Handbook of Dialysis, Fourth Edition

Analyzing Monthly Blood Test Data to Forecast 30-Day Hospital Readmissions among Maintenance Hemodialysis Patients

Background: The increase in the global population of hemodialysis patients is linked to aging demographics and the prevalence of conditions such as arterial hypertension and diabetes mellitus. While previous research in hemodialysis has mainly focused on mortality predictions, there is a gap in studies targeting short-term hospitalization predictions using detailed, monthly blood test data. Methods: This study employs advanced data preprocessing and machine learning techniques to predict hospitalizations within a 30-day period among hemodialysis patients. Initial steps include employing K-Nearest Neighbor (KNN) imputation to address missing data and using the Synthesized Minority Oversampling Technique (SMOTE) to ensure data balance. The study then applies a Support Vector Machine (SVM) algorithm for the predictive analysis, with an additional enhancement through ensemble learning techniques, in order to improve prediction accuracy. Results: The application of SVM in predicting hospitalizations within a 30-day period among hemodialysis patients resulted in an impressive accuracy rate of 93%. This accuracy rate further improved to 96% upon incorporating ensemble learning methods, demonstrating the efficacy of the chosen machine learning approach in this context. Conclusions: This study highlights the potential of utilizing machine learning to predict hospital readmissions within a 30-day period among hemodialysis patients based on monthly blood test data. It represents a significant leap towards precision medicine and personalized healthcare for this patient group, suggesting a paradigm shift in patient care through the proactive identification of hospitalization risks.

Meta-analysis of haematocrit and activated partial thromboplastin time as risk factors for unplanned interruptions in patients undergoing continuous renal replacement therapy

OBJECTIVE

Although continuous renal replacement therapy (CRRT) is common, unplanned interruptions often limit its usefulness. Unplanned interruption refers to the forced interruption of blood purification treatment, the failure to complete blood purification treatment goals or the failure to meet blood purification schedule times. This study aimed to evaluate the effect of haematocrit and activated partial thromboplastin time (APTT) on the incidence of unplanned interruptions in critical patients with CRRT.

METHODS

A systematic review and a meta-analysis were performed by searching the databases of China National Knowledge Infrastructure, Wanfang, VIP, China Biomedical Literature, Cochrane Library, PubMed, Web of Science and Embase from their inception to 31st March 2022 for all studies with a comparator or independent variable relating to the unplanned interruption of CRRT.

RESULTS

Nine studies involving 1165 participants were included. Haematocrit and APTT were independent risk factors for the unplanned interruption of CRRT. The higher the haematocrit level, the greater the risk of unplanned CRRT interruptions (relative risk ratio [RR] = 1.04, 95% confidence interval [CI]: 1.02, 1.07, Z = 4.27, p < 0.001). The prolongation of APPT reduced the risk of unplanned CRRT interruptions (RR = 0.94, 95% CI: 0.92, 0.96, Z = 6.10, p < 0.001).

CONCLUSION

Haematocrit and APTT are the influencing factors on the incidence of unplanned interruptions in critical patients undergoing CRRT.

Identifying survival protective factors for chronic dialysis patients with surgically confirmed acute mesenteric ischemia

BACKGROUND

Mesenteric ischemia is significantly more common in end-stage kidney disease patients undergoing chronic dialysis than in the general population and is associated with high morbidity and mortality. However, reports on prognostic factors in this population are limited.

AIM

To elucidate the in-hospital outcomes of acute mesenteric ischemia in chronic dialysis patients and to analyze protective factors for survival.

METHODS

The case data of 426 chronic dialysis patients who were hospitalized in a tertiary medical center for acute mesenteric ischemia over a 14-year period were retrospectively reviewed. Of these cases, 103 were surgically confirmed, and the patients were enrolled in this study. A Cox regression analysis was used to evaluate the protective factors for survival.

