Hyperosmolar dehydration: A predictor of kidney injury and outcome in hospitalised older adults

Abstract

Background & aims: Hospitalised older adults are vulnerable to dehydration. However, the prevalence of hyperosmolar dehydration (HD) and its impact on outcome is unknown. Serum osmolality is not measured routinely but osmolarity, a validated alternative, can be calculated using routinely measured serum biochemistry. This study aimed to use calculated osmolarity to measure the prevalence of HD (serum osmolarity >300 mOsm/l) and assess its impact on acute kidney injury (AKI) and outcome in hospitalised older adults.

Methods: This retrospective cohort study used data from a UK teaching hospital retrieved from the electronic database relating to all medical emergency admissions of patients aged ≥ 65 years admitted between 1st May 2011 and 31st October 2013. Using these data, Charlson comorbidity index (CCI), National Early Warning Score (NEWS), length of hospital stay (LOS) and mortality were determined. Osmolarity was calculated using the equation of Krahn and Khajuria.

Results: A total of 6632 patients were identified; 27% had HD, 39% of whom had AKI. HD was associated with a median (Q1, Q3) LOS of 5 (1, 12) days compared with 3 (1, 9) days in the euhydrated group, P < 0.001. Adjusted Cox-regression analysis demonstrated that patients with HD were four-times more likely to develop AKI 12-24 h after admission [Hazards Ratio (95% Confidence Interval) 4.5 (3.5-5.6), P < 0.001], and had 60% greater 30-day mortality [1.6 (1.4-1.9), P < 0.001], compared with those who were euhydrated.

Conclusion: HD is common in hospitalised older adults and is associated with increased LOS, risk of AKI and mortality. Further work is required to assess the validity of osmolality or osmolarity as an early predictor of AKI and the impact of HD on outcome prospectively.

Keywords: Acute kidney injury; Dehydration; Hypohydration; Older adults; Osmolarity; Serum biochemistry.

Fig. 1

Data selection methods. Patients admitted with any alcohol related condition including alcohol intoxication were excluded to reduce the risk of artificially high osmolar gap, the difference between measured serum osmolality and calculated osmolarity. Patients admitted with bleeding or those admitted to surgery were also excluded. Patients who did not have measured serum biochemistry required for the equation of Krahn & Khajuria within 12 h of admission were also excluded. First admission episode selected. If a patient was admitted multiple times over the study period. Formal laboratory serum glucose measurements were performed on blood sampled used for other biochemistry analysis.

Fig. 2

(top) Prevalence of dehydration with Charlson Comorbidity Index (age unadjusted). ‘None’ (no comorbidity, 0 points), ‘Mild’ (mild comorbidity, 1–2 points), ‘Moderate’ (moderate comorbidity, 3–4 points) and ‘Severe’ (severe comorbidity, ≥5 points). (bottom): Prevalence of dehydration with increasing age.

Fig. 3

Kaplan-Meier survival plot demonstrating the relationship between hydration status and mortality (P < 0.001). Dehydrated indicates hyperosmolar dehydration.