Objective To construct, validate and evaluate a nomogram prediction model based on triglyceride-glucose index for predicting the risk of type 2 diabetes mellitus (T2DM) in patients with obstructive sleep apnea (OSA). Methods A total of 414 patients diagnosed with OSA who were hospitalized in the Second Affiliated Hospital of Kunming Medical University from July 2013 to July 2023 were retrospectively analyzed. They were randomly divided into training set (n=289) and validation set (n=125) at a ratio of 7:3 using R software. In the training set, univariate logistic regression, best subsets regression (BSR) and multivariate Logistic regression were used to determine the independent predictors of OSA combined with T2DM and construct a nomogram. The area under the receiver operating characteristic curve (AUC), calibration curve, Hosmer-Lemeshow goodness of fit test, decision curve analysis (DCA) and clinical impact curve (CIC) were used to evaluate the discrimination, calibration and clinical applicability of the nomogram prediction model. Finally, the internal validation of the nomogram prediction model was carried out on the validation set. Results In the training set, the results of univariate logistic regression, BSR and multivariate logistic regression analysis showed that hypertension (OR=2.413, 95%CI 1.276-4.563, P=0.007), apnea hypopnea index (OR=1.034, 95%CI 1.014-1.053, P=0.001), triglyceride-glucose index( OR=12.065, 95%CI 5.735-25.379, P<0.001), triglyceride/high density lipoprotein cholesterol (OR=0.736, 95%CI 0.634-0.855, P<0.001) were independent predictors of T2DM in OSA patients. A nomogram prediction model was constructed based on the above four predictors. In the training set and validation set, the AUC, sensitivity, and specificity of the nomogram prediction model for predicting the risk of T2DM in OSA patients were 0.820 (95%CI 0.771-0.869), 75.7%, 75.9% and 0.778 (95%CI 0.696-0.861), 74.5%, 73.0%, respectively, indicating that the nomogram had good discrimination. The calibration curve showed that the nomogram had a good calibration for predicting T2DM in OSA patients. DCA and CIC also showed that the nomogram prediction model had certain clinical utility. Conclusions A simple, fast and effective nomogram prediction model with good discrimination, calibration and clinical applicability was successfully constructed, validated and evaluated. It can be used to predict the risk of T2DM in OSA patients and help clinicians to identify patients with high risk of T2DM in OSA patients.
ObjectiveThe aim of this study was to investigate the value of Artificial Neural Networks (ANNs) in predicting the occurrence of Venous Thromboembolism (VTE) in patients with Obstructive Sleep Apnea (OSA), and to compare it with traditional Logistic regression models to assess its predictive efficacy, providing theoretical basis for the prediction of VTE risk in OSA patients. MethodsA retrospective analysis was conducted on patients diagnosed with OSA and hospitalized in the Department of Respiratory and Critical Care Medicine, Second Affiliated Hospital of Kunming Medical University, from January 2018 to August 2023. Patients were divided into OSA combined with VTE group (n=128) and pure OSA control group (n=680). The dataset was randomly divided into a training set (n=646) and an independent validation set (n=162). The Synthetic Minority Oversampling Technique (SMOTE) was employed to address the issue of data imbalance. Artificial Neural Networks and Logistic regression models were then built on training sets with and without SMOTE. Finally, the performance of each model was evaluated using accuracy, sensitivity, specificity, Youden's index, and Area Under the Receiver Operating Characteristic Curve (AUC). Results When oversampling was conducted using SMOTE on the training set, both the Artificial Neural Network and Logistic regression models showed improved AUC. The Artificial Neural Network model with SMOTE performed the best with an AUC value of 0.935 (95%CI: 0.898–0.961), achieving an accuracy of 90.15%, specificity of 87.32%, sensitivity of 93.44%, and Youden’s index of 0.808 at the optimal cutoff point. The Logistic regression model with SMOTE yielded an AUC value of 0.817 (95%CI: 0.765–0.861), with an accuracy of 77.27%, specificity of 83.80%, sensitivity of 69.67%, and Youden's index of 0.535. The difference in AUC between the Artificial Neural Network model and Logistic regression model was statistically significant after employing SMOTE (P<0.05). Conclusions The Artificial Neural Network model demonstrates high effectiveness in predicting VTE formation in OSA patients, particularly with the further improvement in predictive performance when utilizing SMOTE oversampling technique, rendering it more accurate and stable compared to the traditional Logistic regression model.
Objective To investigate levels of 8-isoprostane in serum of patients with bronchial asthma. Methods Eighteen patients diagnosed with acute exacerbation of asthma were enrolled as the experimental group from Department of Respiratory Medicine from February 2009 to August 2009. After treatment all the patients reached remission. Twenty healthy workers from Department of Respiratory Medicine were enrolled as the control group in August 2009. The levels of 8-isoprostane in serum of all subjects were measured, and their FEV1% pred was also evaluated. Results The levels of 8-isoprostane in serum were significantly higher in patients with acute exacerbation of asthma compared with those in remission stage and the healthy control group [ ( 157. 46 ±46. 99) pg/mL vs. ( 43. 52 ±13. 62) pg/mL and( 15. 23 ±1. 96) pg/mL, P lt;0. 01] . Meanwhile the levels of 8-isoprostane in serum of patients with asthma in remission stage were significantly higher compared with the healthy control group ( P lt;0. 05) . The levels of 8-isoprostane in serum were negatively correlated with FEV1% pred in the asthma group( r = - 0. 533,P lt;0. 05) . Conclusions 8-isoprostane as amarker of oxidative stress response involves in the pathogenesis of asthma. Monitoring 8-isoprostane levels in serum may reflect the state of oxidative stress, and may be useful for severity judgment and follow-up of treatment effectiveness in patients with asthma.
Objective To invesitgate the relationship between 8-isoprostane ( 8-iso-PG) level in exhaled breath condensates ( EBCs) and severity of asthma and explore the role of 8-iso-PG in asthma evaluation and monitoring. Methods Fifty-nine patients with asthma were enrolled. In which 15 cases were acute exacerbation, 13 cases were mild intermittent, 15 cases were mild persistent, and 16 cases were moderate-to-severe persistent. Thirteen healthy volunteers were recruited as control. EBCs were collected using EcoScreen system. The 8-iso-PG levels in EBCs were measured by a specific enzyme immunoassay.The patients with mild intermittent asthma were treated with inhaled corticosteroid ( ICS) for one month and their EBCs were recollected for 8-iso-PG measurement. Results Exhaled 8-iso-PG levels were obviously increased in the patients with acute asthma compared with those chronic asthmatics [ ( 47. 2 ±6. 8) pg/mL vs ( 24. 5 ±12. 0) pg/mL, P lt; 0. 01] . In the chronic persistent asthma, the levels were significantly higher in patients with mild persistent and moderate-to-severe asthma [ ( 17. 9 ±1. 2) pg/mL and ( 39. 7 ±4. 0) pg/mL,P lt; 0. 01] . While 8-iso-PG level did not differ significantly in intermittent asthma [ ( 13. 5 ±1. 1) pg/mL]compared with the control subjects ( P gt; 0. 05 ) . After one-month ICS treatment the 8-iso-PG level in the patients with mild intermittent asthma did not change significantly although the ACT score improved. Conclusions 8-iso-PG levels in EBC are associated with the severity of asthma, implicating 8-iso-PG may be useful in monitoring airway oxidative stress in asthma. ICS treatment is incapable of decreasing the 8-iso-PG, suggesting the ICS has minor impact on oxidative stress.