Related Experiment Video
Updated: Jun 27, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Development and validation of a nomogram for delirium in the old ischaemic stroke patients
Xiaoyan Cai1,2, Xuefen Yu3, Jieying Qin2
1Department of Nursing, Foshan Stomatology Hospital, the Affiliated Stomatology Hospital of Foshan University, Foshan, China.
Aim:
To investigate the predictors of post-stroke delirium (PSD) in the old ischaemic stroke patients, and develop a nomogram to predict the risk of PSD.
Methods:
A cross-observational study was conducted. The old ischaemic stroke patients in a tertiary hospital in South China were recruited and randomly divided into the train group and test group. Multivariate logistic regression analysis was performed in the train group to screen out predictors of PSD, and develop a nomogram. The receiver operating characteristic (ROC) curve, calibration curve, Hosmer-Lemeshow goodness-of-fit test (H-L test) and decision curve analysis (DCA) were used to evaluate the nomogram. The internal validation was performed in test group.
Results:
The incidence of PSD was 21.1% (105/497). Coronary heart disease (CHD), indwelling catheter, physical restraint, and neutrophil-to-lymphocyte ratio (NLR) were significantly associated with PSD. The area under the ROC curve of the nomogram was 0.885 in the train group, and 0.865 in the test group. The calibration curves of the two groups were close to the standardised line. The P-values of H-L test were over 0.05. The DCA presented some net benefits in the two groups.
Conclusion:
CHD, indwelling catheter, restraint, and NLR were strongly associated with PSD in the old. A nomogram with good prediction effect and advisable clinical applicability was developed.
