Prediction of premature all-cause mortality in patients receiving peritoneal dialysis using modified artificial neural networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhou Q
PROVIDER: S-EPMC8202888 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Unlike hemodialysis (HD), peritoneal dialysis (PD) is a continuous therapy and does not induce myocardial stunning. Yet, the death risk in HD and PD patients is similar. This study tested the hypothesis that serum potassium abnormalities contribute more to the death risk in PD patients than in HD patients.Data from patients treated in DaVita facilities between July 1, 2001 and June 30, 2006 (n=10,468 PD patients; n=111,651 HD patients) were used to determine association of serum potassium with mortality.PD patients were significantly more likely to have serum potassium < 4 mEq/L, with an adjusted odds ratio of 3.30 (95% confidence interval [95% CI], 3.05, 3.56). There was a U-shaped relationship between time-averaged serum potassium and all-cause and cardiovascular mortality of PD patients, with adjusted hazards ratios of 1.51 for all-cause mortality for potassium < 3.5 mEq/L (95% CI, 1.29, 1.76) and 1.52 for potassium ? 5.5 mEq/L (95% CI, 1.32, 1.75). The population-attributable risks for all-cause mortality for serum potassium < 4.0 and ? 5.5 mEq/L were 3.6% and 1.9%, respectively, in PD patients, and 0.8% and 1.5%, respectively, in HD patients.Abnormalities in serum potassium contribute disproportionately to the high death risk in PD patients. This may, in part, account for the equivalent cardiac risk seen with the two therapies.
| S-EPMC3408121 | biostudies-literature
Project description:Technique failure is a frequent complication of peritoneal dialysis (PD), but the association between causes of death-censored technique failure and mortality remains unclear. Using Australian and New Zealand Dialysis and Transplant (ANZDATA) registry data, we examined the associations between technique failure causes and mortality in all incident PD patients who experienced technique failure between 1989-2014. Of 4663 patients, 2415 experienced technique failure attributed to infection, 883 to inadequate dialysis, 836 to mechanical failure and 529 to social reasons. Compared to infection, the adjusted hazard ratios (HR) for all-cause mortality in the first 2 years were 0.83 (95%CI 0.70-0.98) for inadequate dialysis, 0.78 (95%CI 0.66-0.93) for mechanical failure and 1.46 (95%CI 1.24-1.72) for social reasons. The estimates from the competing risk models were similar. There was an interaction between age and causes of technique failure (pinteraction < 0.001), such that the greatest premature mortality was observed in patients aged >60 years post social-related technique failure. There was no association between causes of technique failure and mortality beyond 2 years. In conclusion, infection and social-related technique failure are associated with premature mortality within 2 years post technique failure. Future studies examining the associations may help to improve outcomes in these patients.
| S-EPMC5838094 | biostudies-literature
Project description:BackgroundThe large amount of glucose in the dialysate used in peritoneal dialysis (PD) likely affects the glycemic control. The aim of this study was to investigate the association between HbA1c variability, as a measure of long-term glycemic variability, and the risk of all-cause mortality in diabetic patients with PD.Methods325 patients with diabetes and ESRD were followed (2008-2018) in the Swedish Renal Registry. Patients were separated in seven groups according to level of HbA1c variability. The group with the lowest variability was denoted the reference. The ratio of the standard deviation (SD) to the mean of HbA1c, HbA1c (SD)/HbA1c (mean), i.e. the coefficient of variation (CV), was defined as HbA1c variability. Hazard ratios (HR) and 95% confidence intervals (CI) were examined using Cox regression analyses.ResultsDuring follow-up, 170 (52%) deaths occurred. The highest mortality was among patients with the second highest HbA1c variability, CV≥2.83 [n = 44 of which 68% patients died]. In the multivariate analyses where lowest HbA1c variability (CV≤0.51) was used as the reference group, HbA1c CV 2.83-4.60 (HR 3.15, 95% CI 1.78-5.55; p<0.001) and CV> 4.6 (HR 2.48, 95% CI 1.21-5.11; p = 0.014) were associated with increased risk of death.ConclusionThe high risk of all-cause mortality in patients with diabetes and PD increased significantly with elevated HbA1c variability, as measure of long-term glycemic control. This indicates that stable glycemia is associated with an improvement of survival; whereas more severe glycemic fluctuations, possibly caused by radical changes in dialysis regimes or peritonitis, are associated with a higher risk of mortality in diabetic patients with PD.
