This study sought to evaluate the performance of machine learning (ML) models and establish an explainable ML model with good prediction of 3-year all-cause mortality in patients with heart failure (HF) caused by coronary heart disease (CHD). We established six ML models using follow-up data to predict 3-year all-cause mortality. Through comprehensive evaluation, the best performing model was used to predict and stratify patients. The log-rank test was used to assess the difference between Kaplan-Meier curves. The association between ML risk and 3-year all-cause mortality was also assessed using multivariable Cox regression. Finally, an explainable approach based on ML and the SHapley Additive exPlanations (SHAP) method was deployed to calculate 3-year all-cause mortality risk and to generate individual explanations of the model's decisions. The best performing extreme gradient boosting (XGBoost) model was selected to predict and stratify patients. Subjects with a higher ML score had a high hazard of suffering events (hazard ratio [HR]: 10.351; P < 0.001), and this relationship persisted with a multivariable analysis (adjusted HR: 5.343; P < 0.001). Age, N-terminal pro-B-type natriuretic peptide, occupation, New York Heart Association classification, and nitrate drug use were important factors for both genders. The ML-based risk stratification tool was able to accurately assess and stratify the risk of 3-year all-cause mortality in patients with HF caused by CHD. ML combined with SHAP could provide an explicit explanation of individualized risk prediction and give physicians an intuitive understanding of the influence of key features in the model.

Purpose: This study sought to develop models with good identification for adverse outcomes in patients with heart failure (HF) and find strong factors that affect prognosis. Patients and Methods: A total of 5004 qualifying cases were selected, among which 498 cases had adverse outcomes and 4506 cases were discharged after improvement. The study subjects were hospitalized patients diagnosed with HF from a regional cardiovascular hospital and the cardiology department of a medical university hospital in Shanxi Province of China between January 2014 and June 2019. Synthesizing minority oversampling technology combined with edited nearest neighbors (SMOTE+ENN) was used to pre-process unbalanced data. Traditional logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost) were used to build risk identification models, and each model was repeated 100 times. Model discrimination and calibration were estimated using F1-score, the area under the receiver-operating characteristic curve (AUROC), and Brier score. The best performing of the five models was used to identify the risk of adverse outcomes and evaluate the influencing factors. Results: The SME-XGBoost was the best performing model with means of F1-score (0.3673, 95% confidence interval [CI]: 0.3633– 0.3712), AUC (0.8010, CI: 0.7974– 0.8046), and Brier score (0.1769, CI: 0.1748– 0.1789). Age, N-terminal pronatriuretic peptide, pulmonary disease, etc. were the most significant factors of adverse outcomes in patients with HF. Conclusion: The combination of SMOTE+ENN and advanced machine learning methods effectively improved the discrimination efficacy of adverse outcomes in HF patients, accurately stratified patients at risk of adverse outcomes, and found the top factors of adverse outcomes. These models and factors emphasize the importance of health status data in determining adverse outcomes in patients with HF.

Congenital heart defects (CHD) is one of the most common birth defects in China. Many studies have examined risk factors for CHD, but their predictive abilities have not been evaluated. In particular, few studies have attempted to predict risks of CHD from, necessarily unbalanced, population-based cross-sectional data. Therefore, we developed and validated machine learning models for predicting, before and during pregnancy, women’s risks of bearing children with CHD. We compared the results of these models in a large-scale, comprehensive population-based retrospective cross-sectional epidemiological survey of birth defects in six counties in Shanxi Province, China, covering 2006 to 2008. This contained 78 cases of CHD among 33831 live births. We constructed nine synthetic variables to use in the models: maternal age, annual per capita income, family history, maternal history of illness, nutrition and folic acid deficiency, maternal illness in pregnancy, medication use in pregnancy, environmental risk factors in pregnancy, and unhealthy maternal lifestyle in pregnancy. The machine learning algorithms Weighted Support Vector Machine (WSVM) and Weighted Random Forest (WRF) were trained on, and a logistic regression (Logit) was fitted to, two-thirds of the data. Their predictive abilities were then tested in the remaining data. True positive rate (TPR), true negative rate (TNR), accuracy (ACC), area under the curves (AUC), G-means, and Weighted accuracy (WTacc) were used to compare the classification performance of the models. Median values, from repeating the data partitioning 1000 times, were used in all comparisons. The TPR and TNR of the three classifiers were above 0.65 and 0.93, respectively, better than any reported in the literature. TPR, wtACC, AUC and G were highest for WSVM, showing that it performed best. All three models are precise enough to identify groups at high risk of CHD. They should all be considered for future investigations of other birth defects and diseases.

