{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T21:13:53Z","timestamp":1793481233784,"version":"4.5.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Acute kidney injury (AKI) is a life-threatening problem for hospitalized patients, and early detection is crucial to reduce severe outcomes. Traditional predictive methods lack in monitoring complex physiological patterns and ensuring data privacy in decentralized healthcare settings. The study aims to develop and evaluate two distinctly complementary novel graph-based approaches, namely the centralized Graph Attention Network (GAT) and the decentralized model, Gossip Learning with Adaptive Aggregation GAT (GL-AA-GAT), to identify AKI onset between 6 and 12\u00a0h in advance, using physiological time-series data from the Kaggle Sepsis dataset. Multi-Head Attention is used for modeling feature interactions in centralized GAT, while GL-AA-GAT can further achieve this by decentralized training of five nodes using gossip exchange and adaptive aggregation for privacy and scalability. Through its novel graph structure, centralized GAT predicts the onset of AKI with an accuracy of 94.1%, sensitivity of 94%, AUC-ROC of 95%, and AUPRC of 91%. With decentralized privacy additions, GL-AA-GAT achieves an accuracy of 92.8%, a sensitivity of 93%, an AUC-ROC of 93.8%, and an AUPRC of 90%, with robustness. Sensitivity analyses revealed that the performance was stable with the prediction horizons and correlation thresholds, and external validation on non-sepsis cohorts of the ICU further indicated generalizability. Both models outperform existing models, which means high predictive reliability. The GL-AA-GAT\u2019s distributed approach gives privacy and flexibility, making it innovative for distributed clinical environments, with task scheduling enhancing training efficiency.<\/jats:p>","DOI":"10.1038\/s41598-025-31211-x","type":"journal-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:53:59Z","timestamp":1765043639000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Novel graph-based centralized and decentralized approaches for early AKI prediction"],"prefix":"10.1038","volume":"15","author":[{"given":"V. S. Suresh","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. Devi","family":"Priya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.","family":"Vijayakumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"31211_CR1","doi-asserted-by":"publisher","first-page":"635631","DOI":"10.3389\/fped.2021.635631","volume":"9","author":"B Leghrouz","year":"2021","unstructured":"Leghrouz, B. & Kaddourah, A. Impact of acute kidney injury on critically ill children and neonates. Front. Pead. 9, 635631. https:\/\/doi.org\/10.3389\/fped.2021.635631 (2021).","journal-title":"Front. Pead."},{"key":"31211_CR2","unstructured":"United States Renal Data System. USRDS Annual Data Report: Epidemiology of kidney disease in the United States. National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases, Bethesda, MD. (2024). https:\/\/usrds-adr.niddk.nih.gov\/2024\/chronic-kidney-disease\/4-acute-kidney-injury"},{"issue":"8","key":"31211_CR3","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/s00134-021-06454-7","volume":"47","author":"P Pickkers","year":"2021","unstructured":"Pickkers, P. et al. Acute kidney injury in the critically ill: an updated review on pathophysiology and management. Intensive Care Med. 47 (8), 835\u2013850. https:\/\/doi.org\/10.1007\/s00134-021-06454-7 (2021).","journal-title":"Intensive Care Med."},{"issue":"12","key":"31211_CR4","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.3390\/healthcare9121662","volume":"9","author":"TH Lee","year":"2021","unstructured":"Lee, T. H. et al. Does artificial intelligence make clinical decision better? A review of artificial intelligence and machine learning in acute kidney injury prediction. Healthc. (Basel Switzerland). 