Comparison of Prediction Models for Acute Kidney Injury Among Patients with Hepatobiliary Malignancies Based on XGBoost and LASSO-Logistic Algorithms

A pilot clinical risk model to predict polymyxin-induced nephrotoxicity: a real-world, retrospective cohort study

OBJECTIVES

Polymyxin-induced nephrotoxicity (PIN) is a major safety concern and challenge in clinical practice, which limits the clinical use of polymyxins. This study aims to investigate the risk factors and to develop a scoring tool for the early prediction of PIN.

METHODS

Data on critically ill patients who received intravenous polymyxin B or colistin sulfate for over 24 h were collected. Logistic regression with the least absolute shrinkage and selection operator (LASSO) was used to identify variables that are associated with outcomes. The eXtreme Gradient Boosting (XGB) classifier algorithm was used to further visualize factors with significant differences. A prediction model for PIN was developed through binary logistic regression analysis and the model was assessed by temporal validation and external validation. Finally, a risk-scoring system was developed based on the prediction model.

RESULTS

Of 508 patients, 161 (31.6%) patients developed PIN. Polymyxin type, loading dose, septic shock, concomitant vasopressors and baseline blood urea nitrogen (BUN) level were identified as significant predictors of PIN. All validation exhibited great discrimination, with the AUC of 0.742 (95% CI: 0.696-0.787) for internal validation, of 0.708 (95% CI: 0.605-0.810) for temporal validation and of 0.874 (95% CI: 0.759-0.989) for external validation, respectively. A simple risk-scoring tool was developed with a total risk score ranging from -3 to 4, corresponding to a risk of PIN from 0.79% to 81.24%.

CONCLUSIONS

This study established a prediction model for PIN. Before using polymyxins, the simple risk-scoring tool can effectively identify patients at risk of developing PIN within a range of 7% to 65%.

A machine learning radiomics model based on bpMRI to predict bone metastasis in newly diagnosed prostate cancer patients

OBJECTIVES

To develop and evaluate a machine learning radiomics model based on biparametric magnetic resonance imaging MRI (bpMRI) to predict bone metastasis (BM) status in newly diagnosed prostate cancer (PCa) patients.

METHODS

We retrospectively analyzed bpMRI scans of PCa patients from multiple centers between January 2016 and October 2021. 348 PCa patients were recruited from two institutions for this study. The first institution contributed 284 patients, stratified and randomly divided into training and internal validation cohorts at a 7:3 ratio. The remaining 64 patients were sourced from the second institution and comprised the external validation cohort. Radiomics features were extracted from axial T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) tumor regions. We developed the radiomics prediction model for BM in the training cohort and validated it in the internal and external validation cohorts. As a benchmark, we trained the logistic regression model with lasso feature reduction (LFR-LRM) in the training cohort and further compared it with Naive Bayes, eXtreme Gradient Boosting (XGboost), Random Forest (RF), GBDT, SVM, Adaboost, and KNN algorithms and validated in both the internal and external cohorts. The performance of several predictive models was assessed by receiver operating characteristic (ROC).

RESULTS

The LFR-LRM model achieved an area under the receiver operating characteristic curve (AUC) of 0.89 (95% CI: 0.822-0.974) and an accuracy of 0.828 (95% CI: 0.713-0.911). The AUC and accuracy in external validation were 0.866 (95% CI: 0.784-0.948) and 0.769 (95% CI: 0.648-0.864), respectively. The RF and XGBoost models outperformed the LFR-LRM, with AUCs of 0.907 (95% CI: 0.863-0.949) and 0.928 (95% CI: 0.882-0.974) and accuracies of 0.831 (95% CI: 0.727-0.907) and 0.884 (95% CI: 0.792-0.946). External validation for these models yielded AUCs and accuracies of 0.911 (95% CI: 0.861-0.966), 0.921 (95% CI: 0.889-0.953), and 0.846 (95% CI: 0.735-0.923) and 0.876 (95% CI: 0.771-0.945), respectively.

CONCLUSIONS

The XGboost machine learning model is more accurate than LFR-LRM for predicting BM in patients with newly confirmed PCa.

Assessing the risk of concurrent mycoplasma pneumoniae pneumonia in children with tracheobronchial tuberculosis: retrospective study

Objective

This study aimed to create a predictive model based on machine learning to identify the risk for tracheobronchial tuberculosis (TBTB) occurring alongside Mycoplasma pneumoniae pneumonia in pediatric patients.

Methods

Clinical data from 212 pediatric patients were examined in this retrospective analysis. This cohort included 42 individuals diagnosed with TBTB and Mycoplasma pneumoniae pneumonia (combined group) and 170 patients diagnosed with lobar pneumonia alone (pneumonia group). Three predictive models, namely XGBoost, decision tree, and logistic regression, were constructed, and their performances were assessed using the receiver's operating characteristic (ROC) curve, precision-recall curve (PR), and decision curve analysis (DCA). The dataset was divided into a 7:3 ratio to test the first and second groups, utilizing them to validate the XGBoost model and to construct the nomogram model.

