Assessing proximate intermediates between ambient temperature, hospital admissions, and mortality in hemodialysis patients

Prediction of mortality in hemodialysis patients based on autoencoders

BACKGROUND

Patients with end-stage renal disease (ESRD) undergoing hemodialysis (HD) exhibit a high mortality risk, particularly at the onset of treatment. Conventional risk assessment models, dependent on extensive temporal data accumulation, frequently encounter issues of data incompleteness and lengthy collection periods.

OBJECTIVE

This study addresses the imbalance in short-term HD data and the issue of missing data features, achieving a robust assessment of mortality risk for HD patients over the subsequent 30 to 450 days.

METHODS

An autoencoder-based mortality prediction model for HD patients is proposed. Leveraging the manifold structure of the non-missing features and the intrinsic relationship between the features in the high-dimensional data space, the model infers the values of the missing features. Noise and redundant information typically distort the manifold structure, impacting the accuracy of inferences about missing features. Consequently, we generate feature dropping masks to simulate the missing data distribution in the deep learning framework and design an autoencoder, forming an adaptive feature extraction module. The module utilizes readily available short-term data for unsupervised learning, enabling the encoder to reconstruct missing features and derive latent representations. Finally, a classifier based on the latent representations achieves the mortality prediction.

RESULTS

Over a 30-day observation window, the model demonstrated superior mortality prediction performance compared to other models across all prediction windows. Feature importance analysis showed that creatinine and age are consistently the most critical features across all prediction windows. Glucose (fasting) and platelet count also remain significant, with their correlation with mortality risk increasing over time. Serum albumin, international standard ratio, and phosphate are particularly important for short-term predictions, while conjugated bilirubin and prothrombin time gain prominence in mid- and long-term predictions.

CONCLUSION

The proposed model proficiently leverages short-term HD data to provide precise mortality risk evaluations in HD patients, with particular efficacy in the short-term. Its application holds considerable value for clinical decision-making and risk management in this patient population.

Ambient temperature and the occurrence of intradialytic hypotension in patients receiving hemodialysis

Background

Intradialytic hypotension (IDH) is a common hemodialysis complication causing adverse outcomes. Despite the well-documented associations of ambient temperatures with fluid removal and pre-dialysis blood pressure (BP), the relationship between ambient temperature and IDH has not been adequately studied.

Methods

We conducted a cohort study at a tertiary hospital in southern Taiwan between 1 January 2016 and 31 October 2021. The 24-h pre-hemodialysis mean ambient temperature was determined using hourly readings from the weather station closest to each patient's residence. IDH was defined using Fall40 [systolic BP (SBP) drop of ≥40 mmHg] or Nadir90/100 (SBP <100 if pre-dialysis SBP was ≥160, or SBP <90 mmHg). Multivariate logistic regression with generalizing estimating equations and mediation analysis were utilized.

Results

The study examined 110 400 hemodialysis sessions from 182 patients, finding an IDH prevalence of 11.8% and 10.4% as per the Fall40 and Nadir90/100 criteria, respectively. It revealed a reverse J-shaped relationship between ambient temperature and IDH, with a turning point around 27°C. For temperatures under 27°C, a 4°C drop significantly increased the odds ratio of IDH to 1.292 [95% confidence interval (CI) 1.228 to 1.358] and 1.207 (95% CI 1.149 to 1.268) under the Fall40 and Nadir90/100 definitions, respectively. Lower ambient temperatures correlated with higher ultrafiltration, accounting for about 23% of the increased IDH risk. Stratified seasonal analysis indicated that this relationship was consistent in spring, autumn and winter.

Conclusion

Lower ambient temperature is significantly associated with an increased risk of IDH below the threshold of 27°C, irrespective of the IDH definition. This study provides further insight into environmental risk factors for IDH in patients undergoing hemodialysis.

Amantadine-associated delirium in patients with maintenance dialysis: Insomnia-associated recovery and uneven seasonal distribution

