{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T05:04:09Z","timestamp":1789362249845,"version":"build-2803163510"},"reference-count":21,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"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>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Preoperative insomnia disorder (PID) and emergence agitation (EA) often present as a complex perioperative comorbidity. Traditional linear models may not adequately capture their underlying interactive mechanisms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective, single-center study analyzed 542 adult surgical patients. Machine learning algorithms, particularly XGBoost, were developed using stratified random splitting (70% training, 30% testing) to predict the PID-EA co-occurrence. The Shapley Additive exPlanations (SHAP) framework was utilized to interpret statistical associations and non-linear interactions among clinical variables.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The XGBoost model demonstrated superior discriminative performance (AUC\u202f=\u202f0.874 [95% CI: 0.812\u20130.936], AUPRC\u202f=\u202f0.883, Brier score\u202f=\u202f0.150) compared to logistic regression (AUC\u202f=\u202f0.749 [95% CI: 0.675\u20130.823]). SHAP analysis indicated that preoperative cortisol and melatonin were the primary features associated with the model\u2019s predictions. Partial dependence plots suggested potential non-linear risk thresholds for neuroendocrine markers. Furthermore, interaction analyses illustrated that severe postoperative pain may synergistically amplify the risk associated with preoperative insomnia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The integration of XGBoost and SHAP offers an interpretable approach to evaluating the PID-EA comorbidity network. These findings highlight potential clinical thresholds and interaction patterns, warranting further validation through multi-center prospective studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1875540","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T04:32:08Z","timestamp":1789360328000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating non-linear thresholds and synergistic interactions in the comorbidity of preoperative insomnia and emergence agitation: a SHAP-based machine learning study"],"prefix":"10.3389","volume":"17","author":[{"given":"Jianheng","family":"Zhao","sequence":"first","affiliation":[{"name":"Panzhihua Central Hospital","place":["Panzhihua, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxu","family":"Yu","sequence":"additional","affiliation":[{"name":"Panzhihua Central Hospital","place":["Panzhihua, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bangjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Panzhihua Central Hospital","place":["Panzhihua, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengying","family":"Wang","sequence":"additional","affiliation":[{"name":"Panzhihua Central Hospital","place":["Panzhihua, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Yang","sequence":"additional","affiliation":[{"name":"Panzhihua Central Hospital","place":["Panzhihua, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"844565","DOI":"10.1016\/j.bjane.2024.844565","article-title":"Pharmacological and non-pharmacological interventions in patients undergoing nasal surgeries for prevention of emergence agitation: a systematic review and network meta-analysis","volume":"75","author":"Wegner","year":"2025","journal-title":"Brazil J Anesthesiol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1726908","DOI":"10.3389\/fmed.2026.1726908","article-title":"Diabetes mellitus is associated with an increased risk of postoperative neurocognitive disorders: a systematic review","volume":"13","author":"Li","year":"2026","journal-title":"Front Med (Lausanne)"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1007\/s10620-016-4214-2","article-title":"A comparative study of treatment-emergent adverse events following use of common bowel preparations among a colonoscopy screening population: results from a post-marketing observational study","volume":"61","author":"Anastassopoulos","year":"2016","journal-title":"Dig Dis Sci"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e0118848","DOI":"10.1371\/journal.pone.0118848","article-title":"Recurrent invasive pneumococcal disease in children: underlying clinical conditions, and immunological and microbiological characteristics","volume":"10","author":"Alsina","year":"2015","journal-title":"PLoS One"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1038\/s41390-021-01445-2","article-title":"Treg-associated monogenic autoimmune disorders and gut microbial dysbiosis","volume":"91","author":"Liu","year":"2022","journal-title":"Pediatr Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/cancers14081982","article-title":"A new approach to understanding Cancer-related fatigue: leveraging the 3P model to facilitate risk prediction and clinical care","volume":"14","author":"Sleight","year":"2022","journal-title":"Cancers (Basel)"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1186\/s12885-018-4681-2","article-title":"Incidence and risk factors of subsyndromal delirium after curative resection of gastric cancer","volume":"18","author":"Hwang","year":"2018","journal-title":"BMC Cancer"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1001\/jamacardio.2016.4792","article-title":"Perioperative major adverse cardiovascular and cerebrovascular events associated with noncardiac surgery","volume":"2","author":"Smilowitz","year":"2017","journal-title":"JAMA Cardiol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1186\/s12909-026-08689-8","article-title":"Ethical behavior profiles among nursing interns and their determinants: a latent profile analysis","volume":"26","author":"Qu","year":"2026","journal-title":"BMC Med Educ"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e0298743","DOI":"10.1371\/journal.pone.0298743","article-title":"Predicting successful draft outcome in Australian rules football: model sensitivity is superior in neural networks when compared to logistic regression","volume":"19","author":"Jennings","year":"2024","journal-title":"PLoS One"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1186\/s12913-025-13847-7","article-title":"Predictors of rural hospital closures in the United States: a systematic review and call for AI-driven early warning systems","volume":"26","author":"Balakrishnan","year":"2025","journal-title":"BMC Health Serv Res"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1186\/s12889-026-26603-1","article-title":"Association rule analysis of physical activity and multimorbidity in middle-aged Korean adults with diabetes: an evidence to promote active lifestyles","volume":"26","author":"Huang","year":"2026","journal-title":"BMC Public Health"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"4026","DOI":"10.3390\/jcm14124026","article-title":"Machine learning and artificial intelligence in intensive care medicine: critical recalibrations from rule-based systems to frontier models","volume":"14","author":"Hadweh","year":"2025","journal-title":"J Clin Med"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1186\/s12877-022-03295-x","article-title":"Interpretable classifiers for prediction of disability trajectories using a nationwide longitudinal database","volume":"22","author":"Wu","year":"2022","journal-title":"BMC Geriatr"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"930","DOI":"10.5498\/wjp.v14.i6.930","article-title":"Correlation between pre-anesthesia anxiety and emergence agitation in non-small cell lung cancer surgery patients","volume":"14","author":"Yan","year":"2024","journal-title":"World J Psychiatry"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1186\/s12871-023-02228-4","article-title":"Development of a nomogram to predict negative postoperative behavioral changes based on a prospective cohort","volume":"23","author":"Li","year":"2023","journal-title":"BMC Anesthesiol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"e25894","DOI":"10.1097\/MD.0000000000025894","article-title":"Development and validation of a postoperative delirium prediction model for pediatric patients: a prospective, observational, single-center study","volume":"100","author":"Lin","year":"2021","journal-title":"Medicine (Baltimore)"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"12043","DOI":"10.3390\/ijms262412043","article-title":"Molecular mechanisms driving precision medicine in perioperative care: integrating inflammation, metabolism, and Neuroimmunomodulation for personalized outcomes","volume":"26","author":"Wenner","year":"2025","journal-title":"Int J Mol Sci"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1668523","DOI":"10.3389\/fnmol.2025.1668523","article-title":"Advances in research on propofol-induced postoperative cognitive dysfunction via piezo channels","volume":"18","author":"Xue","year":"2025","journal-title":"Front Mol Neurosci"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"9012","DOI":"10.1038\/s41598-026-37372-7","article-title":"Global spatiotemporal analysis of interactions between urban heat islands and extreme heat waves","volume":"16","author":"Guo","year":"2026","journal-title":"Sci Rep"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"323","DOI":"10.61399\/ikcusbfd.1278806","article-title":"Comparison of total intravenous anesthesia with inhaler anesthesia in children intubated with remifentanil without muscle relaxant","volume":"9","author":"G\u00f6k\u00e7e","year":"2024","journal-title":"\u0130zmir Katip \u00c7elebi \u00dcniversitesi Sa\u011fl\u0131k Bilimleri Fak\u00fcltesi Dergisi"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1875540\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T04:32:18Z","timestamp":1789360338000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1875540\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":21,"alternative-id":["10.3389\/fneur.2026.1875540"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1875540","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"article-number":"1875540"}}