| S-EPMC8789125 | biostudies-literature
Project description:BackgroundThe Aboriginal population in Canada experiences high rates of end-stage renal disease and need for dialytic therapies. Our objective was to examine rates of mortality, technique failure and peritonitis among adult aboriginal patients receiving peritoneal dialysis in the province of Manitoba. We also aimed to explore whether differences in these rates may be accounted for by location of residence (i.e., urban versus rural).MethodsWe included all adult patients residing in the province of Manitoba who received peritoneal dialysis during the period from 1997-2007 (n = 727). We extracted data from a local administrative database and from the Canadian Organ Replacement Registry and the Peritonitis Organism Exit-sites/Tunnel infections (POET) database. We used Cox and logistic regression models to determine the relationship between outcomes and Aboriginal ethnicity. We performed Kaplan-Meier analyses to examine the relationship between outcomes and urban (i.e., 50 km or less from the primary dialysis centre in Winnipeg) versus rural (i.e., more than 50 km from the centre) residency among patients who were aboriginal.ResultsOne hundred sixty-one Aboriginal and 566 non-Aboriginal patients were included in the analyses. Adjusted hazard ratios for mortality (HR 1.476, CI 1.073-2.030) and adjusted time to peritonitis (HR 1.785, CI 1.352-2.357) were significantly higher among Aboriginal patients than among non-Aboriginal patients. We found no significant differences in mortality, technique failure or peritonitis between urban- or rural-residing Aboriginal patients.InterpretationCompared with non-Aboriginal patients receiving peritoneal dialysis, Aboriginal patients receiving peritoneal dialysis had higher mortality and faster time to peritonitis independent of comorbidities and demographic characteristics. This effect was not influenced by place of residence, whether rural or urban.
| S-EPMC2942916 | biostudies-literature
Project description:BackgroundResults concerning the association between peritoneal dialysis-related peritonitis and mortality in peritoneal dialysis patients are inconclusive, with one potential reason being that the time-dependent effect of peritonitis has rarely been considered in previous studies. This study aimed to evaluate whether peritonitis has a negative impact on mortality in a large cohort of peritoneal dialysis patients. We also assessed the changing impact of peritonitis on patient mortality with respect to duration of follow-up.MethodsThis retrospective cohort study included incident patients who started peritoneal dialysis from 1 January 2006 to 31 December 2011. Episodes of peritonitis were recorded at the time of onset, and peritonitis was parameterized as a time-dependent variable for analysis. We used the Cox regression model to assess whether peritonitis has a negative impact on mortality.ResultsA total of 1321 patients were included. The mean age was 48.1 ± 15.3 years, 41.3% were female, and 23.5% with diabetes mellitus. The median (interquartile) follow-up time was 34 (21-48) months. After adjusting for confounders, peritonitis was independently associated with 95% increased risk of all-cause mortality (hazard ratio, 1.95; 95% confidence interval: 1.46-2.60), 90% increased risk of cardiovascular mortality (hazard ratio, 1.90; 95% confidence interval: 1.28-2.81) and near 4-fold increased risk of infection-related mortality (hazard ratio, 4.94; 95% confidence interval: 2.47-9.86). Further analyses showed that peritonitis was not significantly associated with mortality within 2 years of peritoneal dialysis initiation, but strongly influenced mortality in patients dialysed longer than 2 years.ConclusionsPeritonitis was independently associated with higher risk of all-cause, cardiovascular and infection-related mortality in peritoneal dialysis patients, and its impact on mortality was more significant in patients with longer peritoneal dialysis duration.
