In-Hospital Outcomes of Patients on Maintenance Dialysis With Frailty: 10-year Results From the US National Inpatient Sample Database

Frailty in Kidney Disease: A Comprehensive Review to Advance Its Clinical and Research Applications

Frailty is a multisystem syndrome of decreased physiologic reserve that has been shown to strongly and independently predict morbidity and mortality. Frailty is prevalent in patients living with kidney disease and occurs earlier in individuals with kidney disease as compared to the general population. In this comprehensive review, we examine clinical and research applications of frailty in kidney disease populations. Specifically, we clarify the definition of frailty and address common misconceptions, review the mechanisms and epidemiology of frailty in kidney disease, discuss challenges and limitations in frailty measurement, and provide updated evidence related to risk factors for frailty, its associated adverse outcomes, and interventions. We further add to the literature in this topic by highlighting the potential applications of frailty measurement in the care of patients with kidney disease and conclude with our recommendations for future research related to this important syndrome.

Application of intelligent nursing system based on big data in maintenance hemodialysis patients

Maintenance hemodialysis (MHD) is one of the most important renal replacement therapies for patients with end-stage renal disease. However, long-term and frequent treatment not only damages the physiological functions of patients but also leads to serious economic burdens and mental stress. This can easily cause a series of psychological disorders in patients, resulting in severe rejection and fear of MHD. To reduce patient resistance and improve the quality of life of MHD, this article built an intelligent nursing system based on big data and then used the constructed intelligent nursing system to research MHD. Through experiments, it has been found that compared to self-efficacy intervention, intelligent nursing systems can control the concurrent rate of MHD patients below 14 %, and self-efficacy intervention methods can control the concurrent rate of MHD patients above 13 %. Moreover, using intelligent nursing systems can improve the ability of MHD patients to self-care. At the same time, before the use of intelligent nursing systems, the nursing satisfaction of MHD patients also varied greatly, with the overall satisfaction rate after use being 70 % higher than before. Using intelligent nursing systems can improve the satisfaction of MHD patients with nursing outcomes.

A machine learning-based assistant tool for early frailty screening of patients receiving maintenance hemodialysis

PURPOSE

To develop an assistant tool based on machine learning for early frailty screening in patients receiving maintenance hemodialysis.

METHODS

This is a single-center retrospective study. 141 participants' basic information, scale results and laboratory findings were collected and the FRAIL scale was used to assess frailty. Then participants were divided into the frailty group (n = 84) and control group (n = 57). After feature selection, data split and oversampling, ten commonly used binary machine learning methods were performed and a voting classifier was developed.

RESULTS

The grade results of Clinical Frailty Scale, age, serum magnesium, lactate dehydrogenase, comorbidity and fast blood glucose were considered to be the best feature set for early frailty screening. After abandoning models with overfitting or poor performance, the voting classifier based on Support Vector Machine, Adaptive Boosting and Naive Bayes achieved a good screening performance (sensitivity: 68.24% ± 8.40%, specificity:72.50% ± 11.81%, F1 score: 72.55% ± 4.65%, AUC:78.38% ± 6.94%).

CONCLUSION

A simple and efficient early frailty screening assistant tool for patients receiving maintenance hemodialysis based on machine learning was developed. It can provide assistance on frailty, especially pre-frailty screening and decision-making tasks.

Clinical frailty assessment might be associated with mortality in incident dialysis patients

Frailty is associated with mortality in maintenance dialysis patients. For incident dialysis patients, we used the clinical frailty scale (CFS) to investigate frailty as related to mortality or hospitalization within 2 years. We retrospectively reviewed the medical records of patients initiating hemodialysis or peritoneal dialysis during 2016-2018. Based on those records, two dialysis nurses independently used a 9-point CFS (1 = "Very fit" to 9 = "Terminally ill") to assess each patient's frailty at dialysis initiation. Patients with a mean CFS value of 5 or higher were classified into the frail group. The 2-year survival rates or hospitalization-free rates after the initiation of dialysis were compared between the frail (mean CFS score ≥ 5) and non-frail (mean CFS score < 5) groups. The analysis included 155 incident dialysis patients with mean age of 66.7 ± 14.1 (71% male). Frailty was inferred for 39 (25%) patients at dialysis initiation. Kaplan-Meier analyses showed that the survival rate and hospitalization-free rate within 2 years were significantly lower in the frail group than in the non-frail group (p < 0.01). Cox proportional hazards regression analyses revealed the CFS score as associated with the occurrence of a composite outcome, independently of age (hazard ratio 1.34, 95% confidence interval 1.04-1.72). Frailty assessment based on clinical judgment using CFS might predict adverse outcomes in dialysis-initiated patients.