Prediction of Mortality in Hemodialysis Patients Using Moving Multivariate Distance

Abstract

There is an increasingly widespread use of biomarkers in network physiology to evaluate an organism’s physiological state. A recent study showed that albumin variability increases before death in chronic hemodialysis patients. We hypothesized that a multivariate statistical approach would better allow us to capture signals of impending physiological collapse/death. We proposed a Moving Multivariate Distance (MMD), based on the Mahalanobis distance, to quantify the variability of the multivariate biomarker profile as a whole from one visit to the next. Biomarker profiles from a visit were used as the reference to calculate MMD at the subsequent visit. We selected 16 biomarkers (of which 11 are measured every 2 weeks) from blood samples of 763 chronic kidney disease patients hemodialyzed at the CHUS hospital in Quebec, who visited the hospital regularly (∼every 2 weeks) to perform routine blood tests. MMD tended to increase markedly preceding death, indicating an increasing intraindividual multivariate variability presaging a critical transition. In survival analysis, the hazard ratio between the 97.5th percentile and the 2.5th percentile of MMD reached as high as 21.1 [95% CI: 14.3, 31.2], showing that higher variability indicates substantially higher mortality risk. Multivariate approaches to early warning signs of critical transitions hold substantial clinical promise to identify early signs of critical transitions, such as risk of death in hemodialysis patients; future work should also explore whether the MMD approach works in other complex systems (i.e., ecosystems, economies), and should compare it to other multivariate approaches to quantify system variability.

The New Field of Network Physiology: Building the Human Physiolome

“…New computational and analytical approaches are needed to extract information from complex data, to infer transient interactions between dynamically changing systems, and to quantify global behavior at the organism level generated by networks of interactions that are function of time. In fact, in recent years, we have already witnessed the broad impact of introducing novel concepts and methods derived from modern statistical physics and network theory to biology and medicine, shifting the paradigm from reductionism to a new integrative framework essential to address fundamentally new problems in systems biology (Yao et al, 2019;Prats-Puig et al, 2020;Corkey and Deeney, 2020;Rizi et al, 2021;Barajas-Martínez et al, 2020), neuroscience (Castelluzzo et al, 2020;Pa¨eske et al, 2020;Fesce, 2020;Stramaglia et al, 2021), physiology (Podobnik et al, 2020;Zmazek et al, 2021), clinical medicine (Loscalzo and Barabasi, 2011;Delussi et al, 2020;Li et al, 2020;Liu et al, 2020;McNorgan et al, 2020;Tan et al, 2020;Haug et al, 2021;Liu et al, 2021) and even drug discovery (Hopkins, 2008). A central focus of research within this integrative framework is the interplay between structural connectivity and functional dependency, a key problem in neuroscience, brain research (Bullmore and Sporns, 2009;Gallos et al, 2012;Rothkegel and Lehnertz, 2014;Liu et al, 2015a;Bolton et al, 2020;Wang and Liu, 2020) and human physiology (Pereira-Ferrero et al, 2019;Lavanga et al, 2020;Barajas-Martínez et al, 2021;Gao et al, 2018;Balagué et al, 2020;Porta et al, 2017;Lioi et al, ...…”

Synchrony of biomarker variability indicates a critical transition: Application to mortality prediction in hemodialysis

“…While this study shows the clinical potential of biomarker variability as an EWS, more work is required before clinical implementation. Other multivariate indices of variability exist beyond CVPC1 ( Liu et al., 2021 ; Weinans et al., 2021 ), and variability is only one signal among many that can be extracted from time series (e.g. lag-1 autocorrelations, flickering, skewness, etc., Scheffer et al., 2012 ).…”

Mortality in hemodialysis: Synchrony of biomarker variability indicates a critical transition

“…While this study shows the clinical potential of biomarker variability as an EWS, more work is required before clinical implementation. Other multivariate indices of variability exist beyond CVPC1 29 , and variability is only one signal among many that can be extracted from time series (e.g. lag-1 autocorrelations, flickering, skewness, etc.…”