Objective To develop and compare the predictive performance of five machine learning models for adverse postoperative outcomes in cardiac surgery patients, and to identify key decision factors through SHapley Additive exPlanations (SHAP) interpretability analysis. Methods A retrospective collection of perioperative data (including demographic information, preoperative, intraoperative, and postoperative indicators) with 88 variables was conducted from adult cardiac surgery patients at the First Affiliated Hospital of Xinjiang Medical University in 2023. Adverse postoperative outcomes were defined as the occurrence of acute kidney injury and/or in-hospital mortality during the postoperative hospitalization period following cardiac surgery. Patients were divided into an adverse outcome group and a favorable outcome group based on the presence of adverse postoperative outcomes. After screening feature variables using the least absolute shrinkage and selection operator (LASSO) regression method, five machine learning models were constructed: eXtreme gradient boosting (XGBoost), random forest (RF), gradient boosting machine (GBM), light gradient boosting machine (LightGBM), and generalized linear model (GLM). The dataset was randomly divided into a training set and a test set at a 7 : 3 ratio using stratified sampling, with postoperative outcome as the stratification factor. Model performance was evaluated using receiver operating characteristic curves, decision curve analysis, and F1 Score. The SHAP method was applied to analyze feature contribution. Results A total of 639 patients were included, comprising 395 males and 244 females, with a median age of 62 (55, 69) years. The adverse outcome group consisted of 191 patients, while the favorable outcome group included 448 patients, resulting in an adverse postoperative outcome incidence of 29.9%. Univariate analysis showed no significant differences between the two groups for any variables (P>0.05). Using LASSO regression, 16 feature variables were selected (including cardiopulmonary bypass support time, blood glucose on postoperative day 3, creatine kinase-MB isoenzyme, systemic inflammatory response index, etc.), and five machine learning models (GLM, RF, GBM, LightGBM, XGBoost) were constructed. Evaluation results demonstrated that the XGBoost model exhibited the best predictive performance on both the training set (n=447) and test set (n=192), with area under the curve values of 0.761 [95%CI (0.719, 0.800) ] and 0.759 [95%CI (0.692, 0.818) ], respectively. It also significantly outperformed other models in positive predictive value, and balanced accuracy in the test set. Decision curve analysis further confirmed its clinical utility across various risk thresholds. SHAP analysis indicated that variables such as cardiopulmonary bypass support time, blood glucose on postoperative day 3, creatine kinase-MB isoenzyme, and inflammatory markers (SIRI, NLR, CAR) had high contributions to the prediction. Conclusion The XGBoost model effectively predicts adverse postoperative outcomes in cardiac surgery patients. Clinically, attention should be focused on cardiopulmonary bypass support time, postoperative blood glucose control, and monitoring of inflammatory levels to improve patient prognosis.
Objective To construct the prediction model of hospitalization expenses for ischemic heart disease, reveal the key factors affecting hospitalization expenses, and analyze the interaction between variables. Methods Patients from Sichuan medical insurance comprehensive service platform from January 2020 to December 2021 were extracted. The training set and test set were divided according to the ratio of 7∶3. Six machine learning models were constructed and trained by ten-fold cross validation, and was explained by SHAP theory. Results XGBoost model had the best performance among these models, with a R2 of 0.60, RMSE of 9 969.71 yuan, and MAE of 5 242.90 yuan in the test set. SHAP results showed that the five variables with the greatest impact on hospitalization expenses were surgery, length of stay, hospital grade, disease type and DRG. Hospitalization costs were higher when grade 3 or 4 procedures were performed, the length of stay was prolonged, the hospitalization was in a tertiary hospital, and payments were made for acute myocardial infarction and non-DRG. With the prolongation of hospital stay, the hospitalization expenses increased faster when the patient had grade 4 surgery and was in a tertiary hospital. In addition, DRG payment will reduce the length of hospital stay and the hospitalization expenses of patients with different disease types. Conclusion The interpretable XGBoost model constructed in this study has a good predictive performance for the hospitalization expenses of patients with ischemic heart disease. Combined with SHAP theory, it can effectively identify the key factors affecting the hospitalization expenses and analyze their interactions.