9 (12), 1662. https:\/\/doi.org\/10.3390\/healthcare9121662 (2021).","journal-title":"Healthc. (Basel Switzerland)"},{"issue":"8","key":"31211_CR5","doi-asserted-by":"publisher","first-page":"2047","DOI":"10.1007\/s40620-022-01335-8","volume":"35","author":"F Alfieri","year":"2022","unstructured":"Alfieri, F. et al. External validation of a deep-learning model to predict severe acute kidney injury based on urine output changes in critically ill patients. J. Nephrol. 35 (8), 2047\u20132056. https:\/\/doi.org\/10.1007\/s40620-022-01335-8 (2022).","journal-title":"J. Nephrol."},{"key":"31211_CR6","doi-asserted-by":"publisher","first-page":"1050255","DOI":"10.3389\/fmed.2023.1050255","volume":"10","author":"X Yu","year":"2023","unstructured":"Yu, X., Ji, Y., Huang, M. & Feng, Z. Machine learning for acute kidney injury: changing the traditional disease prediction mode. Front. Med. 10, 1050255. https:\/\/doi.org\/10.3389\/fmed.2023.1050255 (2023).","journal-title":"Front. Med."},{"issue":"1","key":"31211_CR7","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1186\/s12967-022-03364-0","volume":"20","author":"S Yue","year":"2022","unstructured":"Yue, S. et al. Machine learning for the prediction of acute kidney injury in patients with sepsis. J. Translational Med. 20 (1), 215. https:\/\/doi.org\/10.1186\/s12967-022-03364-0 (2022).","journal-title":"J. Translational Med."},{"key":"31211_CR8","doi-asserted-by":"publisher","first-page":"5061","DOI":"10.2147\/IJGM.S361330","volume":"15","author":"Y Yang","year":"2022","unstructured":"Yang, Y. et al. Machine learning-assisted ensemble analysis for the prediction of acute pancreatitis with acute kidney injury. Int. J. Gen. Med. 15, 5061\u20135072. https:\/\/doi.org\/10.2147\/IJGM.S361330 (2022).","journal-title":"Int. J. Gen. Med."},{"key":"31211_CR9","doi-asserted-by":"publisher","first-page":"1140755","DOI":"10.3389\/fimmu.2023.1140755","volume":"14","author":"H Zhou","year":"2023","unstructured":"Zhou, H. et al. Machine learning for the prediction of all-cause mortality in patients with sepsis-associated acute kidney injury during hospitalization. Front. Immunol. 14, 1140755. https:\/\/doi.org\/10.3389\/fimmu.2023.1140755 (2023).","journal-title":"Front. Immunol."},{"key":"31211_CR10","doi-asserted-by":"publisher","first-page":"842873","DOI":"10.3389\/fcvm.2022.842873","volume":"9","author":"X Peng","year":"2022","unstructured":"Peng, X., Li, L., Wang, X. & Zhang, H. A machine learning-based prediction model for acute kidney injury in patients with congestive heart failure. Front. Cardiovasc. Med. 9, 842873. https:\/\/doi.org\/10.3389\/fcvm.2022.842873 (2022).","journal-title":"Front. Cardiovasc. Med."},{"issue":"2","key":"31211_CR11","doi-asserted-by":"publisher","first-page":"e0246306","DOI":"10.1371\/journal.pone.0246306","volume":"16","author":"J Liu","year":"2021","unstructured":"Liu, J. et al. Predicting mortality of patients with acute kidney injury in the ICU using XGBoost model. PloS One. 16 (2), e0246306. https:\/\/doi.org\/10.1371\/journal.pone.0246306 (2021).","journal-title":"PloS One"},{"issue":"1","key":"31211_CR12","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1186\/s13054-020-03179-9","volume":"24","author":"PY Tseng","year":"2020","unstructured":"Tseng, P. Y. et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit. Care. (London, England). 24 (1), 478. https:\/\/doi.org\/10.1186\/s13054-020-03179-9 (2020).","journal-title":"Crit. Care. (London, England)"},{"issue":"1","key":"31211_CR13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1038\/s41746-020-00346-8","volume":"3","author":"N Rank","year":"2020","unstructured":"Rank, N. et al. Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance. Npj Digit. Med. 3 (1), 139. https:\/\/doi.org\/10.1038\/s41746-020-00346-8 (2020).","journal-title":"Npj Digit. Med."},{"issue":"15","key":"31211_CR14","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.1080\/08839514.2021.1976908","volume":"35","author":"S Shi","year":"2021","unstructured":"Shi, S. A novel hybrid deep learning architecture for predicting acute kidney injury using patient record data and ultrasound kidney images. Appl. Artif. Intelligence: AAI. 35 (15), 1329\u20131345. https:\/\/doi.org\/10.1080\/08839514.2021.1976908 (2021).","journal-title":"Appl. Artif. Intelligence: AAI"},{"key":"31211_CR15","doi-asserted-by":"publisher","unstructured":"Wu, C. et al. Predicting in-hospital outcomes of patients with acute kidney injury. Nat. Commun. 