EUVIMEDEUVIMED entdecken
Beobachtungsstudie

Predicting Postoperative Cognitive Dysfunction in Older Cardiac Surgery Patients: An Integrated Machine Learning Approach With a Visual Nomogram

Ming Sang, Fengxia Weng, Sirui Wang, Ping Zhang, Yanan Leng, Jianhua Wei

Journal of Cardiothoracic and Vascular Anesthesia · 2026-09 · 40 (9) · 2865-2874

DOI: 10.1053/j.jvca.2026.04.010 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Journal of Cardiothoracic and Vascular Anesthesia, 2026-09. Verfasst von Ming Sang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nursing, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Electronic address: mingsang@zju.edu.c…. Hauptthemen laut MEDLINE: Machine Learning, Nomograms, Cardiac Surgical Procedures, Postoperative Cognitive Complications. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Chinese Medical Association.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: To integrate machine learning algorithms to identify key risk factors for postoperative cognitive dysfunction (POCD) in older cardiac surgery patients and to develop a predictive nomogram to assist clinicians and nurses in identifying high-risk patients and implementing targeted interventions. DESIGN: Prospective observational cohort study. SETTING: Surgical intensive care unit (ICU) of a tertiary academic medical center. PARTICIPANTS: A total of 353 consecutive older patients (aged ≥ 60 years) who underwent cardiac surgery. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Comprehensive perioperative data, including demographic characteristics, laboratory findings, and clinical variables, were collected. The least absolute shrinkage and selection operator regression was used for predictor selection, followed by multivariate logistic regression to construct the nomogram. The overall incidence of POCD was 49.86% (176 of 353). Seven independent predictors were identified and incorporated into the model: surgical approach, pre-existing comorbidities, surgery duration, intraoperative blood loss, ICU sleep quality score, Acute Physiology and Chronic Health Evaluation II (APACHE II) score, and preoperative self-care ability. The nomogram demonstrated good discrimination, with an area under the receiver operating characteristic curve of 0.786 (95% confidence interval, 0.738-0.834). Calibration curves indicated excellent agreement between predicted and observed probabilities. Decision curve analysis confirmed the model's clinical net benefit across a wide range of threshold probabilities. CONCLUSIONS: A precise and effective nomogram was developed using surgical approach, underlying comorbidities, surgery duration, blood loss, ICU sleep quality score, APACHE II score, and self-care ability as predictors of POCD in older cardiac surgery patients. This tool may facilitate early risk stratification and targeted prevention strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningNomogramsCardiac Surgical ProceduresPostoperative Cognitive ComplicationsPostoperative ComplicationsHumansFemaleMaleProspective StudiesAgedRisk FactorsCohort StudiesMiddle AgedPredictive Learning ModelsAged, 80 and overPredictive Value of Tests

Stichwörter der Autor:innen

cardiac surgerycognitive dysfunctionmachine learningnomogramsrisk assessment

Autor:innen und Institutionen

  • Department of Nursing, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Electronic address: mingsang@zju.edu.cn.
  • Department of Nursing, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Electronic address: 112715133@qq.com.
  • Department of Nursing, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Electronic address: 1371265631@qq.com.
  • Department of Nursing, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Electronic address: 524741366@qq.com.
  • Department of Hepatobiliary Surgery, Southwest Hospital, The First Affiliated Hospital to Army Medical University, Chongqing, China. Electronic address: lengyn1220@163.com.
  • Department of Nursing, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Electronic address: 1188029@zju.edu.cn.

Förderung

  • Chinese Medical Association

Zitieren

APA

Sang, M., Weng, F., Wang, S., Zhang, P., Leng, Y., & Wei, J. (2026). Predicting Postoperative Cognitive Dysfunction in Older Cardiac Surgery Patients: An Integrated Machine Learning Approach With a Visual Nomogram. Journal of Cardiothoracic and Vascular Anesthesia, 40(9), 2865-2874. https://doi.org/10.1053/j.jvca.2026.04.010

Vancouver

Sang M, Weng F, Wang S, Zhang P, Leng Y, Wei J. Predicting Postoperative Cognitive Dysfunction in Older Cardiac Surgery Patients: An Integrated Machine Learning Approach With a Visual Nomogram. Journal of Cardiothoracic and Vascular Anesthesia. 2026;40(9):2865-2874. doi:10.1053/j.jvca.2026.04.010

BibTeX
@article{Sang2026,
  author = {Sang, Ming and Weng, Fengxia and Wang, Sirui and Zhang, Ping and Leng, Yanan and Wei, Jianhua},
  title = {Predicting Postoperative Cognitive Dysfunction in Older Cardiac Surgery Patients: An Integrated Machine Learning Approach With a Visual Nomogram},
  journal = {Journal of Cardiothoracic and Vascular Anesthesia},
  year = {2026},
  volume = {40},
  number = {9},
  pages = {2865--2874},
  doi = {10.1053/j.jvca.2026.04.010}
}
Kostenlos starten →