ObjectiveTo investigate the association between the stress-induced hyperglycemia ratio (SHR) and all-cause, cardiovascular, and diabetes-related mortality in patients with advanced cardiovascular-kidney-metabolic (CKM) syndrome, and to evaluate the value of SHR as an independent prognostic marker. MethodsThis retrospective cohort study used data from the 1999–2018 U.S. National Health and Nutrition Examination Survey (NHANES). A total of 2 135 patients with advanced CKM (stages 3 and 4) were included. Kaplan-Meier analysis and multivariable Cox regression models were applied to assess the relationship between SHR and mortality outcomes. Restricted cubic spline (RCS) analysis was employed to explore potential non-linear associations. Subgroup analyses were conducted to identify possible effect modifiers. ResultsOver a mean follow-up of 248 months, 674 all-cause, 198 cardiovascular, and 31 diabetes-related deaths occurred. Elevated SHR was significantly associated with diabetes-related mortality (HR=3.48, P<0.001) in a dose-response manner. SHR exhibited a U-shaped relationship with both all-cause and cardiovascular mortality (non-linearity P<0.001), indicating increased risk at both low and high SHR levels. Subgroup analyses revealed that sex, BMI, and hyperlipidemia significantly modified the association between SHR and diabetes-related death. ConclusionSHR is an independent predictor of mortality risk in patients with advanced CKM syndrome, particularly for diabetes-related death. These findings support the integration of SHR into risk stratification of high-risk CKM populations and provide a basis for metabolic stress-targeted interventions.
Objective To evaluate the histocompatibil ity of porous hydroxyapatite (HAP) coating NiTi shape memory alloy and to provide a theoretical basis for its cl inical appl ication in bone defect repair. Methods Twenty-four Chinchilla rabbits weighing 2.0-2.5 kg were randomized into experimental group and control group (n=12). HAP coating NiTi shape memory alloy was implanted into the distal part of left femur of 12 rabbits in the experimental group, while holes without alloy implantation were performed on the control group. At 7, 14, 28 and 56 days after implantation, the animals werekilled (3 rabbits in each group at a time). Gross observation, histology observation, BMP-2 immunohistochemistry observation and image grey scale analysis were performed. And the histology observation was evaluated by GB/T16886.6-1997 in terms of inflammation, capsule wall of fibrous tissue, materials degradation and the response of peripheral tissue. Results All of the animals survived until being killed. The implants reached a peak embedded in bone tissue wholly, without loosening and bone absorption. The inflammatory cell infiltration and fibrous hyperplasia were at 7 days after implantation, with the formation of cyst wall of fibrous tissue and the implant wrapped by the cyst wall. The response of connective tissue proliferation was still obvious in partial samples of experimental group at 56 days after implantation, which was wrose than the control group but consistent with the in vivo implantation standard of GB/T16886.6-1997. Immunohistochemistry observation displayed the endogenous BMP-2 were in the cytoplasm of MSCs and osteoblast. The result of image analysis showed the expression of BMP-2 were staged in line with the repair of bone defect, two groups witnessed the peak expression of the BMP-2 at 14 days after implantation. There wereno significant differences among different time points in the staining gray scale of BMP-2 (P gt; 0.05). Conclusion HAP coating NiTi shape memory alloy, as a biomedical material, has excellent histocompatibility with bone.