RESULTS

The in-hospital mortality rate among the 103 enrolled patients was 46.6%. Univariate analysis was performed to compare factors in survivors and nonsurvivors, with better in-hospital outcomes associated with a surgery delay (defined as the time from onset of signs and symptoms to operation) < 4.5 d, no shock, a higher potassium level on day 1 of hospitalization, no resection of the colon, and a total bowel resection length < 110 cm. After 1 wk of hospitalization, patients with lower white blood cell count and neutrophil counts, higher lymphocyte counts, and lower C-reactive protein levels had better in-hospital outcomes. Following multivariate adjustment, a higher potassium level on day 1 of hospitalization (HR 1.71, 95%CI 1.19 to 2.46; P = 0.004), a lower neutrophil count (HR 0.91, 95%CI 0.84 to 0.99; P = 0.037) at 1 wk after admission, resection not involving the colon (HR 2.70, 95%CI 1.05 to 7.14; P = 0.039), and a total bowel resection length < 110 cm (HR 4.55, 95%CI 1.43 to 14.29; P = 0.010) were significantly associated with survival.

CONCLUSION

A surgery delay < 4.5 d, no shock, no resection of the colon, and a total bowel resection length < 110 cm predicted better outcomes in chronic dialysis patients with acute mesenteric ischemia.

Second Generation Nanoporous Silicon Nitride Membranes for High Toxin Clearance and Small Format Hemodialysis

Conventional hemodialysis (HD) uses floor-standing instruments and bulky dialysis cartridges containing ≈2 m2 of 10 micrometer thick, tortuous-path membranes. Portable and wearable HD systems can improve outcomes for patients with end-stage renal disease by facilitating more frequent, longer dialysis at home, providing more physiological toxin clearance. Developing devices with these benefits requires highly efficient membranes to clear clinically relevant toxins in small formats. Here, the ability of ultrathin (<100 nm) silicon-nitride-based membranes to reduce the membrane area required to clear toxins by orders of magnitude is shown. Advanced fabrication methods are introduced that produce nanoporous silicon nitride membranes (NPN-O) that are two times stronger than the original nanoporous nitride materials (NPN) and feature pore sizes appropriate for middle-weight serum toxin removal. Single-pass benchtop studies with NPN-O (1.4 mm2 ) demonstrate the extraordinary clearance potential of these membranes (105 mL min-1 m-2 ), and their intrinsic hemocompatibility. Results of benchtop studies with nanomembranes, and 4 h dialysis of uremic rats, indicate that NPN-O can reduce the membrane area required for hemodialysis by two orders of magnitude, suggesting the performance and robustness needed to enable small-format hemodialysis, a milestone in the development of small-format hemodialysis systems.

Biocompatibility Reduces Inflammation-Induced Apoptosis in Mesothelial Cells Exposed to Peritoneal Dialysis Fluid

Background/Aims: Peritonitis is a major complication that arises out of peritoneal dialysis (PD), leading to death and loss of mesothelium and peritoneal injury, which may impede PD. We studied the combined impact of inflammatory mediators and PD fluids on mesothelial cell death. Methods: Cultured human mesothelial cells. Results: Inflammatory cytokines (TNF-α and interferon-γ) cooperate with bioincompatible PD fluids containing high glucose degradation product (GDP) concentrations to promote mesothelial cell death. Thus, the inflammatory cytokine cocktail induced a higher rate of death in cells cultured in high GDP PD fluid than in low GDP PD fluid or cell culture medium (cell death expressed as % hypodiploid cells: TNF-α and interferon-γ in RPMI: 14.15 ± 1.68, TNF-α and interferon-γ in 4.25% low GDP PD fluid 13.16 ± 3.29, TNF-α and interferon-γ in 4.25% high GDP PD fluid 25.88 ± 2.18%, p < 0.05 vs. the other two groups). BclxL BH4 peptides, Apaf-1 inhibition or caspase inhibition failed to protect from apoptosis induced by the combination of inflammatory cytokines and bioincompatible PD fluids, although they protected from other forms of mesothelial cell apoptosis. Conclusion: Inflammation cooperates with high GDP PD fluids to promote mesothelial cell death, which is resistant to several therapeutic approaches. This information provides a framework for selection of PD fluid during peritonitis.