during exercise and Post-exercise recovery using heart rate variability and systolic time Intervals\u2014A review. Front. Physiol 8  (2017).","DOI":"10.3389\/fphys.2017.00301"},{"key":"20195_CR39","doi-asserted-by":"crossref","unstructured":"Millis, R. M., Austin, R. E., Hatcher, M. D., Bond, V. & Goring, K. L. Metabolic energy correlates of heart rate variability spectral power associated with a 900-calorie challenge. J. Nutr. Metab. 2011, 715361 (2011).","DOI":"10.1155\/2011\/715361"},{"key":"20195_CR40","doi-asserted-by":"publisher","first-page":"57","DOI":"10.2174\/1874192401610010057","volume":"10","author":"SS Vieira","year":"2016","unstructured":"Vieira, S. S. et al. Does stroke volume increase during an incremental exercise? A systematic review. Open. Cardiovasc. Med. J. 10, 57\u201363 (2016).","journal-title":"Open. Cardiovasc. Med. J."},{"key":"20195_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, S., Wang, Z., Tang, C. & Huang, Z. A. Dual-Stream fusion network for human energy expenditure Estimation with wearable sensor. Int J. Comput. Intell. Appl 24  (2025).","DOI":"10.1142\/S1469026824500287"},{"key":"20195_CR42","doi-asserted-by":"publisher","first-page":"112515","DOI":"10.1016\/j.jbiomech.2025.112515","volume":"180","author":"BDM Jones","year":"2025","unstructured":"Jones, B. D. M., Wheat, J., Middleton, K., Carey, D. L. & Heller, B. Reliability of running gait variability measures calculated from inertial measurement units. J. Biomech. 180, 112515 (2025).","journal-title":"J. Biomech."},{"key":"20195_CR43","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1152\/japplphysiol.00703.2003","volume":"96","author":"S Brage","year":"2004","unstructured":"Brage, S. et al. Branched equation modeling of simultaneous accelerometry and heart rate monitoring improves estimate of directly measured physical activity energy expenditure. J. Appl. Physiol. 96, 343\u2013351 (2004).","journal-title":"J. Appl. Physiol."},{"key":"20195_CR44","doi-asserted-by":"publisher","first-page":"1770","DOI":"10.1249\/MSS.0b013e3181a24536","volume":"41","author":"AG Bonomi","year":"2009","unstructured":"Bonomi, A. G., Goris, A. H. C., Yin, B. & Westerterp, K. R. Detection of type, duration, and intensity of physical activity using an accelerometer. Med. Sci. Sports Exerc. 41, 1770\u20131777 (2009).","journal-title":"Med. Sci. Sports Exerc."},{"key":"20195_CR45","doi-asserted-by":"crossref","unstructured":"Jabbour, G. & Iancu, H. D. Supramaximal-Exercise training improves heart rate variability in association with reduced catecholamine in obese adults. Front. Physiol. 12 (2021).","DOI":"10.3389\/fphys.2021.654695"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20195-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20195-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20195-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:56:39Z","timestamp":1760612199000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20195-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["20195"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-20195-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"14 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"36277"}}