14 (1). https:\/\/doi.org\/10.1038\/s41467-023-39474-6 (2023).","DOI":"10.1038\/s41467-023-39474-6"},{"issue":"3","key":"31211_CR16","doi-asserted-by":"publisher","first-page":"ooae097","DOI":"10.1093\/jamiaopen\/ooae097","volume":"7","author":"G Ghanbari","year":"2024","unstructured":"Ghanbari, G. et al. Development and validation of a deep learning algorithm for the prediction of serum creatinine in critically ill patients. JAMIA Open. 7 (3), ooae097. https:\/\/doi.org\/10.1093\/jamiaopen\/ooae097 (2024).","journal-title":"JAMIA Open."},{"issue":"6","key":"31211_CR17","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1007\/s40620-021-01046-6","volume":"34","author":"F Alfieri","year":"2021","unstructured":"Alfieri, F. et al. A deep-learning model to continuously predict severe acute kidney injury based on urine output changes in critically ill patients. J. Nephrol. 34 (6), 1875\u20131886. https:\/\/doi.org\/10.1007\/s40620-021-01046-6 (2021).","journal-title":"J. Nephrol."},{"key":"31211_CR18","doi-asserted-by":"publisher","first-page":"97","DOI":"10.3233\/SHTI210868","volume":"289","author":"X Li","year":"2022","unstructured":"Li, X. A deep learning program to predict acute kidney injury. Stud. Health Technol. Inform. 289, 97\u2013101. https:\/\/doi.org\/10.3233\/SHTI210868 (2022).","journal-title":"Stud. Health Technol. Inform."},{"issue":"1","key":"31211_CR19","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/s41467-024-55629-5","volume":"16","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y. et al. Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients. Nat. Commun. 16 (1), 68. https:\/\/doi.org\/10.1038\/s41467-024-55629-5 (2025).","journal-title":"Nat. Commun."},{"issue":"1","key":"31211_CR20","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/s13755-023-00248-5","volume":"11","author":"CT Huang","year":"2023","unstructured":"Huang, C. T. et al. Federated machine learning for predicting acute kidney injury in critically ill patients: a multicenter study in Taiwan. Health Inform. Sci. Syst. 11 (1), 48. https:\/\/doi.org\/10.1007\/s13755-023-00248-5 (2023).","journal-title":"Health Inform. Sci. Syst."},{"issue":"11","key":"31211_CR21","doi-asserted-by":"publisher","first-page":"2595","DOI":"10.3390\/cancers13112595","volume":"13","author":"C Bian","year":"2021","unstructured":"Bian, C., Lei, X. J. & Wu, F. X. Predicting circRNA-disease associations based on graph attention network. Cancers 13 (11), 2595. https:\/\/doi.org\/10.3390\/cancers13112595 (2021).","journal-title":"Cancers"},{"issue":"5","key":"31211_CR22","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1049\/syb2.12098","volume":"18","author":"BM Momanyi","year":"2024","unstructured":"Momanyi, B. M. et al. iGATTLDA: integrative graph attention and transformer-based model for predicting lncRNA-Disease associations. IET Syst. Biol. 18 (5), 172\u2013182. https:\/\/doi.org\/10.1049\/syb2.12098 (2024).","journal-title":"IET Syst. Biol."},{"issue":"9","key":"31211_CR23","doi-asserted-by":"publisher","first-page":"2384","DOI":"10.1049\/ipr2.12495","volume":"16","author":"S Li","year":"2022","unstructured":"Li, S. et al. Adaptive aggregation with self-attention network for Gastrointestinal image classification. IET Image Proc. 16 (9), 2384\u20132397. https:\/\/doi.org\/10.1049\/ipr2.12495 (2022).","journal-title":"IET Image Proc."},{"key":"31211_CR24","doi-asserted-by":"publisher","unstructured":"Ali, M. N. et al. Ensemble and gossip learning-based framework for intrusion detection system in vehicle-to-everything communication environment. Sens. (Basel Switzerland). 24 (20). https:\/\/doi.org\/10.3390\/s24206528 (2024).","DOI":"10.3390\/s24206528"},{"key":"31211_CR25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.jpdc.2020.10.006","volume":"148","author":"I Heged\u0171s","year":"2021","unstructured":"Heged\u0171s, I., Danner, G. & Jelasity, M. Decentralized learning works: an empirical comparison of gossip learning and federated learning. J. Parallel Distrib. Comput. 