Predictive nomogram for coronary heart disease in patients with type 2 diabetes mellitus

Predicting coronary heart disease in Chinese diabetics using machine learning

Diabetes, a common chronic disease worldwide, can induce vascular complications, such as coronary heart disease (CHD), which is also one of the main causes of human death. It is of great significance to study the factors of diabetic patients complicated with CHD for understanding the occurrence of diabetes/CHD comorbidity. In this study, by analyzing the risk of CHD in more than 300,000 diabetes patients in southwest China, an artificial intelligence (AI) model was proposed to predict the risk of diabetes/CHD comorbidity. Firstly, we statistically analyzed the distribution of four types of features (basic demographic information, laboratory indicators, medical examination, and questionnaire) in comorbidities, and evaluated the predictive performance of three traditional machine learning methods (eXtreme Gradient Boosting, Random Forest, and Logistic regression). In addition, we have identified nine important features, including age, WHtR, BMI, stroke, smoking, chronic lung disease, drinking and MSP. Finally, the model produced an area under the receiver operating characteristic curve (AUC) of 0.701 on the test samples. These findings can provide personalized guidance for early CHD warning for diabetic populations.

Development and validation of a nomogram for predicting dysphagia in long-term care facility residents

BACKGROUND

Dysphagia is a common problem that can seriously affect the health of elderly residents in long-term care facilities. Early identification and targeted measures can significantly reduce the incidence of dysphagia.

AIM

This study aims to establish a nomogram to evaluate the risk of dysphagia for elderly residents in long-term care facilities.

METHODS

A total of 409 older adults were included in the development set, and 109 were included in the validation set. Least absolute shrinkage selection operator (LASSO) regression analysis was used to select the predictor variables, and logistic regression was used to establish the prediction model. The nomogram was constructed based on the results of logistic regression. The performance of the nomogram was evaluated by receiver operating characteristic (ROC) curve, calibration, and decision curve analysis (DCA). Internal validation was performed using tenfold cross-validation with 1000 iterations.

RESULTS

The predictive nomogram included the following variables: stroke, sputum suction history (within one year), Barthel Index (BI), nutrition status, and texture-modified food. The area under the curve (AUC) for the model was 0.800; the AUC value for the internal validation set was 0.791, and the AUC value for the external validation set was 0.824. The nomogram showed good calibration in both the development set and validation set. Decision curve analysis (DCA) demonstrated that the nomogram was clinically valuable.

DISCUSSION

This predictive nomogram provides a practical tool for predicting dysphagia. The variables included in this nomogram were easy to assess.

CONCLUSIONS

The nomogram may help long-term care facility staff identify older adults at high risk for dysphagia.

Development and External Validation of Nomogram to Identify Risk Factors for CHD in T2DM in the Population of Northwestern China

Purpose

Cardiovascular disease is the leading cause of mortality in patients with type 2 diabetes mellitus (T2DM). This study aimed to develop and validate a nomogram for predicting the risk factors for coronary heart disease (CHD) in T2DM in the population of northwestern China.

Patients and Methods

The records of 2357 T2DM patients who were treated in the First Affiliated Hospital of Xinjiang Medical University from July 2021 to July 2022 were reviewed. After some data (n =239) were excluded, 2118 participants were included in the study and randomly divided into a training set (n =1483) and a validation set (n = 635) at a ratio of 3:1. Univariate and stepwise regression analysis was performed to screen risk factors and develop predictive models. The results of logistic regression are presented through a nomogram. The C-index, receiver operating characteristic (ROC) curve, calibration plot, and decision curve analysis (DCA) were employed to verify the distinction, calibration, and clinical practicality of the model.

Results

The stepwise logistic regression analysis suggested that independent factors in patients with T2DM combined with CHD were age, gender, hypertension (HTN), glycated hemoglobin (HbA1c), high density lipoprotein cholesterol (HDL-C), low density lipoprotein cholesterol (LDL-C), and Uygur, which were associated with the occurrence of CHD. The nomogram demonstrated good discrimination with a C-index of 0.771 (95% CI, 0.741, 0.800) in the training set and 0.785 (95% CI, 0.743, 0.828) in the validation set. The area under curve (AUC) of the ROC curves were 0.771 (95% CI, 0.741, 0.800) and 0.785 (95% CI, 0.743, 0.828) in the training and validation sets, respectively. The nomogram was well-calibrated. The DCA revealed that the nomogram was clinically valuable.

Conclusion

A nomogram based on 7 clinical characteristics was developed to predict CHD in patients with T2DM.