Association between Mean Arterial Pressure during the First 24 Hours and Clinical Outcome in Critically Ill Stroke Patients: An Analysis of the MIMIC-III Database

A novel higher performance nomogram based on explainable machine learning for predicting mortality risk in stroke patients within 30 days based on clinical features on the first day ICU admission

BACKGROUND

This study aimed to develop a higher performance nomogram based on explainable machine learning methods, and to predict the risk of death of stroke patients within 30 days based on clinical characteristics on the first day of intensive care units (ICU) admission.

METHODS

Data relating to stroke patients were extracted from the Medical Information Marketplace of the Intensive Care (MIMIC) IV and III database. The LightGBM machine learning approach together with Shapely additive explanations (termed as explain machine learning, EML) was used to select clinical features and define cut-off points for the selected features. These selected features and cut-off points were then evaluated using the Cox proportional hazards regression model and Kaplan-Meier survival curves. Finally, logistic regression-based nomograms for predicting 30-day mortality of stroke patients were constructed using original variables and variables dichotomized by cut-off points, respectively. The performance of two nomograms were evaluated in overall and individual dimension.

RESULTS

A total of 2982 stroke patients and 64 clinical features were included, and the 30-day mortality rate was 23.6% in the MIMIC-IV datasets. 10 variables ("sofa (sepsis-related organ failure assessment)", "minimum glucose", "maximum sodium", "age", "mean spo2 (blood oxygen saturation)", "maximum temperature", "maximum heart rate", "minimum bun (blood urea nitrogen)", "minimum wbc (white blood cells)" and "charlson comorbidity index") and respective cut-off points were defined from the EML. In the Cox proportional hazards regression model (Cox regression) and Kaplan-Meier survival curves, after grouping stroke patients according to the cut-off point of each variable, patients belonging to the high-risk subgroup were associated with higher 30-day mortality than those in the low-risk subgroup. The evaluation of nomograms found that the EML-based nomogram not only outperformed the conventional nomogram in NIR (net reclassification index), brier score and clinical net benefits in overall dimension, but also significant improved in individual dimension especially for low "maximum temperature" patients.

CONCLUSIONS

The 10 selected first-day ICU admission clinical features require greater attention for stroke patients. And the nomogram based on explainable machine learning will have greater clinical application.

Exploring the utility of a latent variable as comprehensive inflammatory prognostic index in critically ill patients with cerebral infarction

Objective

We introduce the comprehensive inflammatory prognostic index (CIPI), a novel prognostic tool for critically ill cerebral infarction patients, designed to meet the urgent need for timely and convenient clinical decision-making in this high-risk patient group.

Methods

Using exploratory factor analysis on selected indices-neutrophil to lymphocyte ratio (NLR), systemic inflammation response index (SIRI), and systemic immune inflammation index (SIII)-we derived CIPI, a latent variable capturing their combined predictive power. Data from 1,022 patients in the Medical Information Mart for Intensive Care (MIMIC)-IV database were used to develop CIPI-based survival models, with the robustness and area under the receiver operating characteristic curve (AUC) performance of CIPI validated against an independent dataset of 326 patients from the MIMIC-III CareVue subset. The CIPI's predictive power for in-hospital and intensive care unit (ICU) mortality was assessed through Kaplan-Meier analysis, univariate and multivariate Cox regression models, and time-dependent AUC analysis. Linearity, subgroup sensitivity analyses and interaction effects with CIPI were also evaluated.

Results

CIPI was an independent prognostic factor, demonstrating a statistically significant association with in-hospital and ICU mortality, when assessed as a continuous and a categorical variable. It showed a linear relationship with mortality rates and demonstrated stability across most subgroups, with no significant interactions observed. Its predictive capabilities for in-hospital and ICU mortality among critically ill cerebral infarction patients matched those of established prognostic indices in the MIMIC database.

Conclusion

Our study indicates that CIPI is a reliable and effective prognostic tool for critically ill cerebral infarction patients in predicting in-hospital and ICU mortality. Its straightforward calculation, rooted in routine blood tests, enhances its practicality, promising significant utility in clinical settings.