Evaluation of Outcomes of Peritoneal Dialysis Patients in the Post-COVID-19 Period: A National Multicenter Case-Control Study from Turkey

COVID-19 and outcomes in Chinese peritoneal dialysis patients

BACKGROUND

Reports on COVID-19 in peritoneal dialysis (PD) patients are scarce in China. This study aimed to describe the characteristics and outcomes of PD patients with COVID-19 after China abandoned the 'zero-COVID' policy.

METHODS

This single-centre retrospective study included patients receiving PD who underwent testing for COVID-19 infections between 7 December 2022 and 7 January 2023. Outcomes of interest included factors associated with positive COVID-19 testing result and clinical outcomes including COVID-19-related hospitalisation and severe COVID-19, which were analysed using logistic regression analyses.

RESULTS

A total of 349 PD patients (male 53.6%, age 49 ± 13 years old) were included, and 235 patients (67.3%) were infected. There were no significant differences between COVID-19 and non-COVID-19 patients other than higher proportion of vaccinated patients and slow transporters in the patients who tested positive for COVID-19 (44.7% vs. 28.1%, p = 0.003; 8.7% vs. 1.8%, p = 0.03, respectively). Multivariate analysis showed COVID-19 was associated with vaccination (odds ratio (OR): 1.71, 95% confidence interval (CI): 1.02-2.86) and slow transport type (compared with average transport type, OR: 4.52, 95% CI: 1.01-20.21). Among the patients with infection, 38 (16.2%) patients were hospitalised, 18 (7.7%) patients had severe disease and 9 (3.8%) patients died. In multivariate logistic analysis, both age (OR: 1.04, 95% CI: 1.01-1.07; OR: 1.06, 95% CI: 1.02-1.11) and hyponatremia (OR: 5.44, 95% CI: 1.63-18.13; OR: 6.50, 95% CI: 1.77-23.85) were independent risk factors for COVID-19-related hospitalisation and severe disease.

CONCLUSIONS

Although vaccinated patients were more likely to have tested positive for COVID-19 infection, they appeared to have less severe infection and less need for hospitalisation. Patients who were older with a history of hyponatremia were more likely to experience adverse outcomes from COVID-19.

Machine learning algorithms for the prediction of adverse prognosis in patients undergoing peritoneal dialysis

BACKGROUND

An appropriate prediction model for adverse prognosis before peritoneal dialysis (PD) is lacking. Thus, we retrospectively analysed patients who underwent PD to construct a predictive model for adverse prognoses using machine learning (ML).

METHODS

A retrospective analysis was conducted on 873 patients who underwent PD from August 2007 to December 2020. A total of 824 patients who met the inclusion criteria were included in the analysis. Five commonly used ML algorithms were used for the initial model training. By using the area under the curve (AUC) and accuracy (ACC), we ranked the indicators with the highest impact and displayed them using the values of Shapley additive explanation (SHAP) version 0.41.0. The top 20 indicators were selected to build a compact model that is conducive to clinical application. All model-building steps were implemented in Python 3.8.3.

RESULTS

At the end of follow-up, 353 patients withdrew from PD (converted to haemodialysis or died), and 471 patients continued receiving PD. In the complete model, the categorical boosting classifier (CatBoost) model exhibited the strongest performance (AUC = 0.80, 95% confidence interval [CI] = 0.76-0.83; ACC: 0.78, 95% CI = 0.72-0.83) and was selected for subsequent analysis. We reconstructed a compression model by extracting 20 key features ranked by the SHAP values, and the CatBoost model still showed the strongest performance (AUC = 0.79, ACC = 0.74).

CONCLUSIONS

The CatBoost model, which was built using the intelligent analysis technology of ML, demonstrated the best predictive performance. Therefore, our developed prediction model has potential value in patient screening before PD and hierarchical management after PD.