| S-EPMC5460447 | biostudies-literature
Project description:BackgroundThe association between serum creatine kinase and mortality in patients with peritoneal dialysis (PD) remained unknown.MethodsWe retrospectively collected data on 3,446 incident patients with from five PD centers in China between 1 January 2005 and 31 May 2020. Creatine kinase was collected 1 week before the start of PD. We examined the association between creatine kinase and mortality using Cox proportional hazards model.ResultsThe median creatine kinase was 113 (range, 1.22-4,574) IU/L. With a median follow-up of 39.5 (range, 3.1-181.5) months, 763 (22.1%) all-cause deaths occurred, including 384 (11.1%) cardiovascular deaths. As compared with a creatine kinase of 111-179 IU/L (reference range), a higher creatine kinase (>179 IU/L) was associated with increased risks of all-cause mortality [hazards ratio (HR), 1.72; 95% CI, 1.35-2.00; E-value = 2.83] and cardiovascular mortality (HR, 1.44; 95% CI, 1.05-1.98; E-value = 2.24). As compared with the reference range, a lower creatine kinase (<111 IU/L) was associated with increased risks of all-cause mortality (HR, 1.40; 95% CI, 1.12-1.76; E-value = 2.15) and cardiovascular mortality (HR, 1.45; 95% CI, 1.08-1.94; E-value = 2.26). Interaction between creatine kinase and no hyperlipidemia (p = 0.034 for interaction) was observed.ConclusionA creatine kinase before the start of PD between 111 and 179 IU/L was associated with a lower risk of death than a higher or lower creatine kinase, resulting in a U-shaped association curve.
| S-EPMC9127078 | biostudies-literature
Project description:Avoidable hospital readmissions not only contribute to the high costs of healthcare in the US, but also have an impact on the quality of care for patients. Large scale adoption of Electronic Health Records (EHR) has created the opportunity to proactively identify patients with high risk of hospital readmission, and apply effective interventions to mitigate that risk. To that end, in the past, numerous machine-learning models have been employed to predict the risk of 30-day hospital readmission. However, the need for an accurate and real-time predictive model, suitable for hospital setting applications still exists. Here, using data from more than 300,000 hospital stays in California from Sutter Health's EHR system, we built and tested an artificial neural network (NN) model based on Google's TensorFlow library. Through comparison with other traditional and non-traditional models, we demonstrated that neural networks are great candidates to capture the complexity and interdependency of various data fields in EHRs. LACE, the current industry standard, showed a precision (PPV) of 0.20 in identifying high-risk patients in our database. In contrast, our NN model yielded a PPV of 0.24, which is a 20% improvement over LACE. Additionally, we discussed the predictive power of Social Determinants of Health (SDoH) data, and presented a simple cost analysis to assist hospitalists in implementing helpful and cost-effective post-discharge interventions.
| S-EPMC5510858 | biostudies-other
Project description:Rationale & objectiveWe sought to compare outcomes of patients receiving dialysis after cardiothoracic surgery on the basis of dialysis modality (intermittent hemodialysis [HD] vs peritoneal dialysis [PD]).Study designThis was a retrospective analysis.Setting & participantsIn total, 590 patients with kidney failure receiving intermittent HD or PD undergoing coronary artery bypass graft and/or valvular cardiac surgery at Cleveland Clinic were included.ExposureThe patients received PD versus HD (intermittent or continuous).OutcomesOur primary outcomes were in-hospital and 30-day mortality. Secondary outcomes were length of stay, days in the intensive care unit, the number of intraoperative blood transfusions, postsurgical pericardial effusion, and sternal wound infection, and a composite of the following 4 in-hospital events: death, cardiac arrest, effusion, and sternal wound infection.Analytical approachWe used χ2, Fisher exact, Wilcoxon rank sum, and t tests, Kaplan-Meier survival, and plots for analysis.ResultsAmong the 590 patients undergoing cardiac surgery, 62 (11%) were receiving PD, and 528 (89%) were receiving intermittent HD. Notably, 30-day Kaplan-Meier survival was 95.7% (95% CI: 93.9-97.5) for HD and 98.2% (95% CI: 94.7-100) for PD (P = 0.30). In total, 75 patients receiving HD (14.2%) and 1 patient receiving PD (1.6%) had a composite of 4 in-hospital events (death, cardiac arrest, effusion, and sternal wound infection) (P = 0.005). Out of 62 patients receiving PD, 16 (26%) were converted to HD.LimitationsRetrospective analyses are prone to residual confounding. We lacked details about nutritional data. Intensive care unit length of stay was used as a surrogate for volume status control. Patients have been followed in a single health care system. The HD cohort outnumbered the PD cohort significantly.ConclusionsWhen compared with PD, HD does not appear to improve outcomes of patients with kidney failure undergoing cardiothoracic surgery. Patients receiving PD had a lower incidence of a composite outcome of 4 in-hospital events (death, cardiac arrest, pericardial effusion, and sternal wound infections).