ObjectiveTo develop and validate a machine learning model based on preoperative clinical characteristics, laboratory indices, and radiological features for the non-invasive prediction of spread through air spaces (STAS) in patients with early-stage lung adenocarcinoma. Methods Preoperative data from patients with early-stage lung adenocarcinoma who underwent surgical resection at Northern Jiangsu People's Hospital between January 2020 and August 2025 were retrospectively collected. The data included clinical characteristics, laboratory indices, and radiological features. Patients were divided into a STAS-positive and a STAS-negative group based on postoperative pathological findings. The dataset was randomly split into a training set and a testing set at a 7 : 3 ratio. Feature variables were selected using the maximum relevance and minimum redundancy (mRMR) algorithm and the least absolute shrinkage and selection operator (LASSO) regression. Five machine learning models were constructed: logistic regression (LR), random forest (RF), support vector machine (SVM), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). The shapley additive explanations (SHAP) method was employed to interpret the optimal prediction model. Results A total of 377 patients were included, comprising 177 (46.9%) males and 200 females (53.1%), with a mean age of (63.31±9.73) years. There were 261 patients in the training set and 116 patients in the testing set. In the training set, statistically significant differences were observed between the STAS-positive group (n=130) and STAS-negative group (n=131) across multiple features, including age, sex, neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), clinical T stage, and maximum solid component diameter (P<0.05). A final set of 10 feature variables was selected by combining mRMR and LASSO regression, and five machine learning models (LR, RF, SVM, LightGBM, XGBoost) were developed. The XGBoost model demonstrated superior predictive performance in both the training and testing sets, achieving AUCs of 0.947 [95%CI (0.920, 0.975)] and 0.943 [95%CI (0.894, 0.993)], respectively, and achieved the optimal level in the testing set. DCA indicated that the XGBoost model provided a high net clinical benefit across a wide range of threshold probabilities. SHAP analysis revealed that the vessel convergence sign, clinical T stage, age, consolidation-to-tumor ratio (CTR), and MLR were the features with the highest contributions to STAS prediction. Conclusion The XGBoost model effectively predicts preoperative STAS status in early-stage lung adenocarcinoma, exhibiting excellent discriminative performance and good clinical interpretability. Key predictors such as the vessel convergence sign, clinical T stage, age and CTR provide a crucial reference for preoperative risk assessment and the individualized selection of surgical strategies, ultimately benefiting patients.
Objective To develop a machine learning (ML) model to predict the risk of death in intensive care unit (ICU) patients with chronic obstructive pulmonary disease (COPD), explain the factors related to the risk of death in COPD patients, and solve the "black box" problem of ML model. Methods A total of 8088 patients with severe COPD were selected from the eICU Collaborative Research Database (eICU-CRD). Data within the initial 24 hours of each ICU stay were extracted and randomly divided, with 70% for model training and 30% for model validation. The LASSO regression was deployed for predictor variable selection to avoid overfitting. Five ML models were employed to predict in-hospital mortality. The prediction performance of the ML models was compared with alternative models using the area under curve (AUC), while SHAP (SHapley Additive exPlanations) method was used to explain this random forest (RF) model. Results The RF model performed best among the APACHE IVa scoring system and five ML models with the AUC of 0.830 (95%CI 0.806 - 0.855). The SHAP method detects the top 10 predictors according to the importance ranking and the minimum of non-invasive systolic blood pressure was recognized as the most significant predictor variable. Conclusion Leveraging ML model to capture risk factors and using the SHAP method to interpret the prediction outcome can predict the risk of death of patients early, which helps clinicians make accurate treatment plans and allocate medical resources rationally.
This study aimed to provide suggestions for future researchers to select and optimize sham acupuncture reporting guidelines in acupuncture clinical trials. Through qualitative analysis, we compared the basic information and concrete contents between Acupuncture Controls gUideline for Reporting humAn Trials and Experiments (ACURATE) and SHam Acupuncture REporting guidelines in clinical trials (SHARE) developed by researchers from China and Korea. In addition, the similarities and differences of the two guidelines were illustrated through a specific case. We found that the two guidelines had their own characteristics and emphasis in content, but both emphasized the reports of detailed information and background factors of sham acupuncture compared with the previous STRICTA and TIDieR-Placebo checklist. In terms of item division, we found that the ACURATE split the same topic into several items to emphasize the importance of each item content. SHARE emphasized the comprehensive reports of sham acupuncture by combining several items into a single item. In terms of item content, ACURATE also focused on combination therapy, the information regarding sham acupuncture provided to participants, and any differences in treatment settings between versus/sham acupuncture, which had some referential meaning for setting sham acupuncture control. SHARE also focused on sham acupuncture detailed information, practitioner, and modifications, etc. Case analysis showed that there were some "not reported" or "partially reported" items in both guidelines. Therefore, it is suggested that researchers can use the above two guidelines to complement and learn from each other to report sham acupuncture. In addition, it is necessary for researchers to verify the operability and practicability of the above two guidelines, and provide suggestions for optimizing and updating them in the future.
