A Simple Weaning Model Based on Interpretable Machine Learning Algorithm for Patients With Sepsis: A Research of MIMIC-IV and eICU Databases

Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study

Sepsis triggers a harmful immune response due to infection, causing high mortality. Predicting sepsis outcomes early is vital. Despite machine learning's (ML) use in medical research, local validation within the Medical Information Mart for Intensive Care IV (MIMIC-IV) database is lacking. We aimed to devise a prognostic model, leveraging MIMIC-IV data, to predict sepsis mortality and validate it in a Chinese teaching hospital. MIMIC-IV provided patient data, split into training and internal validation sets. Four ML models logistic regression (LR), support vector machine (SVM), deep neural networks (DNN), and extreme gradient boosting (XGBoost) were employed. Shapley additive interpretation offered early and interpretable mortality predictions. Area under the ROC curve (AUROC) gaged predictive performance. Results were cross verified in a Chinese teaching hospital. The study included 27,134 sepsis patients from MIMIC-IV and 487 from China. After comparing, 52 clinical indicators were selected for ML model development. All models exhibited excellent discriminative ability. XGBoost surpassed others, with AUROC of 0.873 internally and 0.844 externally. XGBoost outperformed other ML models (LR: 0.829; SVM: 0.830; DNN: 0.837) and clinical scores (Simplified Acute Physiology Score II: 0.728; Sequential Organ Failure Assessment: 0.728; Oxford Acute Severity of Illness Score: 0.738; Glasgow Coma Scale: 0.691). XGBoost's hospital mortality prediction achieved AUROC 0.873, sensitivity 0.818, accuracy 0.777, specificity 0.768, and F1 score 0.551. We crafted an interpretable model for sepsis death risk prediction. ML algorithms surpassed traditional scores for sepsis mortality forecast. Validation in a Chinese teaching hospital echoed these findings.

Early Warning Models Using Machine Learning to Predict Sepsis-Associated Chronic Critical Illness: A Study Based on the Medical Information Mart for Intensive Care Database

Background Patients with chronic critical illness (CCI) experience poor prognoses and incur high medical costs. However, there is currently limited clinical awareness of sepsis-associated CCI, resulting in insufficient vigilance. Therefore, it is necessary to build a machine learning model that can predict whether sepsis patients will develop CCI. Methods Clinical data on 19,077 sepsis patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were analyzed. Predictive factors were identified using the Student's t-test, Mann-Whitney U test, or χ 2 test. Six machine learning classification models, namely, the logistic regression, support vector machine, decision tree, random forest, extreme gradient enhancement, and artificial neural network, were established. The optimal model was selected on the basis of its performance. Calibration curves were used to evaluate the accuracy of model classification, while the external validation dataset was used to evaluate the performance of the model. Results Thirty-seven characteristics, such as elevated alanine aminotransferase, rapid heart rate, and high Logistic Organ Dysfunction System scores, were identified as risk factors for developing CCI. The area under the receiver operating characteristic curve (AUROC) values for all models were above 0.73 on the internal test set. Among them, the extreme gradient enhancement model exhibited superior performance (F1 score = 0.91, AUROC = 0.91, Brier score = 0.052). It also exhibited stable prediction performance on the external validation set (AUROC = 0.72). Conclusion A machine learning model was established to predict whether sepsis patients will develop CCI. It can provide useful predictive information for clinical decision-making.

Exploring Predictive Factors for Heart Failure Progression in Hypertensive Patients Based on Medical Diagnosis Data from the MIMIC-IV Database

Heart failure is associated with a significant mortality rate, and an elevated prevalence of this condition has been noted among hypertensive patients. The identification of predictive factors for heart failure progression in hypertensive individuals is crucial for early intervention and improved patient outcomes. In this study, we aimed to identify these predictive factors by utilizing medical diagnosis records for hypertension patients from the MIMIC-IV database. In particular, we employed only diagnostic history prior to hypertension to enable patients to anticipate the onset of heart failure at the moment of hypertension diagnosis. In the methodology, chi-square tests and XGBoost modeling were applied to examine age-specific predictive factors across four groups: AL (all ages), G1 (0 to 65 years), G2 (65 to 80 years), and G3 (over 80 years). As a result, the chi-square tests identified 34, 28, 20, and 10 predictive factors for the AL, G1, G2, and G3 groups, respectively. Meanwhile, the XGBoost modeling uncovered 19, 21, 27, and 33 predictive factors for these respective groups. Ultimately, our findings reveal 21 overall predictive factors, encompassing conditions such as atrial fibrillation, the use of anticoagulants, kidney failure, obstructive pulmonary disease, and anemia. These factors were assessed through a comprehensive review of the existing literature. We anticipate that the results will offer valuable insights for the risk assessment of heart failure in hypertensive patients.

