Phenotyping normal kidney function in elderly patients with type 2 diabetes: a cross-sectional multicentre study

Analysis for warning factors of type 2 diabetes mellitus complications with Markov blanket based on a Bayesian network model

BACKGROUND AND OBJECTIVE

Type 2 diabetes mellitus (T2DM) complications seriously affect the quality of life and could not be cured completely. Actions should be taken for prevention and self-management. Analysis of warning factors is beneficial for patients, on which some previous studies focused. They generally used the professional medical test factors or complete factors to predict and prevent, but it was inconvenient and impractical for patients to self-manage. With this in mind, this study built a Bayesian network (BN) model, from the perspective of diabetic patients' self-management and prevention, to predict six complications of T2DM using the selected warning factors which patients could have access from medical examination. Furthermore, the model was analyzed to explore the relationships between physiological variables and T2DM complications, as well as the complications themselves. The model aims to help patients with T2DM self-manage and prevent themselves from complications.

METHODS

The dataset was collected from a well-known data center called the National Health Clinical Center between 1st January 2009 and 31st December 2009. After preprocess and impute the data, a BN model merging expert knowledge was built with Bootstrap and Tabu search algorithm. Markov Blanket (MB) was used to select the warning factors and predict T2DM complications. Moreover, a Bayesian network without prior information (BN-wopi) model learned using 10-fold cross-validation both in structure and in parameters was added to compare with other classifiers learned using 10-fold cross-validation fairly. The warning factors were selected according the structure learned in each fold and were used to predict. Finally, the performance of two BN models using warning features were compared with Naïve Bayes model, Random Forest model, and C5.0 Decision Tree model, which used all features to predict. Besides, the validation parameters of the proposed model were also compared with those in existing studies using some other variables in clinical data or biomedical data to predict T2DM complications.

RESULTS

Experimental results indicated that the BN models using warning factors performed statistically better than their counterparts using all other variables in predicting T2DM complications. In addition, the proposed BN model were effective and significant in predicting diabetic nephropathy (DN) (AUC: 0.831), diabetic foot (DF) (AUC: 0.905), diabetic macrovascular complications (DMV) (AUC: 0.753) and diabetic ketoacidosis (DK) (AUC: 0.877) with the selected warning factors compared with other experiments.

CONCLUSIONS

The warning factors of DN, DF, DMV, and DK selected by MB in this research might be able to help predict certain T2DM complications effectively, and the proposed BN model might be used as a general tool for prevention, monitoring, and self-management.

Predictors of early discontinuation of dapagliflozin versus other glucose-lowering medications: a retrospective multicenter real-world study

BACKGROUND AND AIMS

In routine clinical practice, early discontinuation of newly initiated glucose-lowering medications (GLM) is relatively common. We herein evaluated if the clinical characteristics associated with early discontinuation of dapagliflozin were different from those associated with early discontinuation of other GLM.

METHODS

The DARWIN-T2D was a multicenter retrospective study conducted at diabetes specialist outpatient clinics in Italy. We included 2484 patients who were initiated on dapagliflozin in 2015-2016 and 14,801 patients who were initiated on other GLM (DPP-4 inhibitors, GLP-1 receptor agonists, or gliclazide) in the same period. After excluding patients who had not (yet) returned to follow-up, we compared the characteristics of patients who persisted on drug versus those who were no longer on drug at the first available follow-up after at least 3 months.

RESULTS

As compared to those who persisted on drug, patients who discontinued dapagliflozin (51.7%) were more often female, had higher baseline fasting plasma glucose (FPG), HbA1c, and eGFR, and less common use of metformin. Upon multiple regression, higher HbA1c, higher eGFR, and lower metformin use remained independently associated with early discontinuation. Among patients who had been initiated on other GLM, 41.7% discontinued. Variables independently associated with discontinuation were older age, longer diabetes duration, higher HbA1c, eGFR, and albumin excretion, more common use of insulin and less metformin.

CONCLUSION

In routine clinical practice, all variables associated with dapagliflozin discontinuation were also associated with discontinuation of other GLM. Thus, despite a distinctive mechanism of action and a peculiar tolerability profile, no specific predictor of dapagliflozin discontinuation was detected.