Prediction Model of Postoperative Severe Hypocalcemia in Patients with Secondary Hyperparathyroidism Based on Logistic Regression and XGBoost Algorithm

Machine learning prediction models for multidrug-resistant organism infections in ICU ventilator-associated pneumonia patients: Analysis using the MIMIC-IV database

OBJECTIVE

This study aims to construct and compare four machine learning models using the MIMIC-IV database to identify high-risk factors for multidrug-resistant organism (MDRO) infection in Ventilator-associated pneumonia (VAP) patients.

METHODS

The study included 972 VAP patients from the MIMIC-IV database. Data encompassing demographic information, vital signs, laboratory results, and other relevant variables were collected. The class imbalance issue was addressed using the Synthetic Minority Over-sampling Technique (SMOTE). The dataset was randomly split into training and testing sets (8:2). LASSO regression and feature importance scores were used for feature selection. Clinical prediction models were built using logistic regression, XGBoost, random forest and gradient boosting machine. The performance of the models was evaluated through receiver operating characteristic(ROC) curve analysis.Model calibration was assessed using calibration curves and Brier scores. The effectiveness was evaluated through Decision Curve Analysis (DCA). SHAP was utilized for model interpretation.

RESULTS

Among 972 patients, 824 were non-MDROs-VAP and 128 were MDROs-VAP. Comparative analysis revealed statistically significant differences in various clinical parameters. XGBoost exhibited the best predictive performance, incorporating 20 features with an AUC of 0.831 (95 % CI: 0.785-0.877) on the test set. Calibration curves demonstrated robust consistency, corroborated by Decision Curve Analysis (DCA) affirming the clinical utility. SHAP analysis identified the most important features: red cell distribution width, duration of mechanical ventilation, anion gap, basophil percentage, and neutrophil percentage.

CONCLUSION

This study established and compared four machine learning models for MDROs infections in VAP patients. XGBoost was identified as the optimal predictor, and SHAP values provided insights into 20 independent risk factors, confirming its excellent predictive value.

IMPLICATIONS FOR CLINICAL PRACTICE

VAP is a common infection in ICU patients with a heightened risk of MDRO and increased mortality. The recognition of high bias in existing models calls for future research to employ rigorous methodologies and robust data sources, aiming to develop and validate more accurate and clinically applicable predictive models for MDROs infections in VAP patients.

Determinants of Severe Hypocalcemia After Parathyroidectomy in Patients with End-Stage Kidney Disease and Renal Hyperparathyroidism: A Retrospective Cohort Study

Background: Parathyroidectomy (PTX) is generally curative in renal hyperparathyroidism (RHPT) that is refractory to medical treatment in end-stage kidney disease (ESKD) patients. Severe hypocalcemia is a common complication of PTX and results in increased monitoring, interventions, lengths of stay, and costs of care. This study aimed to find the determinants and cutoff values of the biochemical determinants, if any, for severe post-operative hypocalcemia after PTX in adult patients with ESKD. Methods: Severe post-operative hypocalcemia was defined as a lowest adjusted serum calcium level < 2 mmol/L during a hospitalization stay following PTX. Receiver operating curves (ROCs) with area under the curve (AUC) values for pre-operative intact parathyroid hormone (iPTH) and pre-operative alkaline phosphatase (ALP) levels against hypocalcemia were used to determine cutoffs. Generalized linear models using Poisson regression with robust error variance were used to estimate the relative risk of severe post-operative hypocalcemia. Results: In total, 75 patients (38 women, 50.7%) with a mean age of 53.8 ± 11.4 years were enrolled; 43 (57%) patients developed severe hypocalcemia post-PTX and had higher pre-operative serum iPTH and ALP levels, as well as a significantly longer hospitalization post-operation (10.5 vs. 4.3 days, p =< 0.001). A pre-operative iPTH level of >166 pmol/L had an AUC-ROC of 0.73 and 72% sensitivity and 73% specificity, respectively, in predicting severe post-operative hypocalcemia with a relative risk of 2.00 [95% CI 1.27-3.33, p = 0.003]. Conclusions: A pre-operative iPTH level > 166 pmol/L is a strong risk predictor for post-operative severe hypocalcemia. Pre-emptive interventions in this high-risk group could potentially result in a reduced length of stay and lower acuity of care.

Machine learning-based models for prediction of the risk of stroke in coronary artery disease patients receiving coronary revascularization

BACKGROUND

To construct several prediction models for the risk of stroke in coronary artery disease (CAD) patients receiving coronary revascularization based on machine learning methods.

METHODS

In total, 5757 CAD patients receiving coronary revascularization admitted to ICU in Medical Information Mart for Intensive Care IV (MIMIC-IV) were included in this cohort study. All the data were randomly split into the training set (n = 4029) and testing set (n = 1728) at 7:3. Pearson correlation analysis and least absolute shrinkage and selection operator (LASSO) regression model were applied for feature screening. Variables with Pearson correlation coefficient<9 were included, and the regression coefficients were set to 0. Features more closely related to the outcome were selected from the 10-fold cross-validation, and features with non-0 Coefficent were retained and included in the final model. The predictive values of the models were evaluated by sensitivity, specificity, area under the curve (AUC), accuracy, and 95% confidence interval (CI).

RESULTS

The Catboost model presented the best predictive performance with the AUC of 0.831 (95%CI: 0.811-0.851) in the training set, and 0.760 (95%CI: 0.722-0.798) in the testing set. The AUC of the logistic regression model was 0.789 (95%CI: 0.764-0.814) in the training set and 0.731 (95%CI: 0.686-0.776) in the testing set. The results of Delong test revealed that the predictive value of the Catboost model was significantly higher than the logistic regression model (P<0.05). Charlson Comorbidity Index (CCI) was the most important variable associated with the risk of stroke in CAD patients receiving coronary revascularization.

CONCLUSION

The Catboost model was the optimal model for predicting the risk of stroke in CAD patients receiving coronary revascularization, which might provide a tool to quickly identify CAD patients who were at high risk of postoperative stroke.