| S-EPMC10907222 | biostudies-literature
Project description:Patients with end-stage renal disease (ESRD) are at a higher mortality risk compared with the general population. Previous studies have described a relationship between mortality and patients with ESRD, but the data on standardized mortality ratio (SMR) corresponding to different causes of death in patients undergoing hemodialysis (HD) and peritoneal dialysis (PD) are limited. This study was designed as a nationwide population-based retrospective cohort study. Incident dialysis patients between January 2000 and December 2015 in Taiwan were included. Using data acquired from the Taiwan Death Registry, SMR values were calculated and compared with the overall survival. The results showed there were a total of 128,966 patients enrolled, including 117,376 incident HD patients and 11,590 incident PD patients. It was found that 75,297 patients (58.4%) died during the period of 2000-2017. The overall SMR was 5.21. The neoplasms SMR was 2.11; the endocrine, nutritional, metabolic, and immunity disorders SMR was 13.53; the circulatory system SMR was 4.31; the respiratory system SMR was 2.59; the digestive system SMR was 6.1; and the genitourinary system SMR was 27.22. Therefore, more attention should be paid to these diseases in clinical care.
| S-EPMC9915131 | biostudies-literature
Project description:Background New lipid-lowering therapy at the start of dialysis and measurement of lipid parameters over the follow-up period is not recommended in dialysis patients, which seems unappropriated in clinical practice. We aimed to examine the effect of hyperlipidemia on mortality in patients undergoing continuous ambulatory peritoneal dialysis (CAPD). Methods A retrospective cohort study was performed, including 2939 incident CAPD patients from five dialysis facilities between January 1, 2005, and December 31, 2018. The primary outcome was all-cause mortality. The association between hyperlipidemia at the start of CAPD and all-cause mortality was evaluated using Cox proportional hazards regression. Results Of 2939 with a median age of 50.0 (interquartile range, 39.0–61.0), 1697 (57.7%) were men, 533 (18.1%) had hyperlipidemia, 549 (18.7%) had diabetes mellitus, 1915 (65.2%) had hypertension, and 410 (14.0%) had a history of CVD. During the median follow-up period of 35.1 months, 519 (17.7%) died, including 402 (16.7%, 47.4/1000 patient-years) in the non-hyperlipidemia group and 117 (22.0%, 71.1/1000 patient-years) in the hyperlipidemia group. Over the overall follow-up period, patients with hyperlipidemia had an equally high risk of all-cause mortality throughout follow-up as those without hyperlipidemia ([HR] 1.04, 95% confidence interval [CI] 0.83 to 1.31). However, from the 48-month follow-up onwards, hyperlipidemia was associated with a 2.26 (95% CI 1.49 to 3.43)-time higher risk of all-cause mortality than non-hyperlipidemia. Hypertension modified the association between hyperlipidemia and all-cause mortality (P for interaction < 0.001). A significantly increased risk of all-cause mortality was observed among patients with hypertension (HR 2.27, 95%CI 1.44–3.58). Conclusion Among CAPD patients, hyperlipidemia at the beginning of CAPD was associated with a high risk of long-term mortality. Hypertension may mediate the association. Our findings suggested that long-term lipid-lowering treatment should be used in those patients with hyperlipidemia. Supplementary information The online version contains supplementary material available at 10.1186/s12882-022-02970-w.
| S-EPMC9590170 | biostudies-literature