Dehydration is associated with production of organic osmolytes and predicts physical long-term symptoms after COVID-19: a multicenter cohort study

Abstract

Background: We have previously shown that iatrogenic dehydration is associated with a shift to organic osmolyte production in the general ICU population. The aim of the present investigation was to determine the validity of the physiological response to dehydration known as aestivation and its relevance for long-term disease outcome in COVID-19.

Methods: The study includes 374 COVID-19 patients from the Pronmed cohort admitted to the ICU at Uppsala University Hospital. Dehydration data was available for 165 of these patients and used for the primary analysis. Validation was performed in Biobanque Québécoise de la COVID-19 (BQC19) using 1052 patients with dehydration data. Dehydration was assessed through estimated osmolality (eOSM = 2Na + 2 K + glucose + urea), and correlated to important endpoints including death, invasive mechanical ventilation, acute kidney injury, and long COVID-19 symptom score grouped by physical or mental.

Results: Increasing eOSM was correlated with increasing role of organic osmolytes for eOSM, while the proportion of sodium and potassium of eOSM were inversely correlated to eOSM. Acute outcomes were associated with pronounced dehydration, and physical long-COVID was more strongly associated with dehydration than mental long-COVID after adjustment for age, sex, and disease severity. Metabolomic analysis showed enrichment of amino acids among metabolites that showed an aestivating pattern.

Conclusions: Dehydration during acute COVID-19 infection causes an aestivation response that is associated with protein degradation and physical long-COVID.

Trial registration: The study was registered à priori (clinicaltrials.gov: NCT04316884 registered on 2020-03-13 and NCT04474249 registered on 2020-06-29).

Keywords: Acute kidney injury; Aestivation; Intensive care medicine; Long-COVID; SARS-CoV-2; Urea synthesis.

Fig. 1

The aestivation hypothesis, which is the subject of the present investigation, is that there is a metabolic response to dehydration that induces the production of the organic osmolytes urea and glucose. This requires protein breakdown, which is further hypothesized to cause physical long-COVID because of the muscle weakness. The main parameters investigated in the present study are estimated osmolality (eOSM = 2*Na⁺ + 2*K⁺ + Glucose + Urea) that is used as a measure of dehydration. The degree of aestivation is measure as the decreasing proportion of ionic (sodium and potassium) osmolytes to total osmolality, and increasing proportion of organic osmolytes (glucose and urea). Finally, the metabolic shift to protein breakdown is investigated using plasma metabolomics to detect release of amino acids that will, in turn, be used by the liver for gluconeogenesis and urea synthesis

Fig. 2

A The present study was based on a discovery analysis of the prospective observational cohort Pronmed with critically ill COVID-19 patients from the ICU at Uppsala University Hospital (A). Out of a total of 374 included patients, 165 had plasma urea analyzed at some point during their ICU stay and could be used to analyze the aestivation response through estimated osmolality (eOSM). Out of these 54 participated in the 3–6 month follow-up and provided data on remaining symptoms. B, C Aestivation response showing the fraction of the estimated total osmolality (eOSM = 2*Na + 2*K + Glucose + Urea) for the ionic osmolytes sodium and potassium (B), and the organic osmolytes glucose and urea (C), showing a shift to organic osmolytes with increasing eOSM. Pearson regression line with p value and R² for the correlation. D, E, F Maximum dehydration measured as eOSM was higher in critically ill COVID-19 patients with important outcomes such as acute kidney injury (AKI, D), need for invasive mechanical ventilation (IMV, E), and 90-day mortality (F). Student’s T-test was used to test for chance difference. G, H, I Interestingly, maximal dehydration was higher in patients who reported more than average remaining physical (G) symptoms after 3–6 months, but not mental symptoms (H). Student’s T-test was used to test for chance difference. The analysis adjusted for sex, age and disease severity using SAPS-3 shows a substantial effect of eOSM on physical long-COVID but not on mental long-COVID (I)

Fig. 3

A To validate the findings the same analysis was performed in the Biobanque Québécoise de la COVID-19 (BQC19) (A). Out of a total of 3768 included patients, 1637 had plasma urea analyzed at some point during their ICU stay and could be used to analyze the aestivation response through estimated osmolality (eOSM). Out of these 872 patients filled out questionnaires on remaining symptoms. B, C The validation cohort recapitulates the aestivation response for the ionic osmolytes (B), and the organic osmolytes (C). Pearson regression line with p value and R² for the correlation. D,E,F: As in the Pronmed cohort maximum dehydration was higher in more severely ill COVID-19 patients for the outcomes acute kidney injury (AKI, D), need for invasive mechanical ventilation (IMV, E), and hospital mortality (F). Student’s T-test was used to test for chance difference. G, H, I Finally, the association of maximal dehydration with physical symptoms after 3–6 months was reproduced (G). In addition, an association was seen for mental long-COVID in the BQC19 cohort (H). Student’s T-test was used to test for chance difference. The analysis adjusted for sex, age and disease severity using ICU-admission reproduces the substantially greater effect eOSM has on physical long-COVID than on mental long-COVID, although both show significant effect (I)

Fig. 4

Predictive validation was performed using an 80:20 split of the BQC19 dataset to test the accuracy of the effect of dehydration adjusted for age, sex and disease severity using ICU-admission. Maximal dehydration measured as estimated osmolality (eOSM = 2*Na⁺ + 2*K⁺ + Glucose + Urea) was a stronger predictor of physical long-COVID (A) as indicated by larger area under the ROC curve (AUC) than for mental long-COVID (B)