{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T15:54:06Z","timestamp":1788537246952,"version":"build-2803163510"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Postoperative delirium (POD) is a prevalent neurological complication linked to adverse clinical outcomes. The underlying mechanisms of POD remain unclear. This study aimed to investigate the association between POD and frailty and determine whether frailty influences POD incidence. Furthermore, machine learning algorithms were utilized to identify key predictors of POD in patients undergoing hip or knee replacement.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 625 Han Chinese patients were recruited between September 2021 and May 2023. Preoperative frailty was assessed using the Frailty Scale and Frailty Phenotype criteria. The Mini-Mental State Examination (MMSE) evaluated preoperative cognitive function, while the Confusion Assessment Method (CAM) diagnosed POD. The severity of POD was additionally quantified using the Memorial Delirium Assessment Scale (MDAS). Receiver Operating Characteristic (ROC) curve analysis explored the association between preoperative frailty and POD, and the mediating effect of cerebrospinal fluid (CSF) biomarkers was analyzed. Ten machine learning algorithms\u2014including Logistic Regression (LR), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), Artificial Neural Network (ANN), Random Forest (RF), XGBoost, K-Nearest Neighbors (KNN), AdaBoost, LightGBM, and CatBoost\u2014were implemented to develop predictive models. The dataset was randomly split into training (70%) and testing (30%) subsets. Ten-fold cross-validation was incorporated during model training and validation to mitigate overfitting and enhance generalizability. Model performance was evaluated using multiple metrics, such as accuracy, sensitivity, specificity, precision, Brier score, area under the ROC curve (AUC), and F1 score. Furthermore, graphical analyses\u2014including calibration curves, decision diagrams, clinical impact curves, and confusion matrices\u2014were applied to assess model robustness and clinical utility. Finally, SHAP (Shapley Additive Explanations) analysis elucidated the model\u2019s decision-making process, emphasizing the pivotal role of preoperative frailty in POD prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The incidence of POD was 14.7%. The study identified frailty, Tau, and P-tau as significant risk factors for POD (OR\u202f=\u202f67.229, 95% CI: 34.649\u2013130.444, <jats:italic>p<\/jats:italic>\u202f&amp;lt;\u202f0.001; OR\u202f=\u202f1.020, 95% CI: 1.016\u20131.024, <jats:italic>p<\/jats:italic>\u202f&amp;lt;\u202f0.001; OR\u202f=\u202f1.018, 95% CI: 1.010\u20131.027, <jats:italic>p<\/jats:italic>\u202f&amp;lt;\u202f0.001). ROC curve analysis (AUC\u202f=\u202f0.983) demonstrated that combining frailty with CSF biomarkers had strong predictive power for distinguishing POD. The direct effect of frailty on POD was 0.504878, the total effect was 0.6547619, and the mediating effect of Tau accounted for 22.89%. Using Lasso regression for variable selection, we subsequently identified eight predictors\u2014frailty, Tau, A\u03b242\/Tau, A\u03b240, age, A\u03b242, P-tau, and drinking history\u2014from the training set via logistic regression. Based on these factors, we constructed 10 machine learning models. Among all machine learning algorithms, GBM performed the best, achieving an AUC of 0.973 (95% CI, 0.973\u20131.000) in the test set. Furthermore, SHAP analysis confirmed that frailty and Tau were the key determinants influencing the machine learning model\u2019s predictions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Preoperative frailty is an independent risk factor for POD. A machine learning model for predicting POD in patients undergoing hip or knee replacement was developed, with GBM demonstrating superior performance among all models. The GBM-based model enabled early identification of patients at high risk of delirium.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fneur.2025.1608264","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:19:06Z","timestamp":1758082746000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Tau protein mediates the association between frailty and postoperative delirium: a machine learning model incorporating cerebrospinal fluid biomarkers"],"prefix":"10.3389","volume":"16","author":[{"given":"Yizhi","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanlin","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhui","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanlong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanlin","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/s41572-020-00223-4","article-title":"Delirium","volume":"6","author":"Wilson","year":"2020","journal-title":"Nat Rev Dis Primers"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1056\/NEJMcp1605501","article-title":"Delirium in Hospitalized Older Adults","volume":"377","author":"Marcantonio","year":"2017","journal-title":"N Engl J Med"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1007\/s10354-021-00904-z","article-title":"Delirium in geriatric patients","volume":"172","author":"Iglseder","year":"2022","journal-title":"Wien Med Wochenschr"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"ITC49","DOI":"10.7326\/aitc202010060","article-title":"Delirium","volume":"173","author":"Mattison","year":"2020","journal-title":"Ann Intern Med"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1007\/s00401-017-1707-9","article-title":"Roles of tau protein in health and disease","volume":"133","author":"Guo","year":"2017","journal-title":"Acta Neuropathol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"207","DOI":"10.3390\/ijms22179207","article-title":"Tau protein interaction partners and their roles in Alzheimer's disease and other tauopathies","volume":"22","author":"Sinsky","year":"2021","journal-title":"Int J Mol Sci"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"4110","DOI":"10.1002\/alz.13118","article-title":"Blood tau-PT217 contributes to the anesthesia\/surgery-induced delirium-like behavior in aged mice","volume":"19","author":"Lu","year":"2023","journal-title":"Alzheimers Dement"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e209795","DOI":"10.1212\/wnl.0000000000209795","article-title":"Core CSF biomarker profile in cerebral amyloid angiopathy: updated