148, 109\u2013124. https:\/\/doi.org\/10.1016\/j.jpdc.2020.10.006 (2021).","journal-title":"J. Parallel Distrib. Comput."},{"key":"31211_CR26","doi-asserted-by":"publisher","first-page":"77873","DOI":"10.1109\/access.2021.3083639","volume":"9","author":"H Oguni","year":"2021","unstructured":"Oguni, H. & Shudo, K. Communication scheduling for gossip SGD in a wide area network. IEEE Access: Practical Innovations Open. Solutions. 9, 77873\u201377881. https:\/\/doi.org\/10.1109\/access.2021.3083639 (2021).","journal-title":"IEEE Access: Practical Innovations Open. Solutions"},{"key":"31211_CR27","doi-asserted-by":"crossref","unstructured":"Chatterjee, M. & Setua, S. K. Gossip-based real-time task scheduling using expander graph. In Advances in Intelligent Systems and Computing (3\u201314). Springer Singapore (2019).","DOI":"10.1007\/978-981-13-3250-0_1"},{"key":"31211_CR28","doi-asserted-by":"publisher","unstructured":"Huang, S., Wang, M., Zheng, X., Chen, J. & Tang, C. Hierarchical and dynamic graph attention network for drug-disease association prediction. IEEE J. Biomedical Health Inf. (4), 2416\u20132427. https:\/\/doi.org\/10.1109\/JBHI.2024.3363080 (2024).","DOI":"10.1109\/JBHI.2024.3363080"},{"key":"31211_CR29","doi-asserted-by":"crossref","unstructured":"Farhadi, A. & Taheri, A. Application of GenAI in synthetic data generation in the healthcare system. In Application of Generative AI in Healthcare Systems (67\u201389). Springer Nature Switzerland. (2025).","DOI":"10.1007\/978-3-031-82963-5_3"},{"key":"31211_CR30","doi-asserted-by":"crossref","unstructured":"Sakil, M. B. H. et al. A transformer and graph-based multi-task learning for optimized decision-making in chronic kidney disease management. In 2025 International Conference on Intelligent Computing and Control Systems (ICICCS), 703\u2013708. (2025).","DOI":"10.1109\/ICICCS65191.2025.10985415"},{"key":"31211_CR31","unstructured":"Salik Hussaini. Prediction of sepsis. Kaggle: Your Machine Learning and Data Science Community. (2022). https:\/\/www.kaggle.com\/datasets\/salikhussaini49\/prediction-of-sepsis."},{"issue":"4","key":"31211_CR32","doi-asserted-by":"publisher","first-page":"c179","DOI":"10.1159\/000339789","volume":"120","author":"A Khwaja","year":"2012","unstructured":"Khwaja, A. KDIGO clinical practice guidelines for acute kidney injury. Nephron Clin. Pract. 120 (4), c179\u2013c184. https:\/\/doi.org\/10.1159\/000339789 (2012).","journal-title":"Nephron Clin. Pract."},{"issue":"Suppl 1","key":"31211_CR33","doi-asserted-by":"publisher","first-page":"i247","DOI":"10.1093\/bioinformatics\/btae212","volume":"40","author":"X Lyu","year":"2024","unstructured":"Lyu, X. et al. An empirical study on KDIGO-defined acute kidney injury prediction in the intensive care unit. Bioinf. (Oxford England). 40 (Suppl 1), i247\u2013i256. https:\/\/doi.org\/10.1093\/bioinformatics\/btae212 (2024).","journal-title":"Bioinf. (Oxford England)"},{"issue":"7","key":"31211_CR34","doi-asserted-by":"publisher","first-page":"e0287398","DOI":"10.1371\/journal.pone.0287398","volume":"18","author":"F Alfieri","year":"2023","unstructured":"Alfieri, F. et al. Continuous and early prediction of future moderate and severe acute kidney injury in critically ill patients: development and multi-centric, multi-national external validation of a machine-learning model. PloS One. 18 (7), e0287398. https:\/\/doi.org\/10.1371\/journal.pone.0287398 (2023).","journal-title":"PloS One"},{"issue":"5","key":"31211_CR35","doi-asserted-by":"publisher","first-page":"e2313359","DOI":"10.1001\/jamanetworkopen.2023.13359","volume":"6","author":"Y Feng","year":"2023","unstructured":"Feng, Y. et al. Characterization of risk prediction models for acute kidney injury: A systematic review and Meta-analysis. JAMA Netw. Open. 6 (5), e2313359. https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.13359 (2023).","journal-title":"JAMA Netw. Open."