Invasive coronary angiography imposes risks and high medical costs. Therefore, accurate, reliable, non-invasive, and cost-effective methods for diagnosing coronary stenosis are required. We designed a machine learning-based risk-prediction system as an accurate, noninvasive, and cost-effective alternative method for evaluating suspected coronary heart disease (CHD) patients. Electronic medical record data were collected from suspected CHD patients undergoing coronary angiography between May 1, 2017, and December 31, 2019. Multi-Class XGBoost, LightGBM, Random Forest, NGBoost, logistic models and MLP were constructed to identify patients with normal coronary arteries (class 0: no coronary artery stenosis), minimum coronary artery stenosis (class 1: 0 < stenosis <50%), and CHD (class 2: stenosis ≥50%). Model stability was verified externally. A risk-assessment and management system was established for patient-specific intervention guidance. Of 1577 suspected CHD patients, 81 (5.14%) had normal coronary arteries. The XGBoost model demonstrated the best overall classification performance (micro-average receiver operating characteristic [ROC] curve: 0.92, macro-average ROC curve: 0.89, class 0 ROC curve: 0.88, class 1 ROC curve: 0.90, class 2 ROC curve: 0.89), with good external verification. In class-specific classification, the XGBoost model yielded F1 values of 0.636, 0.850, and 0.858, for Classes 0, 1, and 2, respectively. The visualization system allowed disease diagnosis and probability estimation, and identified the intervention focus for individual patients. Thus, the system distinguished coronary artery stenosis well in suspected CHD patients. Personalized probability curves provide individualized intervention guidance. This may reduce the number of invasive inspections in negative patients, while facilitating decision-making regarding appropriate medical intervention, improving patient prognosis.

Hepatic encephalopathy (HE) is among the most common complications of cirrhosis. Data for cirrhosis with HE is typically unbalanced. Traditional statistical methods and machine learning algorithms thus cannot identify a few classes. In this paper, we use machine learning algorithms to construct a risk prediction model for liver cirrhosis complicated by HE to improve the efficiency of its prediction. We collected medical data from 1,256 patients with cirrhosis and performed preprocessing to extract 81 features from these irregular data. To predict HE in cirrhotic patients, we compared several classification methods: logistic regression, weighted random forest (WRF), SVM, and weighted SVM (WSVM). We also used an additional 722 patients with cirrhosis for external validation of the model. The WRF, WSVM, and logistic regression models exhibited better recognition ability for patients with HE than traditional machine learning models (sensitivity> 0.70), but their ability to identify patients with uncomplicated HE was slightly lower (specificity approximately 85%). The comprehensive evaluation index of the traditional model was higher than those of other models (G-means> 0.80 and F-measure> 0.40). For the WRF, the G-means (0.82), F-measure (0.46), and AUC (0.82) were superior to those of the logistic regression and WSVM models, which means that it can better predict the incidence of HE in patients. The WRF model is more suitable for the classification of unbalanced medical data and can be used to construct a risk prediction and evaluation system for liver cirrhosis complicated with HE. The probabilistic prediction models of WRF can help clinicians identify high-risk patients with HE.

Objective: Preeclampsia affects 2–8% of women and doubles the risk of cardiovascular disease in women after preeclampsia. This study aimed to develop a model based on machine learning to predict postpartum cardiovascular risk in preeclamptic women.Methods: Collecting demographic characteristics and clinical serum markers associated with preeclampsia during pregnancy of 907 preeclamptic women retrospectively, we predicted the cardiovascular risk (ischemic heart disease, ischemic cerebrovascular disease, peripheral vascular disease, chronic kidney disease, metabolic system disease or arterial hypertension). The study samples were divided into training sets and test sets randomly in the ratio of 8:2. The prediction model was developed by 5 different machine learning algorithms, including Random Forest. 10-fold cross-validation was performed on the training set, and the performance of the model was evaluated on the test set.Results: Cardiovascular disease risk occurred in 186 (20.5%) of these women. By weighing area under the curve (AUC), the Random Forest algorithm presented the best performance (AUC = 0.711[95%CI: 0.697–0.726]) and was adopted in the feature selection and the establishment of the prediction model. The most important variables in Random Forest algorithm included the systolic blood pressure, Urea nitrogen, neutrophil count, glucose, and D-Dimer. Random Forest algorithm was well calibrated (Brier score = 0.133) in the test group, and obtained the highest net benefit in the decision curve analysis.Conclusion: Based on the general situation of patients and clinical variables, a new machine learning algorithm was developed and verified for the individualized prediction of cardiovascular risk in post-preeclamptic women.