EUVIMEDOntdek EUVIMED
Multizentrische StudieKohortenstudieOpen access

Integrated High-Throughput Targeted Metabolomics and Machine Learning for Early Prediction and Prevention of Postoperative Delirium in Older Adult Surgical Patients: Prospective Multicenter Cohort Study

Integrierte hochauflösende zielgerichtete Metabolomik und Machine Learning zur frühen Vorhersage und Prävention von postoperativem Delir bei älteren operativen Patient:innen: prospektive multizentrische Kohortenstudie

Gengrui Zhong, Xiaoli Huang, Congye Li, Deqiang Wang, Dingding Huang, Menghan Sun, Quanhong Zhou, Yong Guo

JMIR Aging · 2026-04-30 · 9 · e78495-e78495

DOI: 10.2196/78495 ↗

Auf einen Blick

Bei 260 älteren Patient:innen nach Hemiarthroplastik sagte ein logistisches Regressionsmodell ein postoperatives Delir mit AUC 0,855 voraus. Die Modellierung basierte auf präoperativer Metabolomik.

Fragestellung

Lässt sich ein postoperatives Delir nach Hemiarthroplastik bei älteren Patient:innen durch präoperative Metabolomik und Machine Learning vorhersagen?

Methode

Prospektive multizentrische Kohortenstudie mit 260 älteren Patient:innen nach Hemiarthroplastik; präoperative Serumproben; Modelle mit Gradient Boosting, logistischer Regression und RF.

Ergebnisse

201 Metabolite wurden quantifiziert, 41 (20,4 %) waren signifikant unterschiedlich exprimiert. 16 Kandidatenbiomarker wurden identifiziert. Das logistische Regressionsmodell erreichte AUC 0,855 (95 %-KI 0,800–0,910); in Training/Test: 0,844/0,856.

Schlussfolgerung der Autor:innen

Die Integration präoperativer Metabolomik und Machine Learning ermöglichte eine genaue Vorhersage von POD bei älteren Patient:innen mit Hüftfraktur.

Kernaussagen

  • AUC des besten Modells: 0,855 (95 %-KI 0,800–0,910)
  • 201 Metabolite analysiert, 41 davon signifikant unterschiedlich
  • 16 Kandidatenbiomarker für die Vorhersage identifiziert

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Multizentrische Studie in JMIR Aging, published online on 2026-04-30. Written by Gengrui Zhong and 7 co-authors. Institution: Department of Critical Care Medicine, The Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, 600 Yishan Road, Sh…. Major MEDLINE topics: Metabolomics, Machine Learning, Delirium, Postoperative Complications. Cited 2 times so far (Crossref); 45 references. The full text is freely available in PubMed Central.

Auf einen BlickSamenvattingSubjectsBibliografische gegevensCiteRelated studies

Abstract (original language)

Background

Postoperative delirium (POD) is a common and severe complication in older adult patients with hip fracture, yet its pathogenesis remains unclear.

Objective

This study aimed to develop a predictive model for POD following hemiarthroplasty in older adult patients by integrating high-throughput targeted metabolomics and machine learning.

Methods

In this prospective multicenter cohort study, 260 older adult patients undergoing hemiarthroplasty for hip fracture were enrolled. Preoperative serum samples were analyzed via high-throughput targeted metabolomics. Differential metabolites were screened using random forest (RF) and least absolute shrinkage and selection operator regression. Predictive models were constructed using gradient boosting, logistic regression, and RF, with performance evaluated using receiver operating characteristic curves and the area under these curves (area under the receiver operating characteristic curve [AUC]).

Results

Absolute quantification of 201 metabolites revealed 41 (20.4%) significantly differentially expressed metabolites. RF and least absolute shrinkage and selection operator regression identified 16 candidate biomarkers. The logistic regression model demonstrated optimal performance, achieving an AUC of 0.855 (95% CI 0.800‐0.910) in the overall cohort. Upon 7:3 partitioning into training and test sets, the model maintained robust predictive accuracy, with AUCs of 0.844 and 0.856, respectively.

Conclusions

Integration of preoperative metabolomics and machine learning enabled accurate prediction of POD in older adult patients with hip fracture, facilitating personalized risk stratification and tailored clinical management.

Subjects

MeSH terms (MEDLINE)

MetabolomicsMachine LearningDeliriumPostoperative ComplicationsHumansProspective StudiesAgedFemaleMaleHip FracturesPredictive Learning ModelsBiomarkersAged, 80 and overRandom ForestROC CurveCohort Studies

Author keywords

high-throughput targeted metabolomicsmachine learningolder adult surgical patientspostoperative deliriumprediction and prevention

Substances

Biomarkers

Authors and institutions

  • Department of Critical Care Medicine, The Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, 600 Yishan Road, Shanghai, 200233, China, 86 15921172011.
  • Department of Critical Care Medicine, Jinshan District Central Hospital, Shanghai, China.
  • Department of Critical Care Medicine, Fengxian District Central Hospital, Shanghai, China.
  • Department of Anesthesiology, Fengxian District Central Hospital, Shanghai, China.
  • Department of Critical Care Medicine, Shanghai Eighth People's Hospital, Shanghai, China.

Cite

APA

Zhong, G., Huang, X., Li, C., Wang, D., Huang, D., Sun, M., Zhou, Q., & Guo, Y. (2026). Integrated High-Throughput Targeted Metabolomics and Machine Learning for Early Prediction and Prevention of Postoperative Delirium in Older Adult Surgical Patients: Prospective Multicenter Cohort Study. JMIR Aging, 9, e78495-e78495. https://doi.org/10.2196/78495

Vancouver

Zhong G, Huang X, Li C, Wang D, Huang D, Sun M, et al. Integrated High-Throughput Targeted Metabolomics and Machine Learning for Early Prediction and Prevention of Postoperative Delirium in Older Adult Surgical Patients: Prospective Multicenter Cohort Study. JMIR Aging. 2026;9:e78495-e78495. doi:10.2196/78495

BibTeX
@article{Zhong2026,
  author = {Zhong, Gengrui and Huang, Xiaoli and Li, Congye and Wang, Deqiang and Huang, Dingding and Sun, Menghan and Zhou, Quanhong and Guo, Yong},
  title = {Integrated High-Throughput Targeted Metabolomics and Machine Learning for Early Prediction and Prevention of Postoperative Delirium in Older Adult Surgical Patients: Prospective Multicenter Cohort Study},
  journal = {JMIR Aging},
  year = {2026},
  volume = {9},
  pages = {e78495--e78495},
  doi = {10.2196/78495}
}
Start for free →