Background: The machine learning algorithm (MLA) was implemented to establish an optimal model to predict the no reflow (NR) process and in-hospital death that occurred in ST-elevation myocardial infarction (STEMI) patients who underwent primary percutaneous coronary intervention (pPCI). Methods: The data were obtained retrospectively from 854 STEMI patients who underwent pPCI. MLA was applied to predict the potential NR phenomenon and confirm the in-hospital mortality. A random sampling method was used to split the data into the training (66.7%) and testing (33.3%) sets. The final results were an average of 10 repeated procedures. The area under the curve (AUC) and the associated 95% confidence intervals (CIs) of the receiver operator characteristic were measured. Results: A random forest algorithm (RAN) had optimal discrimination for the NR phenomenon with an AUC of 0.7891 (95% CI: 0.7093–0.8688) compared with 0.6437 (95% CI: 0.5506–0.7368) for the decision tree (CTREE), 0.7488 (95% CI: 0.6613–0.8363) for the support vector machine (SVM), and 0.681 (95% CI: 0.5767–0.7854) for the neural network algorithm (NNET). The optimal RAN AUC for in-hospital mortality was 0.9273 (95% CI: 0.8819–0.9728), for SVM, 0.8935 (95% CI: 0.826–0.9611); NNET, 0.7756 (95% CI: 0.6559–0.8952); and CTREE, 0.7885 (95% CI: 0.6738–0.9033). Conclusions: The MLA had a relatively higher performance when evaluating the NR risk and in-hospital mortality in patients with STEMI who underwent pPCI and could be utilized in clinical decision making.

Background: The Cox regression model is not sufficiently accurate to predict the survival prognosis of nasopharyngeal carcinoma (NPC) patients. It is impossible to calculate and rank the importance of impact factors due to the low predictive accuracy of the Cox regression model. So, we developed a system. Using the SEER (The Surveillance, Epidemiology, and End Results) database data on NPC patients, we proposed the use of random survival forest (RSF) and survival-support vector machine (SVM) from the machine learning methods to develop a survival prediction system specifically for NPC patients. This approach aimed to make up for the insufficiency of the Cox regression model. We also used the Cox regression model to validate the development of the nomogram and compared it with machine learning methods. Methods: A total of 1,683 NPC patients were extracted from the SEER database from January 2010 to December 2015. We used R language for modeling work, established the nomogram of survival prognosis of NPC patients by Cox regression model, ranked the correlation of influencing factors by RSF model VIMP (variable important) method, developed a survival prognosis system for NPC patients based on survival-SVM, and used C-index for model evaluation and performance comparison. Results: Although the Cox regression models can be developed to predict the prognosis of NPC patients, their accuracy was lower than that of machine learning methods. When we substituted the data for the Cox model, the C-index for the training set was only 0.740, and the C-index for the test set was 0.721. In contrast, the C index of the survival-SVM model was 0.785. The C-index of the RSF model was 0.729. The importance ranking of each variable could be obtained according to the VIMP method. Conclusions: The prediction results from the Cox model are not as good as those of the RSF method and survival-SVM based on the machine learning method. For the survival prognosis of NPC patients, the machine learning method can be considered for clinical application.

Object . The existing diagnostic paradigm for diabetic retinopathy (DR) greatly relies on subjective assessments by medical practitioners utilizing optical imaging, introducing susceptibility to individual interpretation. This work presents a novel system for the early detection and grading of DR, providing an automated alternative to the manual examination. Approach . First, we use advanced image preprocessing techniques, specifically contrast-limited adaptive histogram equalization and Gaussian filtering, with the goal of enhancing image quality and module learning capabilities. Second, a deep learning-based automatic detection system is developed. The system consists of a feature segmentation module, a deep learning feature extraction module, and an ensemble classification module. The feature segmentation module accomplishes vascular segmentation, the deep learning feature extraction module realizes the global feature and local feature extraction of retinopathy images, and the ensemble module performs the diagnosis and classification of DR for the extracted features. Lastly, nine performance evaluation metrics are applied to assess the quality of the model’s performance. Main results . Extensive experiments are conducted on four retinal image databases (APTOS 2019, Messidor, DDR, and EyePACS). The proposed method demonstrates promising performance in the binary and multi-classification tasks for DR, evaluated through nine indicators, including AUC and quadratic weighted Kappa score. The system shows the best performance in the comparison of three segmentation methods, two convolutional neural network architecture models, four Swin Transformer structures, and the latest literature methods. Significance . In contrast to existing methods, our system demonstrates superior performance across multiple indicators, enabling accurate screening of DR and providing valuable support to clinicians in the diagnostic process. Our automated approach minimizes the reliance on subjective assessments, contributing to more consistent and reliable DR evaluations.