Results

The XGBoost highlighted eight significant signatures, while the decision tree and logistic regression models identified six and five signatures, respectively. The ROC analysis revealed an area under the curve (AUC) of 0.996 for XGBoost, significantly outperforming the other models (p < 0.05). Similarly, the PR curve demonstrated the superior predictive capability of XGBoost. DCA further confirmed that XGBoost offered the highest AIC (43.226), the highest average net benefit (0.764), and the best model fit. Validation efforts confirmed the robustness of the findings, with the validation groups 1 and 2 showing ROC and PR curves with AUC of 0.997, indicating a high net benefit. The nomogram model was shown to possess significant clinical value.

Conclusion

Compared to machine learning approaches, the XGBoost model demonstrated superior predictive efficacy in identifying pediatric patients at risk of concurrent TBTB and Mycoplasma pneumoniae pneumonia. The model's identification of critical signatures provides valuable insights into the pathogenesis of these conditions.

Development of rapid and effective risk prediction models for stroke in the Chinese population: a cross-sectional study

OBJECTIVES

The purpose of this study was to use easily obtained and directly observable clinical features to establish predictive models to identify patients at increased risk of stroke.

SETTING AND PARTICIPANTS

A total of 46 240 valid records were obtained from 8 research centres and 14 communities in Jiangxi province, China, between February and September 2018.

PRIMARY AND SECONDARY OUTCOME MEASURES

The area under the receiver operating characteristic curve (AUC), sensitivity, specificity and accuracy were calculated to test the performance of the five models (logistic regression (LR), random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost) and gradient boosting DT). The calibration curve was used to show calibration performance.

RESULTS

The results indicated that XGBoost (AUC: 0.924, accuracy: 0.873, sensitivity: 0.776, specificity: 0.916) and RF (AUC: 0.924, accuracy: 0.872, sensitivity: 0.778, specificity: 0.913) demonstrated excellent performance in predicting stroke. Physical inactivity, hypertension, meat-based diet and high salt intake were important prediction features of stroke.

CONCLUSION

The five machine learning models all had good predictive and discriminatory performance for stroke. The performance of RF and XGBoost was slightly better than that of LR, which was easier to interpret and less prone to overfitting. This work provides a rapid and accurate tool for stroke risk assessment, which can help to improve the efficiency of stroke screening medical services and the management of high-risk groups.

Machine learning for acute kidney injury: Changing the traditional disease prediction mode

Acute kidney injury (AKI) is a serious clinical comorbidity with clear short-term and long-term prognostic implications for inpatients. The diversity of risk factors for AKI has been recognized in previous studies, and a series of predictive models have been developed using traditional statistical methods in conjunction with its preventability, but they have failed to meet the expectations in limited clinical applications, the rapid spread of electronic health records and artificial intelligence machine learning technology has brought new hope for the construction of AKI prediction models. In this article, we systematically review the definition and classification of machine learning methods, modeling ideas and evaluation methods, and the characteristics and current status of modeling studies. According to the modeling objectives, we subdivided them into critical care medical setting models, all medical environment models, special surgery models, special disease models, and special nephrotoxin exposure models. As the first review article to comprehensively summarize and analyze machine learning prediction models for AKI, we aim to objectively describe the advantages and disadvantages of machine learning approaches to modeling, and help other researchers more quickly and intuitively understand the current status of modeling research, inspire ideas and learn from experience, so as to guide and stimulate more research and more in-depth exploration in the future, which will ultimately provide greater help to improve the overall status of AKI diagnosis and treatment.

Surgical or percutaneous coronary revascularization for heart failure: an in silico model using routinely collected health data to emulate a clinical trial

AIMS

The choice of revascularization with coronary artery bypass grafting (CABG) vs. percutaneous coronary intervention (PCI) in people with ischaemic left ventricular dysfunction is not guided by high-quality evidence.

METHODS AND RESULTS

A trial of CABG vs. PCI in people with heart failure (HF) was modelled in silico using routinely collected healthcare data. The in silico trial cohort was selected by matching the target trial cohort, identified from Hospital Episode Statistics in England, with individual patient data from the Surgical Treatment for Ischemic Heart Failure (STICH) trial. Allocation to CABG vs. complex PCI demonstrated random variation across administrative regions in England and was a valid statistical instrument. The primary outcome was 5-year all-cause mortality or cardiovascular hospitalization. Instrumental variable analysis (IVA) was used for the primary analysis. Results were expressed as average treatment effects (ATEs) with 95 confidence intervals (CIs). The target population included 13 519 HF patients undergoing CABG or complex PCI between April 2009 and March 2015. After matching, the emulated trial cohort included 2046 patients. The unadjusted primary outcome rate was 51.1 in the CABG group and 70.0 in the PCI group. IVA of the emulated cohort showed that CABG was associated with a lower risk of the primary outcome (ATE 16.2, 95 CI 20.6 to 11.8), with comparable estimates in the unmatched target population (ATE 15.5, 95 CI 17.5 to 13.5).

CONCLUSION

In people with HF, in silico modelling suggests that CABG is associated with fewer deaths or cardiovascular hospitalizations at 5 years vs. complex PCI. A pragmatic clinical trial is needed to test this hypothesis and this trial would be feasible.