Predicting sepsis onset in ICU using machine learning models: a systematic review and meta-analysis

BACKGROUND

Sepsis is a life-threatening condition caused by an abnormal response of the body to infection and imposes a significant health and economic burden worldwide due to its high mortality rate. Early recognition of sepsis is crucial for effective treatment. This study aimed to systematically evaluate the performance of various machine learning models in predicting the onset of sepsis.

METHODS

We conducted a comprehensive search of the Cochrane Library, PubMed, Embase, and Web of Science databases, covering studies from database inception to November 14, 2022. We used the PROBAST tool to assess the risk of bias. We calculated the predictive performance for sepsis onset using the C-index and accuracy. We followed the PRISMA guidelines for this study.

RESULTS

We included 23 eligible studies with a total of 4,314,145 patients and 26 different machine learning models. The most frequently used models in the studies were random forest (n = 9), extreme gradient boost (n = 7), and logistic regression (n = 6) models. The random forest (test set n = 9, acc = 0.911) and extreme gradient boost (test set n = 7, acc = 0.957) models were the most accurate based on our analysis of the predictive performance. In terms of the C-index outcome, the random forest (n = 6, acc = 0.79) and extreme gradient boost (n = 7, acc = 0.83) models showed the highest performance.

CONCLUSION

Machine learning has proven to be an effective tool for predicting sepsis at an early stage. However, to obtain more accurate results, additional machine learning methods are needed. In our research, we discovered that the XGBoost and random forest models exhibited the best predictive performance and were most frequently utilized for predicting the onset of sepsis.

TRIAL REGISTRATION

CRD42022384015.

Interpretable machine learning for predicting 28-day all-cause in-hospital mortality for hypertensive ischemic or hemorrhagic stroke patients in the ICU: a multi-center retrospective cohort study with internal and external cross-validation

Background

Timely and accurate outcome prediction plays a critical role in guiding clinical decisions for hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. However, interpreting and translating the predictive models into clinical applications are as important as the prediction itself. This study aimed to develop an interpretable machine learning (IML) model that accurately predicts 28-day all-cause mortality in hypertensive ischemic or hemorrhagic stroke patients.

Methods

A total of 4,274 hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU in the USA from multicenter cohorts were included in this study to develop and validate the IML model. Five machine learning (ML) models were developed, including artificial neural network (ANN), gradient boosting machine (GBM), eXtreme Gradient Boosting (XGBoost), logistic regression (LR), and support vector machine (SVM), to predict mortality using the MIMIC-IV and eICU-CRD database in the USA. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Model performance was evaluated based on the area under the curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV). The ML model with the best predictive performance was selected for interpretability analysis. Finally, the SHapley Additive exPlanations (SHAP) method was employed to evaluate the risk of all-cause in-hospital mortality among hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU.

Results

The XGBoost model demonstrated the best predictive performance, with the AUC values of 0.822, 0.739, and 0.700 in the training, test, and external cohorts, respectively. The analysis of feature importance revealed that age, ethnicity, white blood cell (WBC), hyperlipidemia, mean corpuscular volume (MCV), glucose, pulse oximeter oxygen saturation (SpO2), serum calcium, red blood cell distribution width (RDW), blood urea nitrogen (BUN), and bicarbonate were the 11 most important features. The SHAP plots were employed to interpret the XGBoost model.

Conclusions

The XGBoost model accurately predicted 28-day all-cause in-hospital mortality among hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. The SHAP method can provide explicit explanations of personalized risk prediction, which can aid physicians in understanding the model.

Explainable Machine Learning to Predict Successful Weaning of Mechanical Ventilation in Critically Ill Patients Requiring Hemodialysis

Lungs and kidneys are two vital and frequently injured organs among critically ill patients. In this study, we attempt to develop a weaning prediction model for patients with both respiratory and renal failure using an explainable machine learning (XML) approach. We used the eICU collaborative research database, which contained data from 335 ICUs across the United States. Four ML models, including XGBoost, GBM, AdaBoost, and RF, were used, with weaning prediction and feature windows, both at 48 h. The model's explanations were presented at the domain, feature, and individual levels by leveraging various techniques, including cumulative feature importance, the partial dependence plot (PDP), the Shapley additive explanations (SHAP) plot, and local explanation with the local interpretable model-agnostic explanations (LIME). We enrolled 1789 critically ill ventilated patients requiring hemodialysis, and 42.8% (765/1789) of them were weaned successfully from mechanical ventilation. The accuracies in XGBoost and GBM were better than those in the other models. The discriminative characteristics of six key features used to predict weaning were demonstrated through the application of the SHAP and PDP plots. By utilizing LIME, we were able to provide an explanation of the predicted probabilities and the associated reasoning for successful weaning on an individual level. In conclusion, we used an XML approach to establish a weaning prediction model in critically ill ventilated patients requiring hemodialysis.