ObjectiveTo explore the predictive value of four risk scoring systems for cardiovascular complications during pregnancy in patients with congenital heart disease (CHD). MethodsComputer searches were conducted in PubMed, EMbase, The Cochrane Library, Web of Science, China National Knowledge Infrastructure (CNKI), Wanfang Data, VIP, and China Biology Medicine disc (CBM). Relevant studies on risk scoring systems for cardiovascular complications during pregnancy in CHD patients at home and abroad were comprehensively collected. The retrieval period was from the establishment of the databases to January 1, 2025, and the retrieval was updated on March 26, 2025. After two reviewers independently screened the literature and extracted the data, the quality assessment was carried out, and meta-analysis was performed using MedCalc software. ResultsA total of 11 studies were included, with a total of 4 987 patients. The incidence of cardiovascular complications during pregnancy in CHD patients ranged from 6.72% to 28.84%. The QUADAS-2 scoring tool results showed that 2 studies had unclear risk of bias, and 9 studies were determined to have a high risk of bias. The results of the meta-analysis showed that the CARPREGⅠ score [AUC=0.709, 95%CI (0.672, 0.745), P<0.001], CARPREGⅡ score [AUC=0.757, 95%CI (0.720, 0.794), P<0.001], ZAHARA score [AUC=0.732, 95%CI (0.674, 0.790), P<0.001], and mWHO classification system [AUC=0.681, 95%CI (0.617, 0.745), P<0.001] could independently predict cardiovascular complications during pregnancy in CHD patients. ConclusionThe existing evidence indicates that all four scoring systems can be used to predict cardiovascular complications during pregnancy in CHD patients. Although the CARPREGⅡ score has the highest accuracy, the number of included studies is small. It is recommended to give priority to using the ZAHARA score for risk stratification and pregnancy management of women with CHD before pregnancy. In view of the limitations of the quality of the included studies, this study needs to be further confirmed by high-quality studies.
ObjectiveTo evaluate the use of machine learning algorithms for the prediction and characterization of cardiac thrombosis in patients with valvular heart disease and atrial fibrillation. MethodsThis article collected data of patients with valvular disease and atrial fibrillation from West China Hospital of Sichuan University and its branches from 2016 to 2021. From a total of 2 515 patients who underwent valve surgery, 886 patients with valvular disease and atrial fibrillation were included in the study, including 545 (61.5%) males and 341 (38.5%) females, with a mean age of 55.62±9.26 years, and 192 patients had intraoperatively confirmed cardiac thrombosis. We used five supervised machine learning algorithms to predict thrombosis in patients. Based on the clinical data of the patients (33 features after feature screening), the 10-fold nested cross-validation method was used to evaluate the predictive effect of the model through evaluation indicators such as area under the curve, F1 score and Matthews correlation coefficient. Finally, the SHAP interpretation method was used to interpret the model, and the characteristics of the model were analyzed using a patient as an example. ResultsThe final experiment showed that the random forest classifier had the best comprehensive evaluation indicators, the area under the receiver operating characteristic curve was 0.748±0.043, and the accuracy rate reached 79.2%. Interpretation and analysis of the model showed that factors such as stroke volume, peak mitral E-wave velocity and tricuspid pressure gradient were important factors influencing the prediction. ConclusionThe random forest model achieves the best predictive performance and is expected to be used by clinicians as an aided decision-making tool for screening high-embolic risk patients with valvular atrial fibrillation.
ObjectiveTo analyze the prevalence, regional differences, and influencing factors of depression in the middle-aged and elderly population aged 45 years and above in China. MethodsData were obtained from the latest survey data of the China Health and Retirement Longitudinal Study (CHARLS) in 2020, and the CES-D-10 scale was used to assess depression among respondents, and χ2 test and binary logistic regression were used to screen for the influencing factors of depression. ResultsA total of 10 583 valid samples were included, with 47.7% males and 52.3% females, and the mean age was (65.3±8.0) years. The average CES-D-10 scale score of the study population was (9.11±6.53), and the prevalence rate of depression was 40.5% (95%CI 39.6% to 41.5%), with a significantly higher prevalence rate of depression in the Midwestern population than the Eastern population. The gender, age, living with a partner, education, region, urban/rural, duration of sleep, internet access, alcohol consumption, number of chronic diseases, and the presence of ADL and IADL disorders are the influencing factors of depression in middle-aged and elderly populations. ConclusionThe prevalence of depression in the middle-aged and elderly population in China is high, but there are significant differences in the prevalence rates of populations with different characteristics, and the high-risk groups should be emphasized when improving the mental health of the middle-aged and elderly population.