Machine learning models of clinically relevant biomarkers for the prediction of stable obstructive coronary artery disease

Machine learning-based prediction of composite risk of cardiovascular events in patients with stable angina pectoris combined with coronary heart disease: development and validation of a clinical prediction model for Chinese patients

Objective: To develop a risk score model for the occurrence of composite cardiovascular events (CVE) in patients with stable angina pectoris (SA) combined with coronary heart disease (CHD) by comparing the modeling effects of various machine learning (ML) algorithms. Methods: In this prospective study, 690 patients with SA combined with CHD attending the Department of Integrative Cardiology, China-Japan Friendship Hospital, from October 2020 to October 2021 were included. The data set was randomly divided into a training group and a testing group in a 7:3 ratio in the per-protocol set (PPS). Model variables were screened using the least absolute shrinkage selection operator (LASSO) regression, univariate analysis, and multifactor logistic regression. Then, nine ML algorithms are integrated to build the model and compare the model effects. Individualized risk assessment was performed using the SHapley Additive exPlanation (SHAP) and nomograms, respectively. The model discrimination was evaluated by receiver operating characteristic curve (ROC), the calibration ability of the model was evaluated by calibration plot, and the clinical applicability of the model was evaluated by decision curve analysis (DCA). This study was approved by the Clinical Research Ethics Committee of China-Japan Friendship Hospital (2020-114-K73). Results: 690 patients were eligible to finish the complete follow-up in the PPS. After LASSO screening and multifactorial logistic regression analysis, physical activity level, taking antiplatelets, Traditional Chinese medicine treatment, Gensini score, Seattle Angina Questionnaire (SAQ)-exercise capacity score, and SAQ-anginal stability score were found to be predictors of the occurrence of CVE. The above predictors are modeled, and a comprehensive comparison of the modeling effectiveness of multiple ML algorithms is performed. The results show that the Light Gradient Boosting Machine (LightGBM) model is the best model, with an area under the curve (AUC) of 0.95 (95% CI = 0.91-1.00) for the test set, Accuracy: 0.90, Sensitivity: 0.87, and Specificity: 0.96. Interpretation of the model using SHAP highlighted the Gensini score as the most important predictor. Based on the multifactorial logistic regression modeling, a nomogram, and online calculators have been developed for clinical applications. Conclusion: We developed the LightGBM optimization model and the multifactor logistic regression model, respectively. The model is interpreted using SHAP and nomogram. This provides an option for early prediction of CVE in patients with SA combined with CHD.

An Improved Diagnostic of the Mycobacterium tuberculosis Drug Resistance Status by Applying a Decision Tree to Probabilities Assigned by the CatBoost Multiclassifier of Matrix Metalloproteinases Biomarkers

In this work, we discuss an opportunity to use a set of the matrix metalloproteinases MMP-1, MMP-8, and MMP-9 and the tissue inhibitor TIMP, the concentrations of which can be easily obtained via a blood test from patients suffering from tuberculosis, as the biomarker for a fast diagnosis of the drug resistance status of Mycobacterium tuberculosis. The diagnostic approach is based on machine learning with the CatBoost system, which has been supplied with additional postprocessing. The latter refers not only to the simple probabilities of ML-predicted outcomes but also to the decision tree-like procedure, which takes into account the presence of strict zeros in the primary set of probabilities. It is demonstrated that this procedure significantly elevates the accuracy of distinguishing between sensitive, multi-, and extremely drug-resistant strains.

Machine Learning Models for Data-Driven Prediction of Diabetes by Lifestyle Type

The prevalence of diabetes has been increasing in recent years, and previous research has found that machine-learning models are good diabetes prediction tools. The purpose of this study was to compare the efficacy of five different machine-learning models for diabetes prediction using lifestyle data from the National Health and Nutrition Examination Survey (NHANES) database. The 1999-2020 NHANES database yielded data on 17,833 individuals data based on demographic characteristics and lifestyle-related variables. To screen training data for machine models, the Akaike Information Criterion (AIC) forward propagation algorithm was utilized. For predicting diabetes, five machine-learning models (CATBoost, XGBoost, Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM)) were developed. Model performance was evaluated using accuracy, sensitivity, specificity, precision, F1 score, and receiver operating characteristic (ROC) curve. Among the five machine-learning models, the dietary intake levels of energy, carbohydrate, and fat, contributed the most to the prediction of diabetes patients. In terms of model performance, CATBoost ranks higher than RF, LG, XGBoost, and SVM. The best-performing machine-learning model among the five is CATBoost, which achieves an accuracy of 82.1% and an AUC of 0.83. Machine-learning models based on NHANES data can assist medical institutions in identifying diabetes patients.