Background: Type 2 diabetes mellitus (T2DM) is the most common type of diabetes, accounting for around 90% of all diabetes. Studies have found that dietary habits and biochemical metabolic changes are closely related to T2DM disease surveillance, but early surveillance tools are not specific and have lower accuracy. This paper aimed to provide a reliable artificial intelligence model with high accuracy for the clinical diagnosis of T2DM. Methods: A cross-sectional dataset comprising 8981 individuals from the First Affiliated Hospital of Guangxi Medical University was analyzed by a model fusion framework. The model includes four machine learning (ML) models, which used the stacking method. The ability to leverage the strengths of different algorithms to capture complex patterns in the data can effectively combine questionnaire data and blood test data to predict diabetes. Results: The experimental results show that the stacking model achieves significant prediction results in diabetes detection. Compared with the single machine learning algorithm, the stacking model has improved in the metrics of accuracy, recall, and F1-score. The test set accuracy is 0.90, and the precision, recall, F1-score, area under the curve, and average precision (AP) are 0.91, 0.90, 0.90, 0.90, and 0.85, respectively. Additionally, this study showed that HbA1c (P < 0.001,OR = 2.203), fasting blood glucose (FBG) (P < 0.001,OR = 1.586), Ph2BG (P < 0.001,OR = 1.190), age (P < 0.001,OR = 1.018), Han nationality (P < 0.001,OR = 1.484), and carbonate beverages (P = 0.001,OR = 1.347) were important predictors of T2DM. Conclusion: This study demonstrates that stacking models show great potential in diabetes detection, and by integrating multiple machine learning algorithms, stacking models can significantly improve the accuracy and stability of diabetes prediction and provide strong support for disease prevention, early diagnosis, and individualized treatment.

Research on the association of metal mixtures with glucose-insulin homeostasis is limited, and previous studies have typically focused on single metals. This study utilized data from 3110 adult subjects in the NHANES survey (2011–2018). Generalized linear models (GLM), logistic regression (LR), and restricted cubic splines (RCS) were employed to assess the associations of blood and urine metals with insulin resistance (IR) and glucose-insulin homeostasis. The Bayesian kernel machine regression (BKMR) and Bayesian weighted quantile sum (BWQS) models were further used to explore the independent and combined effects of metal exposures. In single-metal analyses, manganese (Mn) was positively correlated with insulin resistance (IR); cadmium(Cd), lead(Pb), mercury(Hg), and arsenic (As) were negatively correlated with the homeostasis model assessment of beta-cell function (HOMA-β); manganese and selenium (Se) were positively correlated with fasting plasma insulin (FPI); Se and cobalt (Co )were positively correlated with fasting plasma glucose (FPG); molybdenum (Mo) was positively correlated with HbA1c. In addition, both BWQS and BKMR models consistently showed that overall metal co-exposure had a positive effect on insulin resistance in the general population. Manganese was the most heavily weighted metal across all subgroups, with this association being more pronounced in males and individuals over 60 years of age. A negative association of metal mixtures with HOMA-β was observed in BWQS models. Furthermore, the analysis of BKMR models revealed possible interactions between insulin resistance and some components of metal mixtures in glucose homeostasis. The RCS model also identified nonlinear relationships between urinary Mo and HOMA-β, as well as between Co and both FPG and HbA1c. Our results suggest that metal mixtures may have adverse individual or combined effects on insulin resistance and glucose homeostasis in different population subgroups. These findings highlight the need for targeted interventions to mitigate the adverse effects of metal exposure on insulin-glucose homeostasis, which may provide new ideas for preventing and controlling the risk of type 2 diabetes due to metal exposure.