Meta-analysis","volume":"103","author":"Charidimou","year":"2024","journal-title":"Neurology"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e70173","DOI":"10.1002\/alz.70173","article-title":"Differences in Alzheimer's disease blood biomarker stability: implications for the use of tau\/amyloid ratios","volume":"21","author":"Figdore","year":"2025","journal-title":"Alzheimers Dement"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1159\/000528561","article-title":"Frailty: pathophysiology, theoretical and operational definition(s), impact, prevalence, management and prevention, in an increasingly economically developed and ageing world","volume":"69","author":"Doody","year":"2023","journal-title":"Gerontology"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1016\/s0140-6736(19)31786-6","article-title":"Frailty: implications for clinical practice and public health","volume":"394","author":"Hoogendijk","year":"2019","journal-title":"Lancet"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/s1474-4422(18)30371-5","article-title":"Investigation of frailty as a moderator of the relationship between neuropathology and dementia in Alzheimer's disease: a cross-sectional analysis of data from the rush memory and aging project","volume":"18","author":"Wallace","year":"2019","journal-title":"Lancet Neurol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/j.dadm.2018.05.002","article-title":"Relationship between frailty and Alzheimer's disease biomarkers: a scoping review","volume":"10","author":"Wallace","year":"2018","journal-title":"Alzheimers Dement"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"283","DOI":"10.5582\/bst.2023.01211","article-title":"Alzheimer's disease with frailty: prevalence, screening, assessment, intervention strategies and challenges","volume":"17","author":"Deng","year":"2023","journal-title":"Biosci Trends"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1097\/eja.0000000000001933","article-title":"Associations between Alzheimer's disease biomarkers and postoperative delirium or cognitive dysfunction: a meta-analysis and trial sequential analysis of prospective clinical trials","volume":"41","author":"Geng","year":"2024","journal-title":"Eur J Anaesthesiol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41576-020-0224-1","article-title":"Electronic health records and polygenic risk scores for predicting disease risk","volume":"21","author":"Li","year":"2020","journal-title":"Nat Rev Genet"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s42979-021-00592-x","article-title":"Machine learning: algorithms, real-world applications and research directions","volume":"2","author":"Sarker","year":"2021","journal-title":"SN Comput Sci"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e019223","DOI":"10.1136\/bmjopen-2017-019223","article-title":"Systematic review of prediction models for delirium in the older adult inpatient","volume":"8","author":"Lindroth","year":"2018","journal-title":"BMJ Open"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"941","DOI":"10.7326\/0003-4819-113-12-941","article-title":"Clarifying confusion: the confusion assessment method. A new method for detection of delirium","volume":"113","author":"Inouye","year":"1990","journal-title":"Ann Intern Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"12468","DOI":"10.1111\/appy.12468","article-title":"Validating the mandarin version of the memorial delirium assessment scale in general medical hospital patients","volume":"14","author":"Hu","year":"2022","journal-title":"Asia Pac Psychiatry"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.ejim.2016.03.007","article-title":"Frailty measurement in research and clinical practice: a review","volume":"31","author":"Dent","year":"2016","journal-title":"Eur J Intern Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1097\/mcc.0000000000000882","article-title":"Postoperative delirium and neurocognitive disorders","volume":"27","author":"Migirov","year":"2021","journal-title":"Curr Opin Crit Care"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1038\/nrn.2015.1","article-title":"Tau in physiology and pathology","volume":"17","author":"Wang","year":"2016","journal-title":"Nat Rev Neurosci"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.conb.2021.03.003","article-title":"A current view on tau protein phosphorylation in Alzheimer's disease","volume":"69","author":"Wegmann","year":"2021","journal-title":"Curr Opin Neurobiol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1516","DOI":"10.1007\/s12640-022-00573-9","article-title":"Activation of PI3k\/Akt\/mTOR Signaling induces deposition of p-tau to promote Aluminum neurotoxicity","volume":"40","author":"Xu","year":"2022","journal-title":"Neurotox Res"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.bbalip.2014.12.006","article-title":"PI3K signalling in inflammation","volume":"1851","author":"Hawkins","year":"2015","journal-title":"Biochim Biophys Acta"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1016\/j.bja.2020.08.061","article-title":"Association between plasma tau and postoperative delirium incidence and severity: a prospective observational study","volume":"126","author":"Ballweg","year":"2021","journal-title":"Br J Anaesth"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"103970","DOI":"10.1016\/j.ebiom.2022.103970","article-title":"Human tau accumulation promotes glycogen synthase kinase-3\u03b2 acetylation and thus upregulates the kinase: a vicious cycle in Alzheimer neurodegeneration","volume":"78","author":"Zhou","year":"2022","journal-title":"EBioMedicine"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/s12192-021-01231-3","article-title":"The PI3K\/Akt signaling axis in Alzheimer's disease: a valuable target to stimulate or suppress?","volume":"26","author":"Razani","year":"2021","journal-title":"Cell Stress Chaperones"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"101208","DOI":"10.1016\/j.arr.2020.101208","article-title":"Synaptic basis of Alzheimer's disease: focus on synaptic amyloid beta, P-tau and mitochondria","volume":"65","author":"John","year":"2021","journal-title":"Ageing Res Rev"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1608264\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:19:07Z","timestamp":1758082747000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1608264\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":30,"alternative-id":["10.3389\/fneur.2025.1608264"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1608264","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"article-number":"1608264"}}