[Development and validation of nomograms for predicting stroke recurrence after firstepisode ischemic stroke]

[Comparison of prediction ability of two extended Cox models in nonlinear survival data analysis]

OBJECTIVE

To compare the predictive ability of two extended Cox models in nonlinear survival data analysis.

METHODS

Through Monte Carlo simulation and empirical study and with the conventional Cox Proportional Hazards model and Random Survival Forests as the reference models, we compared restricted cubic spline Cox model (Cox_RCS) and DeepSurv neural network Cox model (Cox_DNN) for their prediction ability in nonlinear survival data analysis. Concordance index was used to evaluate the differentiation of the prediction results (a larger concordance index indicates a better prediction ability of the model). Integrated Brier Score was used to evaluate the calibration degree of the prediction (a smaller index indicates a better prediction ability).

RESULTS

For data that met requirement of the proportion risk, the Cox_RCS model had the best prediction ability regardless of the sample size or deletion rate. For data that failed to meet the proportion risk, the prediction ability of Cox_DNN was optimal for a large sample size (≥500) with a low deletion (< 40%); the prediction ability of Cox_RCS was superior to those of other models in all other scenarios. For example data, the Cox_RCS model showed the best performance.

CONCLUSION

In analysis of nonlinear low maintenance data, Cox_RCS and Cox_DNN have their respective advantages and disadvantages in prediction. The conventional survival analysis methods are not inferior to machine learning or deep learning methods under certain conditions.

Prediction of Ischemic Stroke Recurrence Based on COX Proportional Risk Regression Model and Evaluation of the Effectiveness of Patient Intensive Care Interventions

With the continuous improvement of medical technology and the aging of the population, the death rate of stroke is gradually decreasing, but the recurrence rate is still high, and the number of recurrences is increasing, resulting in disability and other symptoms, which brings great burden and distress to patients and their families. As the number of strokes increases, neurological impairment becomes more and more severe, affecting patients' ability to live, socialize, and work, and seriously reducing their quality of life. Clustered care is a combination of evidence-based linked interventions and a multidisciplinary team providing the best possible care through evidence-based research and highly operational practice, and it can improve outcomes for ischemic stroke patients more than implementation alone. This paper presents a Cox proportional risk regression-based model, using it to build the most used semi-parametric model for multifactorial survival analysis, due to its advantages of both parametric and nonparametric models, and to analyze the factors influencing survival time in study subjects with incomplete data. The proposed strategy has been found to be useful in predicting ischemic stroke recurrence and cluster care interventions for patients.