Amantadine hydrochloride is a risky drug for triggering delirium in dialysis patients; however, it is often administered casually. Furthermore, little is known regarding the recovery and prognosis of dialysis patients with amantadine-associated delirium. Data of this retrospective cohort study were collected from a local hospital database for hospitalizations between January 2011 and December 2020. Patients were divided into 2 cohorts: early recovery (recovery within 14 days) and delayed recovery (recovery more than 14 days). The cases were analyzed together with the intermonth temperature using descriptive statistics. A Kaplan-Meier survival curve and binary logistic regression were applied for the analyses of prognoses and factors. A total of 57 patients were included in this study. The most common symptoms were hallucinations (45.61%) and muscle tremors (43.86%). Early recovery was observed in 63.16% of the patients. Only 3.51% of the cases occurred in local summer (June, July, and August). Better prognoses for survival (hazard ratio [HR] = 0.066, 95% confidence interval [95% CI] = 0.021-0.212) and hospitalization costs (7968.42 ± 3438.43 CNY vs 12852.38 ± 9361.13 CNY, P = .031) were observed in patients with early recovery than in those with delayed recovery. In the multivariate logistic regression adjusted by 1:1 propensity score matching, delayed recovery was independently caused by insomnia (P = .022, = 10.119, 95% CI = 1.403-72.990) and avoided in patients with urine volume over 300 mL (P = .029, = 0.018, 95% CI = 0.006-0.621). The increment (per 100 mg) of cumulative dose (P = .190, = 1.588, 95% CI = 0.395-3.172) tended to be a risk of delayed recovery. The area under curve of the receiver operating characteristic curve was 0.867, with a sensitivity of 90.5% and a specificity of 82.4% at the cutoff point (cutoff = 0.432). For amantadine-associated delirium in dialysis patients with uneven seasonal distribution, early recovery with better prognosis should be the aim of treatment by giving priority to the remedy of insomnia.

Climate and the Nephrologist: The Intersection of Climate Change, Kidney Disease, and Clinical Care

Climate change is upon us, and it will have a major effect on both kidney disease and the nephrology practice. But the converse is also true: our treatment of kidney disease has an effect on the climate. Much attention has focused on how rising temperatures can lead to acute and CKD and health exacerbations in patients with established kidney disease. Climate change is also associated with rising air pollution from wildfires and industrial wastes and infectious diseases associated with flooding and changing habitats, all of which heighten the risk of acute and CKD. Less well recognized or understood are the ways nephrology practices, in turn, contribute to still more climate change. Hemodialysis, although lifesaving, can be associated with marked water usage (up to 600 L per dialysis session), energy usage (with one 4-hour session averaging as much as one fifth of the total energy consumed by a household per day), and large clinical wastes (with hemodialysis accounting for one third of total clinical medicine-associated waste). Of note, >90% of dialysis occurs in highly affluent countries, whereas dialysis is much less available in the poorer countries where climate change is having the highest effect on kidney disease. We conclude that not only do nephrologists need to prepare for the rise in climate-associated kidney disease, they must also urgently develop more climate-friendly methods of managing patients with kidney disease.

Combined effects of air pollution and extreme heat events among ESKD patients within the Northeastern United States

BACKGROUND

Increasing number of studies have linked air pollution exposure with renal function decline and disease. However, there is a lack of data on its impact among end-stage kidney disease (ESKD) patients and its potential modifying effect from extreme heat events (EHE).

METHODS

Fresenius Kidney Care records from 28 selected northeastern US counties were used to pool daily all-cause mortality (ACM) and all-cause hospital admissions (ACHA) counts. County-level daily ambient PM_2.5 and ozone (O₃) were estimated using a high-resolution spatiotemporal coupled climate-air quality model and matched to ESKD patients based on ZIP codes of treatment sites. We used time-stratified case-crossover analyses to characterize acute exposures using individual and cumulative lag exposures for up to 3 days (Lag 0-3) by using a distributed lag nonlinear model framework. We used a nested model comparison hypothesis test to evaluate for interaction effects between air pollutants and EHE and stratification analyses to estimate effect measures modified by EHE days.

RESULTS

From 2001 to 2016, the sample population consisted of 43,338 ESKD patients. We recorded 5217 deaths and 78,433 hospital admissions. A 10-unit increase in PM_2.5 concentration was associated with a 5% increase in ACM (rate ratio [RR_Lag0-3]: 1.05, 95% CI: 1.00-1.10) and same-day O₃ (RR_Lag0: 1.02, 95% CI: 1.01-1.03) after adjusting for extreme heat exposures. Mortality models suggest evidence of interaction and effect measure modification, though not always simultaneously. ACM risk increased up to 8% when daily ozone concentrations exceeded National Ambient Air Quality Standards established by the United States, but the increases in risk were considerably higher during EHE days across lag periods.

CONCLUSION

Our findings suggest interdependent effects of EHE and air pollution among ESKD patients for all-cause mortality risks. National level assessments are needed to consider the ESKD population as a sensitive population and inform treatment protocols during extreme heat and degraded pollution episodes.