Development and validation of a mechanical power-oriented prediction model of weaning failure in mechanically ventilated patients: a retrospective cohort study

OBJECTIVE

To develop and validate a mechanical power (MP)-oriented prediction model of weaning failure in mechanically ventilated patients.

DESIGN

A retrospective cohort study.

SETTING

Data were collected from the large US Medical Information Mart for Intensive Care-IV (MIMIC-IV) V.1.0, which integrates comprehensive clinical data from 76 540 intensive care unit (ICU) admissions from 2008 to 2019.

PARTICIPANTS

A total of 3695 patients with invasive mechanical ventilation for more than 24 hours and weaned with T-tube ventilation strategies were enrolled from the MIMIC-IV database.

PRIMARY AND SECONDARY OUTCOME

Weaning failure.

RESULTS

All eligible patients were randomised into development cohorts (n=2586, 70%) and validation cohorts (n=1109, 30%). Multivariate logistic regression analysis of the development cohort showed that positive end-expiratory pressure, dynamic lung compliance, MP, inspired oxygen concentration, length of ICU stay and invasive mechanical ventilation duration were independent predictors of weaning failure. Calibration curves showed good correlation between predicted and observed outcomes. The prediction model showed accurate discrimination in the development and validation cohorts, with area under the receiver operating characteristic curve values of 0.828 (95% CI: 0.812 to 0.844) and 0.833 (95% CI: 0.809 to 0.857), respectively. Decision curve analysis indicated that the predictive model was clinically beneficial.

CONCLUSION

The MP-oriented model of weaning failure accurately predicts the risk of weaning failure in mechanical ventilation patients and provides valuable information for clinicians making decisions on weaning.

Explainable machine learning approach to predict extubation in critically ill ventilated patients: a retrospective study in central Taiwan

Background

Weaning from mechanical ventilation (MV) is an essential issue in critically ill patients, and we used an explainable machine learning (ML) approach to establish an extubation prediction model.

Methods

We enrolled patients who were admitted to intensive care units during 2015–2019 at Taichung Veterans General Hospital, a referral hospital in central Taiwan. We used five ML models, including extreme gradient boosting (XGBoost), categorical boosting (CatBoost), light gradient boosting machine (LightGBM), random forest (RF) and logistic regression (LR), to establish the extubation prediction model, and the feature window as well as prediction window was 48 h and 24 h, respectively. We further employed feature importance, Shapley additive explanations (SHAP) plot, partial dependence plot (PDP) and local interpretable model-agnostic explanations (LIME) for interpretation of the model at the domain, feature, and individual levels.

Results

We enrolled 5,940 patients and found the accuracy was comparable among XGBoost, LightGBM, CatBoost and RF, with the area under the receiver operating characteristic curve using XGBoost to predict extubation was 0.921. The calibration and decision curve analysis showed well applicability of models. We also used the SHAP summary plot and PDP plot to demonstrate discriminative points of six key features in predicting extubation. Moreover, we employed LIME and SHAP force plots to show predicted probabilities of extubation and the rationale of the prediction at the individual level.

Conclusions

We developed an extubation prediction model with high accuracy and visualised explanations aligned with clinical workflow, and the model may serve as an autonomous screen tool for timely weaning.

Research trends and global productivity on mechanical ventilation with the impact of COVID-19: a bibliometric analysis in the period 1980-2021

Aim: Although the number of global studies on mechanical ventilation (MV) therapy, which plays an important role in the life process of patients in the intensive care unit, has increased, there is still no bibliometric research on this subject in the literature. This study, it was aimed to determine trend topics and global productivity by holistically analyzing scientific articles on MV published between 1980 and 2021 using various statistical methods and bibliometric approaches. Material and Method: Articles on MV published between 1980 and 2021 were downloaded from the Web of Science (WoS) database and analyzed using various statistical methods. Spearman's correlation coefficient was used for correlation studies. Network visualization maps were used to identify the most effective studies with global collaborations, trend topics, and citation analysis. Results: The study, which was in the category of 5323 articles out of a total of 10135 publications, was analyzed. The first 3 countries that contributed the most to the literature were the USA (n=1740), France (448), and Canada (386). The most active author was Laurent Brochard (n=50). The top 3 most active institutions were Assistance Publique Hopitaux Paris (224), University of Toronto (216), and League of European Research Universities (169). The top 3 journals that published the most articles were Critical Care Medicine (289), Chest (204), and Intensive Care Medicine (166). Gross Domestic Product (GDP) was highly effective in article productivity (r=0.719, p