Herein, we aim to assess mortality risk prediction in peritoneal dialysis patients using machine-learning algorithms for proper prognosis prediction. A total of 1,730 peritoneal dialysis patients in the CRC for ESRD prospective cohort from 2008 to 2014 were enrolled in this study. Classification algorithms were used for prediction of N-year mortality including neural network. The survival hazard ratio was presented by machine-learning algorithms using survival statistics and was compared to conventional algorithms. A survival-tree algorithm presented the most accurate prediction model and outperformed a conventional method such as Cox regression (concordance index 0.769 vs 0.745). Among various survival decision-tree models, the modified Charlson Comorbidity index (mCCI) was selected as the best predictor of mortality. If peritoneal dialysis patients with high mCCI (>4) were aged ≥70.5 years old, the survival hazard ratio was predicted as 4.61 compared to the overall study population. Among the various algorithm using longitudinal data, the AUC value of logistic regression was augmented at 0.804. In addition, the deep neural network significantly improved performance to 0.841. We propose machine learning-based final model, mCCI and age were interrelated as notable risk factors for mortality in Korean peritoneal dialysis patients.

We found that IRI increased expression of STAT3 in murine kidneys, along with inflammation markers. Through the investigation of the role of STAT3 in the AKI-to-CKD transition mechanism using mouse unilateral IRI and unilateral ureteral obstruction models and 24- or 72-h hypoxic induction of primary cultured human tubular epithelial cells, we found that STAT3 could affect the AKI-to-CKD transition. We also observed different degrees of expression in STAT3 isoforms in these processes.

Hayne Cho Park, Do Hyoung Kim, Kyung Don Yoo, Yang-Gyun Kim, Sang-Ho Lee, Hye Eun Yoon, Dong Ki Kim, Seong Nam Kim, Myeong Sung Kim, Yoon Chul Jung, Yon Su Kim, Young-Ki Lee; The Korean Society of Nephrology COVID-19 Task Force Team. Kidney Res Clin Pract 2020;39:145-50. https://doi.org/10.23876/j.krcp.20.046

Long waiting time for deceased donor kidney transplant is inevitable due to the scarcity of donor, resulting in highlighting the importance of waiting time care. We analyzed the Korean Network for Organ Sharing (KONOS) database to assess the impact of waiting time on post-transplant survival outcomes and investigate risk factors for mortality by waiting time based on a complete enumeration survey in Korea. We analyzed all persons aged over 18 years in deceased donor kidney transplant cases enrolled in the Korean Network for Organ Sharing (KONOS) database from January 2000 to January 2015. The primary end point was all-cause mortality after enrollment. Of the 24,296 wait-listed subjects on dialysis, 5,255 patients received kidney transplants from deceased donors, with a median waiting time of 4.5 years. Longer waiting times had distinct deleterious effects on overall survival after transplantation. While waiting for a transplant, patients with diabetes were more likely to die before transplantation (HR 1.515, 95% CI 1.388–1.653, p<0.001). Age was another significant risk factor for mortality. Only 56% of people aged 65 years survived after 10 years of waiting, whereas 86% of people aged 35 years survived after 10 years. Moreover, women on the waiting list were more likely to live longer than men on the list. More attention should be focused on patients with a higher risk of mortality while waiting for a deceased donor kidney transplant, such as patients with diabetes, those of advanced age, and those who are male.

Early mortality after hemodialysis (HD) initiation significantly impacts the longevity of HD patients. This study aimed to quantify the effect sizes of risk factors on mortality using various machine learning approaches. A cohort of 3284 HD patients from the CRC-ESRD (2008–2014) was analyzed. Mortality risk models were validated using logistic regression, ridge regression, lasso regression, and decision trees, as well as ensemble methods like bagging and random forest. To better handle missing data and time-series variables, a recurrent neural network (RNN) with an autoencoder was also developed. Additionally, survival models predicting hazard ratios were employed using survival analysis techniques. The analysis included 1750 prevalent and 1534 incident HD patients (mean age 58.4 ± 13.6 years, 59.3% male). Over a median follow-up of 66.2 months, the overall mortality rate was 19.3%. Random forest models achieved an AUC of 0.8321 for first-year mortality prediction, which was further improved by the RNN with autoencoder (AUC 0.8357). The survival bagging model had the highest hazard ratio predictability (C-index 0.7756). A shorter dialysis duration (< 14.9 months) and high modified Charlson comorbidity index scores (7–9) were associated with hazard ratios up to 7.76 (C-index 0.7693). Comorbidities were more influential than age in predicting early mortality. Monitoring dialysis adequacy (KT/V), RAAS inhibitor use, and urine output is crucial for assessing early prognosis.