},{"issue":"3","key":"31211_CR36","first-page":"69","volume":"24","author":"MM Mukaka","year":"2012","unstructured":"Mukaka, M. M. Statistics corner: A guide to appropriate use of correlation coefficient in medical research. Malawi medical journal. J. Med. Association Malawi. 24 (3), 69\u201371 (2012).","journal-title":"J. Med. Association Malawi"},{"issue":"6","key":"31211_CR37","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1093\/bib\/bbt051","volume":"15","author":"S de Siqueira Santos","year":"2014","unstructured":"de Siqueira Santos, S., Takahashi, D. Y., Nakata, A. & Fujita, A. A comparative study of statistical methods used to identify dependencies between gene expression signals. Brief. Bioinform. 15 (6), 906\u2013918. https:\/\/doi.org\/10.1093\/bib\/bbt051 (2014).","journal-title":"Brief. Bioinform."},{"issue":"1","key":"31211_CR38","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1080\/0886022X.2022.2027247","volume":"44","author":"N Wang","year":"2022","unstructured":"Wang, N. et al. The predictive value of the Oxford acute severity of illness score for clinical outcomes in patients with acute kidney injury. Ren. Fail. 44 (1), 320\u2013328. https:\/\/doi.org\/10.1080\/0886022X.2022.2027247 (2022).","journal-title":"Ren. Fail."},{"issue":"4","key":"31211_CR39","doi-asserted-by":"publisher","first-page":"3619","DOI":"10.3390\/nursrep14040264","volume":"14","author":"WP Sousa","year":"2024","unstructured":"Sousa, W. P. et al. Prognostic scores for acute kidney injury in critically ill patients. Nurs. Rep. 14 (4), 3619\u20133630. https:\/\/doi.org\/10.3390\/nursrep14040264 (2024).","journal-title":"Nurs. Rep."},{"issue":"6","key":"31211_CR40","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","volume":"26","author":"AJ Vickers","year":"2006","unstructured":"Vickers, A. J. & Elkin, E. B. Decision curve analysis: a novel method for evaluating prediction models. Med. Decis. Making: Int. J. Soc. Med. Decis. Mak. 26 (6), 565\u2013574. https:\/\/doi.org\/10.1177\/0272989X06295361 (2006).","journal-title":"Med. Decis. Making: Int. J. Soc. Med. Decis. Mak."},{"key":"31211_CR41","unstructured":"Bilal. mimic-III-10k. Kaggle.com. (2024). https:\/\/www.kaggle.com\/datasets\/bilal1907\/mimic-iii-10k."},{"key":"31211_CR42","unstructured":"Akshay updated_mimic_iv. Kaggle.com. (2025)., February https:\/\/www.kaggle.com\/datasets\/akshaybe\/updated-mimic-iv."},{"issue":"2","key":"31211_CR43","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1109\/JBHI.2022.3224727","volume":"27","author":"Y Li","year":"2023","unstructured":"Li, Y. et al. Hi-BEHRT: hierarchical Transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records. IEEE J. Biomedical Health Inf. 27 (2), 1106\u20131117. https:\/\/doi.org\/10.1109\/JBHI.2022.3224727 (2023).","journal-title":"IEEE J. Biomedical Health Inf."},{"key":"31211_CR44","unstructured":"Mao, C., Yao, L. & Luo, Y. AKI-BERT: A pre-trained clinical language model for early prediction of acute kidney injury. In arXiv [cs.CL]. (2022). http:\/\/arxiv.org\/abs\/2205.03695."},{"key":"31211_CR45","doi-asserted-by":"crossref","unstructured":"Song, Z. et al. Extrapolatable transformer pre-training for long-term time-series forecasting in healthcare. In Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 1\u201310. (2024).","DOI":"10.1145\/3698587.3701364"},{"key":"31211_CR46","unstructured":"Wang, Y., Zhao, Y., Callcut, R. & Petzold, L. Integrating physiological time series and clinical notes with Transformer for early prediction of sepsis. In arXiv [cs.LG]. (2022). http:\/\/arxiv.org\/abs\/2203.14469."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31211-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31211-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31211-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T13:14:18Z","timestamp":1766495658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-31211-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["31211"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-31211-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"10 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 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":"44397"}}