Effect of Serum Albumin Changes on Mortality in Patients with Peritoneal Dialysis: A Joint Modeling Approach and Personalized Dynamic Risk Predictions

Development and validation of prediction model for technique failure in peritoneal dialysis patients: An observational study

AIM

This study aimed to establish a prediction model in peritoneal dialysis patients to estimate the risk of technique failure and guide clinical practice.

METHODS

Clinical and laboratory data of 424 adult peritoneal dialysis patients were retrospectively collected. The risk prediction models were built using univariate Cox regression, best subsets approach and LASSO Cox regression. Final nomogram was constructed based on the best model selected by the area under the curve.

RESULTS

After comparing three models, the nomogram was built using the LASSO Cox regression model. This model included variables consisting of hypertension and peritonitis, serum creatinine, low-density lipoprotein, fibrinogen and thrombin time, and low red blood cell count, serum albumin, triglyceride and prothrombin activity. The predictive model constructed performed well using receiver operating characteristic curve and area under the curve value, C-index and calibration curve.

CONCLUSION

This study developed and verified a new prediction instrument for the risk of technique failure among peritoneal dialysis patients.

Peritoneal Dialysis-Related Infections

Peritoneal dialysis (PD) represents an important treatment choice for patients with kidney failure. It allows them to dialyze outside the hospital setting, facilitating enhanced opportunities to participate in life-related activities, flexibility in schedules, time and cost savings from reduced travel to dialysis centers, and improved quality of life. Despite its numerous advantages, PD utilization has been static or diminishing in parts of the world. PD-related infection, such as peritonitis, exit-site infection, or tunnel infection, is a major concern for patients, caregivers, and health professionals-which may result in hesitation to consider this as treatment or to cease therapy when these complications take place. In this review, the definition, epidemiology, risk factors, prevention, and treatment of PD-related infection on the basis of the contemporary evidence will be described.

Mortality prediction with adaptive feature importance recalibration for peritoneal dialysis patients

The study aims to develop AICare, an interpretable mortality prediction model, using electronic medical records (EMR) from follow-up visits for end-stage renal disease (ESRD) patients. AICare includes a multichannel feature extraction module and an adaptive feature importance recalibration module. It integrates dynamic records and static features to perform personalized health context representation learning. The dataset encompasses 13,091 visits and demographic data of 656 peritoneal dialysis (PD) patients spanning 12 years. An additional public dataset of 4,789 visits from 1,363 hemodialysis (HD) patients is also considered. AICare outperforms traditional deep learning models in mortality prediction while retaining interpretability. It uncovers mortality-feature relationships and variations in feature importance and provides reference values. An AI-doctor interaction system is developed for visualizing patients' health trajectories and risk indicators.

Associations between liver function parameters and poor clinical outcomes in peritoneal dialysis patients

Patients with end-stage renal disease (ESRD) have significantly lower survival rates compared with the general population of the same age. Peritoneal dialysis (PD) is an effective treatment for patients with ESRD, but the clinical outcome of PD patients is still not promising. The survival of PD patients is associated with various clinical factors, and exploring some valid risk predictors may be beneficial for this population. In this review, by integrating the latest research, we summarized the association of some common and novel liver function parameters (ALT, AST, ALP, GGT, serum bilirubin, pre-albumin, albumin, albumin-globulin ratio [AGR], serum ferritin, and hyaluronic acid) with clinical outcomes in PD patients. It may contribute to a better understanding of potential risk factors and help to develop strategies to prevent the disease progression.