Clustering phosphate and iron-related markers and prognosis in dialysis patients

Abstract

Background Hyperphosphatemia in patients undergoing dialysis is common and is associated with mortality. Recently, the link between phosphate metabolism and iron dynamics has received increasing attention. However, the association between this relationship and prognosis remains largely unexplored. Methods We conducted an observational study of patients who initiated dialysis in the 17 centers participating in the Aichi Cohort Study of Prognosis in Patients Newly Initiated into Dialysis. Data were available on sex, age, use of phosphate binder, drug history, medical history, and laboratory data. After excluding patients with missing values of phosphate, hemoglobin, ferritin, and transferrin saturation, we used the Gaussian mixture model to divide the cohort into clusters based on phosphate, hemoglobin, logarithmic ferritin, and transferrin saturation. We investigated the prognosis of patients in these clusters. The primary outcome was all-cause death. In each cluster, the prognostic impact of phosphate binder was also studied. Results The study included 1 175 patients with chronic kidney disease who initiated dialysis between October 2011 and September 2013. Among them, 785 were men, and 390 were women, with a mean age of 67.9 ± 13.0 years. The patients were divided into three clusters, and mortality was higher in cluster c than in cluster a (p = 0.005). Moreover, the use of phosphate binders was associated with a lower risk of all-cause death in two clusters (a and c) that were characterized by older age and higher prevalence of diabetes mellitus, among others. Conclusion We used an unsupervised machine learning method to cluster patients, using phosphate, hemoglobin, and iron-related markers. In two of the clusters, the oral use of a phosphate binder might improve prognosis.

Clustering using unsupervised machine learning to stratify the risk of immune‐related liver injury

“…In this study, we aimed to reveal the potential of predicting liver‐irAEs occurrence with a combination of some markers by using the GMM, a machine learning model. Currently, machine learning analyses are focused on unsupervised machine learning methods 21–26 . Using a clustering approach, we demonstrated that the objective phenotyping of machines could be stratified by the frequency of liver‐irAEs.…”

“…Currently, machine learning analyses are focused on unsupervised machine learning methods. [21][22][23][24][25][26] Using a clustering approach, we demonstrated that the objective phenotyping of machines could be stratified by the frequency of liver-irAEs. We used the GMM because it assumes a multivariate Gaussian distribution for each component.…”

Identification of clinical phenotypes associated with poor prognosis in patients with nonalcoholic fatty liver disease via unsupervised machine learning

“…GMM is a powerful method that was also able to expose potential phenotypes within an observational cohort from a previous report. 37,38 GMM is a powerful tool for phenotyping patients into interpretable groups on a study-by-study basis with different analyses and factors.…”

“…Therefore, our study identified a possible clinical picture that aligns with the picture engaged by clinicians when treating patients. GMM is a powerful method that was also able to expose potential phenotypes within an observational cohort from a previous report 37,38 . GMM is a powerful tool for phenotyping patients into interpretable groups on a study‐by‐study basis with different analyses and factors.…”

Effects of iron-based phosphate binders on mortality and cardiovascular events in patients receiving maintenance dialysis

“…Furthermore, in CKD patients with or without anemia, iron deficiency on its own is associated with mortality 22 . In addition to the importance of avoiding iron deficiency, observational studies in patients at the induction phase of dialysis suggest that simultaneous management of anemia and iron dynamics, in addition to phosphate management, may lead to a better prognosis 23 . Thus, eliminating iron deficiency is expected to increase life expectancy, either by lowering the risk of anemia, or by lowering the risk of heart failure unrelated to anemia.…”