Support vector machine classification applied on weaning trials patients

Identification and immunological characterization of endoplasmic reticulum stress-related molecular subtypes in bronchopulmonary dysplasia based on machine learning

Introduction: Bronchopulmonary dysplasia (BPD) is a life-threatening lung illness that affects premature infants and has a high incidence and mortality. Using interpretable machine learning, we aimed to investigate the involvement of endoplasmic reticulum (ER) stress-related genes (ERSGs) in BPD patients. Methods: We evaluated the expression profiles of endoplasmic reticulum stress-related genes and immune features in bronchopulmonary dysplasia using the GSE32472 dataset. The endoplasmic reticulum stress-related gene-based molecular clusters and associated immune cell infiltration were studied using 62 bronchopulmonary dysplasia samples. Cluster-specific differentially expressed genes (DEGs) were identified utilizing the WGCNA technique. The optimum machine model was applied after comparing its performance with that of the generalized linear model, the extreme Gradient Boosting, the support vector machine (SVM) model, and the random forest model. Validation of the prediction efficiency was done by the use of a calibration curve, nomogram, decision curve analysis, and an external data set. Results: The bronchopulmonary dysplasia samples were compared to the control samples, and the dysregulated endoplasmic reticulum stress-related genes and activated immunological responses were analyzed. In bronchopulmonary dysplasia, two distinct molecular clusters associated with endoplasmic reticulum stress were identified. The analysis of immune cell infiltration indicated a considerable difference in levels of immunity between the various clusters. As measured by residual and root mean square error, as well as the area under the curve, the support vector machine machine model showed the greatest discriminative capacity. In the end, an support vector machine model integrating five genes was developed, and its performance was shown to be excellent on an external validation dataset. The effectiveness in predicting bronchopulmonary dysplasia subtypes was further established by decision curves, calibration curves, and nomogram analyses. Conclusion: We developed a potential prediction model to assess the risk of endoplasmic reticulum stress subtypes and the clinical outcomes of bronchopulmonary dysplasia patients, and our work comprehensively revealed the complex association between endoplasmic reticulum stress and bronchopulmonary dysplasia.

The Feasibility of a Machine Learning Approach in Predicting Successful Ventilator Mode Shifting for Adult Patients in the Medical Intensive Care Unit

Background and Objectives: Traditional assessment of the readiness for the weaning from the mechanical ventilator (MV) needs respiratory parameters in a spontaneous breath. Exempted from the MV disconnecting and manual measurements of weaning parameters, a prediction model based on parameters from MV and electronic medical records (EMRs) may help the assessment before spontaneous breath trials. The study aimed to develop prediction models using machine learning techniques with parameters from the ventilator and EMRs for predicting successful ventilator mode shifting in the medical intensive care unit. Materials and Methods: A retrospective analysis of 1483 adult patients with mechanical ventilators for acute respiratory failure in three medical intensive care units between April 2015 and October 2017 was conducted by machine learning techniques to establish the predicting models. The input candidate parameters included ventilator setting and measurements, patients’ demographics, arterial blood gas, laboratory results, and vital signs. Several classification algorithms were evaluated to fit the models, including Lasso Regression, Ridge Regression, Elastic Net, Random Forest, Extreme Gradient Boosting (XGBoost), Support Vector Machine, and Artificial Neural Network according to the area under the Receiver Operating Characteristic curves (AUROC). Results: Two models were built to predict the success shifting from full to partial support ventilation (WPMV model) or from partial support to the T-piece trial (sSBT model). In total, 3 MV and 13 nonpulmonary features were selected for the WPMV model with the XGBoost algorithm. The sSBT model was built with 8 MV and 4 nonpulmonary features with the Random Forest algorithm. The AUROC of the WPMV model and sSBT model were 0.76 and 0.79, respectively. Conclusions: The weaning predictions using machine learning and parameters from MV and EMRs have acceptable performance. Without manual measurements, a decision-making system would be feasible for the continuous prediction of mode shifting when the novel models process real-time data from MV and EMRs.

Prediction of clinical conditions after coronary bypass surgery using dynamic data analysis

This work studies the impact of using dynamic information as features in a machine learning algorithm for the prediction task of classifying critically ill patients in two classes according to the time they need to reach a stable state after coronary bypass surgery: less or more than 9 h. On the basis of five physiological variables (heart rate, systolic arterial blood pressure, systolic pulmonary pressure, blood temperature and oxygen saturation), different dynamic features were extracted, namely the means and standard deviations at different moments in time, coefficients of multivariate autoregressive models and cepstral coefficients. These sets of features served subsequently as inputs for a Gaussian process and the prediction results were compared with the case where only admission data was used for the classification. The dynamic features, especially the cepstral coefficients (aROC: 0.749, Brier score: 0.206), resulted in higher performances when compared to static admission data (aROC: 0.547, Brier score: 0.247). The differences in performance are shown to be significant. In all cases, the Gaussian process classifier outperformed to logistic regression.

Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies

Background

Several models for mortality prediction have been constructed for critically ill patients with haematological malignancies in recent years. These models have proven to be equally or more accurate in predicting hospital mortality in patients with haematological malignancies than ICU severity of illness scores such as the APACHE II or SAPS II [1]. The objective of this study is to compare the accuracy of predicting hospital mortality in patients with haematological malignancies admitted to the ICU between models based on multiple logistic regression (MLR) and support vector machine (SVM) based models.

Methods

352 patients with haematological malignancies admitted to the ICU between 1997 and 2006 for a life-threatening complication were included. 252 patient records were used for training of the models and 100 were used for validation. In a first model 12 input variables were included for comparison between MLR and SVM. In a second more complex model 17 input variables were used. MLR and SVM analysis were performed independently from each other. Discrimination was evaluated using the area under the receiver operating characteristic (ROC) curves (± SE).

Results

The area under ROC curve for the MLR and SVM in the validation data set were 0.768 (± 0.04) vs. 0.802 (± 0.04) in the first model (p = 0.19) and 0.781 (± 0.05) vs. 0.808 (± 0.04) in the second more complex model (p = 0.44). SVM needed only 4 variables to make its prediction in both models, whereas MLR needed 7 and 8 variables in the first and second model respectively.

Conclusion

The discriminative power of both the MLR and SVM models was good. No statistically significant differences were found in discriminative power between MLR and SVM for prediction of hospital mortality in critically ill patients with haematological malignancies.