RESUMEN
BACKGROUND: Diabetic kidney disease (DKD) is a diabetic microvascular complication often characterized by an unpredictable progression. Hence, early detection and recognition of patients vulnerable to progression is crucial. OBJECTIVE: To develop a prediction model to identify the stages of DKD and the factors contributing to progression to each stage using machine learning. METHODOLOGY: A retrospective study was conducted in a South Indian tertiary care hospital and collected the details of patients diagnosed with DKD from January 2017 to January 2022. Bayesian optimization-based machine learning techniques such as classification and regression were employed. The model was developed with the help of an optimization framework that effectively balances classification, prediction accuracy, and explainability. RESULTS: Of the 311 patients diagnosed with DKD, 227 were selected for the study. A system for predicting DKD has been created for a patient dataset utilizing a variety of machine-learning approaches. The eXtreme gradient (XG) Boost method excelled, achieving 88.75% accuracy, 88.57% precision, 91.4% sensitivity,100% specificity, and 89.49% F1-score. An interpretable data-driven method highlights significant features for early DKD diagnosis. The best explainable prediction model uses the XG Boost classifier, revealing serum uric acid, urea, phosphorous, red blood cells, calcium, and absolute eosinophil count as the major predictors influencing the progression of DKD. In the case of regression models, the gradient boost regressor performed the best, with an R2 score of 0.97. CONCLUSION: Machine learning algorithms can effectively predict the stages of DKD and thus help physicians in providing patients with personalized care at the right time.
Asunto(s)
Teorema de Bayes , Nefropatías Diabéticas , Progresión de la Enfermedad , Aprendizaje Automático , Humanos , Nefropatías Diabéticas/diagnóstico , Estudios Retrospectivos , Masculino , Femenino , Persona de Mediana Edad , Adulto , AncianoRESUMEN
BACKGROUND AND AIM: Adverse drug reactions are one of the contributors to increased hospital admission and length of hospital stay. Among the various antidiabetic agents prescribed, dipeptidyl peptidase-4 (DPP-4) inhibitors have gained wide recognition and shown more persistence than other novel hypoglycemic agents. We performed a scoping review to identify the risk factors contributing to the adverse drug reactions with DPP-4 inhibitors. METHODOLOGY: We followed Preferred Reporting Items for Scoping Review (PRISMA-ScR) Guidelines for reporting the findings. Data sources such as PubMed/MEDLINE, Scopus, Embase, and Cochrane were assessed. We included studies that reported the risk factors contributing to the DPP-4 inhibitor-associated adverse drug reactions. The Joanna Briggs Institute (JBI) critical appraisal checklist was used to assess the methodological quality of the studies. RESULTS: Of the 6406 studies retrieved, 11 studies met our inclusion criteria. Of these 11 studies, seven were post-marketing surveillance studies, one nested case-control study, one comparator cohort study, one food and drug administration (FDA) adverse event reporting system (FAERS)-based observational study, and one questionnaire-based cross-sectional survey study. A total of eight factors were identified that contributed to the DPP-4 inhibitor-associated adverse drug reactions. CONCLUSION: The included studies suggested age >65 years, females, grade 4 and 5 renal impairment, concomitant drugs, disease and drug therapy duration, liver disease, non-smokers, and non-hypertension as risk factors. Further studies should be conducted to provide insight into these risk factors so that the appropriate use of DPP-4 inhibitors in the diabetic population can be encouraged to improve the health-related quality of life. PROSPERO REGISTRATION: CRD42022308764.