Classification of imbalanced data using machine learning algorithms to predict the risk of renal graft failures in Ethiopia.

INTRODUCTION: The prevalence of end-stage renal disease has raised the need for renal replacement therapy over recent decades. Even though a kidney transplant offers an improved quality of life and lower cost of care than dialysis, graft failure is possible after transplantation. Hence, this study aimed to predict the risk of graft failure among post-transplant recipients in Ethiopia using the selected machine learning prediction models. METHODOLOGY: The data was extracted from the retrospective cohort of kidney transplant recipients at the Ethiopian National Kidney Transplantation Center from September 2015 to February 2022. In response to the imbalanced nature of the data, we performed hyperparameter tuning, probability threshold moving, tree-based ensemble learning, stacking ensemble learning, and probability calibrations to improve the prediction results. Merit-based selected probabilistic (logistic regression, naive Bayes, and artificial neural network) and tree-based ensemble (random forest, bagged tree, and stochastic gradient boosting) models were applied. Model comparison was performed in terms of discrimination and calibration performance. The best-performing model was then used to predict the risk of graft failure. RESULTS: A total of 278 completed cases were analyzed, with 21 graft failures and 3 events per predictor. Of these, 74.8% are male, and 25.2% are female, with a median age of 37. From the comparison of models at the individual level, the bagged tree and random forest have top and equal discrimination performance (AUC-ROC = 0.84). In contrast, the random forest has the best calibration performance (brier score = 0.045). Under testing the individual model as a meta-learner for stacking ensemble learning, the result of stochastic gradient boosting as a meta-learner has the top discrimination (AUC-ROC = 0.88) and calibration (brier score = 0.048) performance. Regarding feature importance, chronic rejection, blood urea nitrogen, number of post-transplant admissions, phosphorus level, acute rejection, and urological complications are the top predictors of graft failure. CONCLUSIONS: Bagging, boosting, and stacking, with probability calibration, are good choices for clinical risk predictions working on imbalanced data. The data-driven probability threshold is more beneficial than the natural threshold of 0.5 to improve the prediction result from imbalanced data. Integrating various techniques in a systematic framework is a smart strategy to improve prediction results from imbalanced data. It is recommended for clinical experts in kidney transplantation to use the final calibrated model as a decision support system to predict the risk of graft failure for individual patients.

Predictors for the duration of breastfeeding among ethiopia women of childbearing age with babies; application of accelerate failure time and parametric shared frailty models.

INTRODUCTION: Duration of breastfeeding is the length of the time that infants who were initially breastfed continue to receive breast milk until weaning. The duration of breastfeeding is important for a child's health, growth, and development. However, the duration of breastfeeding decreases from time to time and further leads children to be exposed to malnutrition (stunting, wasting, and weight loss). Children who did not get enough breastfeeding are also exposed to different diseases. Previous studies used a simple survival model and didn't see the shared frailty model on the variable of interest. Therefore, the current study aimed to investigate the factors affecting the duration of breastfeeding among Ethiopian women of reproductive age with babies. METHODS: A cross-sectional study design was conducted on 15,400 women of childbearing age with babies in nine regional states and two city administrations. The data source for the analysis was the 2016 EDHS data. The Cox-proportional hazard model, AFT, and parametric shared frailty models were conducted for the current investigation. Weibull-gamma shared frailty model was in favor of others for current data analysis. RESULTS: Among the covariates, women living in urban area (Φ = 0.96; 95% CI; (0.94,0.97); p-value = 0.001), non-educated women(Φ = 1.03; 95% CI; (1.00,1.06); p-value = 0.039), primary educated women (Φ = 1.13; 95% CI; (1.11,1.15); p-value < 0.001), age of a child (Φ = 0.99; 95% CI; (0.76.0.99); p-value < 0.001) and non-smoker mothers (Φ = 1.60; 95% CI; (1.57, 1.63); p-value < 0.001),birth interval between 2-3 years(Φ = 1.02; 95% CI;(1.09, 1.25, p-value = 0.027), birth interval, > 3 years(Φ = 1.28; 95% CI; (1.06, 1.43); p-value < 0.01 significantly affected the duration of breastfeeding. The median survival time of breastfeeding of women of reproductive age with babies considered under study was 23.4 months. Clustering had a significant effect on the variable of interest. CONCLUSION: Residence area, level of education, age of the child, smoking status of women, and birth interval of successive birth significantly affected the duration of breastfeeding in the current investigation. Hence, the health staff should conduct health-related education for young women, educated women, urban women, smoker women, and women with a shorter interval of birth to increase the women's attitude and awareness towards the use of long-duration of breastfeeding.