EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Rapid Diagnostic Model for Critical Illness Polyneuropathy Based on Electrophysiological Data

Yang Liu iD, Zihan Zhang, Zihan Jing, Binbin Sun, Hong Zhao iD, Yan Wang, Mao Li, Dehao Li, Dengfa Zhao, Hongmei Cheng, Min Su, Haoyang Hu iD und 3 weitere

CNS Neuroscience & Therapeutics · 2025

DOI: 10.1111/cns.70631 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CNS Neuroscience & Therapeutics, 2025. Verfasst von Yang Liu und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, The First Medical Center, Chinese PLA General Hospital, Beijing, China. Hauptthemen laut MEDLINE: Polyneuropathies, Electrodiagnosis. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Critical illness polyneuropathy (CIP) is a common cause of weakness in critically ill patients, and early diagnosis and treatment are essential. Conventional comprehensive electrophysiological testing requires 60–90 min and can be invasive, limiting its utility in the intensive care setting. This study aimed to develop a rapid, efficient, and minimally invasive diagnostic model for CIP.

Methods

Patients who met the inclusion criteria were recruited from the intensive care units (ICU) of the First Medical Center and Fifth Medical Center of the PLA General Hospital and Nanfang Hospital. To identify the optimal diagnostic model, we compared several machine learning approaches, including K‐nearest neighbor, support vector machine with radial basis function (SVM‐RBF), SVM with Gaussian kernel, random forest, and extreme gradient boosting (XGB), using all electrophysiological features. These were also compared with nerve conduction studies of the peroneal and sural nerves. To construct a rapid diagnostic model, different feature combinations were assessed across the machine learning methods. Model performance was evaluated using cross‐validated areas under the receiver operating characteristic curve (AUCs).

Results

Of 14,768 admissions screened, 134 patients with CIP and 135 matched controls were included. In total, 41 electrophysiological features were analyzed. Feature ranking revealed that the distal compound muscle action potential (CMAP) of the peroneal nerve contributed most to diagnostic accuracy. After comparison, the SVM‐RBF method was selected to establish the final diagnostic model. The optimal model, based on seven electrophysiological features of the peroneal and ulnar nerves (proximal latency, distal latency, and CMAP amplitude), achieved an AUC of 0.93, which was comparable to the all‐feature XGB model (AUC = 0.95). In the independent validation set, the rapid diagnostic model maintained strong performance (AUC = 0.88), similar to the all‐feature model (AUC = 0.90).

Conclusion

We developed a rapid diagnostic model for CIP using the SVM‐RBF method and seven electrophysiological features from the peroneal and ulnar nerves. This model enables efficient, minimally invasive, and timely diagnosis of CIP in critically ill patients. The source code and related scripts are available at [ https://github.com/PLAGH‐Neuro‐Yang/RDM‐CIP ].

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PolyneuropathiesElectrodiagnosisHumansMaleFemaleMiddle AgedCritical IllnessAgedNeural ConductionAdultMachine LearningAction PotentialsSupport Vector MachineRapid Diagnostic Tests

Stichwörter der Autor:innen

critical illness polyneuropathyelectrophysiological dataintensive care unitmachine learningrapid diagnostic model

Autor:innen und Institutionen

  • Department of Neurology, The First Medical Center, Chinese PLA General Hospital, Beijing, China.
  • Neurology Institute of Chinese PLA General Hospital, Beijing, China.
  • School of Medicine, Nankai University, Tianjin, China.
  • Department of Neurology, Nanfang Hospital, Guangzhou, China.
  • Department of Neurology, The Fifth Medical Center, Chinese PLA General Hospital, Beijing, China.

ORCID-Profile: Yang Liu, Hong Zhao, Haoyang Hu, Ruozhuo Liu, Shengyuan Yu, Fei Yang

Zitieren

APA

Liu, Y., Zhang, Z., Jing, Z., Sun, B., Zhao, H., Wang, Y., Li, M., Li, D., Zhao, D., Cheng, H., Su, M., Hu, H., Liu, R., Yu, S., & Yang, F. (2025). Rapid Diagnostic Model for Critical Illness Polyneuropathy Based on Electrophysiological Data. CNS Neuroscience & Therapeutics. https://doi.org/10.1111/cns.70631

Vancouver

Liu Y, Zhang Z, Jing Z, Sun B, Zhao H, Wang Y, et al. Rapid Diagnostic Model for Critical Illness Polyneuropathy Based on Electrophysiological Data. CNS Neuroscience & Therapeutics. 2025. doi:10.1111/cns.70631

BibTeX
@article{Liu2025,
  author = {Liu, Yang and Zhang, Zihan and Jing, Zihan and Sun, Binbin and Zhao, Hong and Wang, Yan and Li, Mao and Li, Dehao and Zhao, Dengfa and Cheng, Hongmei and Su, Min and Hu, Haoyang and Liu, Ruozhuo and Yu, Shengyuan and Yang, Fei},
  title = {Rapid Diagnostic Model for Critical Illness Polyneuropathy Based on Electrophysiological Data},
  journal = {CNS Neuroscience & Therapeutics},
  year = {2025},
  doi = {10.1111/cns.70631}
}
Kostenlos starten →