Using Machine Learning for the Risk Factors Classification of Glycemic Control in Type 2 Diabetes Mellitus.

Several risk factors are related to glycemic control in patients with type 2 diabetes mellitus (T2DM), including demographics, medical conditions, negative emotions, lipid profiles, and heart rate variability (HRV; to present cardiac autonomic activity). The interactions between these risk factors remain unclear. This study aimed to use machine learning methods of artificial intelligence to explore the relationships between various risk factors and glycemic control in T2DM patients. The study utilized a database from Lin et al. (2022) that included 647 T2DM patients. Regression tree analysis was conducted to identify the interactions among risk factors that contribute to glycated hemoglobin (HbA1c) values, and various machine learning methods were compared for their accuracy in classifying T2DM patients. The results of the regression tree analysis revealed that high depression scores may be a risk factor in one subgroup but not in others. When comparing different machine learning classification methods, the random forest algorithm emerged as the best-performing method with a small set of features. Specifically, the random forest algorithm achieved 84% accuracy, 95% area under the curve (AUC), 77% sensitivity, and 91% specificity. Using machine learning methods can provide significant value in accurately classifying patients with T2DM when considering depression as a risk factor.

Association of depression and parasympathetic activation with glycemic control in type 2 diabetes mellitus.

AIM: Patients with type 2 diabetes mellitus exhibited autonomic nervous system (ANS) dysfunction and comorbidities with depressive or anxiety symptoms were related to poor glycemic control. Heart rate variability (HRV) converted from electrocardiogram (ECG) has been used as the ANS index. The study aimed to explore the associations between depression, anxiety, HRV, and glycemic control in patients with type 2 diabetes mellitus. METHODS: The Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) questionnaires were used to assess depressive and anxiety symptoms in 647 patients with type 2 diabetes mellitus (mean age was 63 ± 10 years, 56 % males). The ECG raw signals were collected from a 5-min sitting and resting baseline and then transformed to HRV indices referring ANS activation. Blood glucose and lipid profiles including glycated hemoglobin (HbA1c), high-density lipoprotein (HDL), low-density lipoprotein (LDL), and triglyceride were obtained from the electronic medical records. RESULTS: Ninety-nine (15 %) participants had depressive symptoms and 59 (9 %) had anxiety symptoms. Depression and HbA1c were negatively correlated with parasympathetic activation. Depression and anxiety were positively correlated with sympathetic activation. After controlling for demographic data and lipid profiles, depression was a significant positive predictor for HbA1c levels; and HRV indices (lnLF and lnHF) were the significant negative predictors for HbA1c levels. Mediation effect analysis showed that depression was a mediator between parasympathetic activation and glycemic control. CONCLUSIONS: Lower parasympathetic activation and higher depressive symptoms may affect glycemic control in patients with type 2 diabetes mellitus. Intervention programs targeting to increase parasympathetic activities and reducing depression could be further tested for their effects on glycemic outcomes for potential clinical use.

[Sleep-improving mechanism of Chaiqin Ningshen Granules in insomnia rats: based on hippocampal metabonomics].

With the ultra high performance liquid chromatography-quadruple-electrostatic field orbitrap high resolution mass spectrometry(UHPLC-Q Exactive Orbitrap-MS)-based metabonomics technology, this study aims to analyze the effect of Chaiqin Ningshen Granules(CNG) on endogenous metabolites in insomnia rats of liver depression syndrome and explore the sleep-improving mechanism of this prescription. Parachlorophenylalanine(PCPA, ip) and chronic stimulation were combined to induce insomnia of liver depression pattern in rats, and the effect of CNG on the macroscopic signs, hemorheology, and neurotransmitters in the hippocampus of insomnia rats of liver depression syndrome was observed. After the administration, rat hippocampus was collected for liquid chromatography-mass spectrometry(LC-MS) analysis of the metabolomics. Principal component analysis(PCA), partial least squares discriminant analysis(PLS-DA), and orthogonal partial least squares discriminant analysis(OPLS-DA) were employed for analyzing the metabolites in rat hippocampus and screening potential biomarkers. MetPA was used to yield the related metabolic pathways and metabolic networks. The results show that the drugs can significantly improve the mental state, liver depression, and blood stasis of rats, significantly increase the content of 5-hydroxytryptamine(5-HT) and gamma aminobutyric acid(GABA) in hippocampus(except low-dose CNG), and significantly reduce the content of glucose(Glu)(except low-dose CNG). Among them, estazolam and high-dose CNG had better effect than others. Metabolomics analysis yielded 27 potential biomarkers related to insomnia. MetPA analysis showed 4 metabolic pathways of estazolam in intervening insomnia and 3 metabolic pathways of high-dose CNG in intervening insomnia, involving purine metabolism, glycerophospholipid metabolism, histidine metabolism, and caffeine metabolism. CNG can alleviate insomnia by regulating endogenous differential metabolites and further related metabolic pathways. The result lays a basis for further elucidating the mechanism of CNG in improving sleep.