Serum Potassium Levels at Hospital Discharge and One-Year Mortality among Hospitalized Patients

Distinct phenotypes of hospitalized patients with hyperkalemia by machine learning consensus clustering and associated mortality risks

BACKGROUND

Hospitalized patients with hyperkalemia are heterogeneous, and cluster approaches may identify specific homogenous groups. This study aimed to cluster patients with hyperkalemia on admission using unsupervised machine learning (ML) consensus clustering approach, and to compare characteristics and outcomes among these distinct clusters.

METHODS

Consensus cluster analysis was performed in 5133 hospitalized adult patients with admission hyperkalemia, based on available clinical and laboratory data. The standardized mean difference was used to identify each cluster's key clinical features. The association of hyperkalemia clusters with hospital and 1-year mortality was assessed using logistic and Cox proportional hazard regression.

RESULTS

Three distinct clusters of hyperkalemia patients were identified using consensus cluster analysis: 1661 (32%) in cluster 1, 2455 (48%) in cluster 2 and 1017 (20%) in cluster 3. Cluster 1 was mainly characterized by older age, higher serum chloride and acute kidney injury (AKI), but lower estimated glomerular filtration rate (eGFR), serum bicarbonate and hemoglobin. Cluster 2 was mainly characterized by higher eGFR, serum bicarbonate and hemoglobin, but lower comorbidity burden, serum potassium and AKI. Cluster 3 was mainly characterized by higher comorbidity burden, particularly diabetes and end-stage kidney disease, AKI, serum potassium, anion gap, but lower eGFR, serum sodium, chloride and bicarbonate. Hospital and 1-year mortality risk was significantly different among the three identified clusters, with highest mortality in cluster 3, followed by cluster 1 and then cluster 2.

CONCLUSION

In a heterogeneous cohort of hyperkalemia patients, three distinct clusters were identified using unsupervised ML. These three clusters had different clinical characteristics and outcomes.

Subtyping hospitalized patients with hypokalemia by machine learning consensus clustering and associated mortality risks

Background

Hospitalized patients with hypokalemia are heterogeneous and cluster analysis, an unsupervised machine learning methodology, may discover more precise and specific homogeneous groups within this population of interest. Our study aimed to cluster patients with hypokalemia at hospital admission using an unsupervised machine learning approach and assess the mortality risk among these distinct clusters.

Methods

We performed consensus clustering analysis based on demographic information, principal diagnoses, comorbidities and laboratory data among 4763 hospitalized adult patients with admission serum potassium ≤3.5 mEq/L. We calculated the standardized mean difference of each variable and used the cutoff of ±0.3 to identify each cluster's key features. We assessed the association of the hypokalemia cluster with hospital and 1-year mortality.

Results

Consensus cluster analysis identified three distinct clusters that best represented patients’ baseline characteristics. Cluster 1 had 1150 (32%) patients, cluster 2 had 1344 (28%) patients and cluster 3 had 1909 (40%) patients. Based on the standardized difference, patients in cluster 1 were younger, had less comorbidity burden but higher estimated glomerular filtration rate (eGFR) and higher hemoglobin; patients in cluster 2 were older, more likely to be admitted for cardiovascular disease and had higher serum sodium and chloride levels but lower eGFR, serum bicarbonate, strong ion difference (SID) and hemoglobin, while patients in cluster 3 were older, had a greater comorbidity burden, higher serum bicarbonate and SID but lower serum sodium, chloride and eGFR. Compared with cluster 1, cluster 2 had both higher hospital and 1-year mortality, whereas cluster 3 had higher 1-year mortality but comparable hospital mortality.

Conclusion

Our study demonstrated the use of consensus clustering analysis in the heterogeneous cohort of hospitalized hypokalemic patients to characterize their patterns of baseline clinical and laboratory data into three clinically distinct clusters with different mortality risks.

Epidemiology, prognosis and management of potassium disorders in Covid-19

Coronavirus disease (Covid-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is currently the largest health crisis facing most countries. Several factors have been linked with a poor prognosis for this disease, including demographic factors, pre-existing comorbidities and laboratory parameters such as white blood cell count, D-dimer, C-reactive protein, albumin, lactate dehydrogenase, creatinine and electrolytes. Electrolyte abnormalities particularly potassium disorders are common among Covid-19 patients. Based on our pooled analysis, hypokalemia and hyperkalemia occur in 24.3% and 4.15% of Covid-19 patients, respectively. Potassium level deviation from the normal range may increase the chances of unfavorable outcomes and even death. Therefore, this article reviewed the epidemiology of potassium disorders and explained how hypokalemia and hyperkalemia are capable of deteriorating cardiac outcomes and the prognosis of Covid-19 for infected patients. The article finishes by highlighting some important considerations in the management of hypokalemia and hyperkalemia in these patients.

Normal range of serum potassium, prevalence of dyskalaemia and associated factors in Chinese older adults: a cross-sectional study

OBJECTIVE

To investigate the normal range of serum potassium, the prevalence of dyskalaemia and the associated factors in Chinese older adults.

DESIGN

A cross-sectional study conducted from September 2017 to March 2018.

SETTING

Forty-eight community elderly care facilities in four regions in northern China.

PARTICIPANTS

A total of 1266 (308 apparently healthy and 958 unhealthy) participants 55 years or older and with fasting serum potassium measured.

MAIN OUTCOME MEASURES AND METHODS

Serum potassium <3.5 mEq/L and >5.5 mEq/L (guidelines definition) and <2.5th and >97.5th percentiles of the distribution among healthy participants (our study definition) were both used to define hypokalaemia and hyperkalaemia, respectively. Multivariable generalised estimating equation models were used to adjust for clustering effect in the analyses of factors associated with risk of dyskalaemia and with variations in serum potassium.

RESULTS

The study participants had a mean age of 70 (8.8) years. Among apparently healthy participants, the 2.5th and 97.5th percentiles of serum potassium distribution were 3.7 mEq/L and 5.3 mEq/L, respectively. Using the study definition, the prevalence of hyperkalaemia was 4.3% (95% CI 3.2% to 5.4%) and of hypokalaemia was 4.0% (95% CI 2.9% to 5.1%). Multivariable analyses showed that risk of hyperkalaemia was associated with unhealthy conditions (OR=2.21; 95% CI 1.17 to 4.18); risk of hypokalaemia was associated with unhealthy conditions (OR=2.56; 95% CI 1.05 to 6.23), older age (OR=1.70 per 10-year increase; 95% CI 1.04 to 2.79) and region (OR=16.87; 95% CI 6.41 to 44.38); and higher serum potassium was associated with male gender (mean difference (MD)=0.12; 95% CI 0.05 to 0.19) and estimated glomerular filtration rate <60 mL/min/1.73 m² (MD=0.29; 95% CI 0.12 to 0.46). Using the guidelines definition, hyperkalaemia accounted for 2.7% (1.8%, 3.6%) and hypokalaemia 1.8% (1.1%, 2.5%). Analyses of the associated factors showed similar trends.

CONCLUSIONS

The study suggested a narrower normal range of serum potassium for defining dyskalaemia, which was common in older Chinese and more prevalent in unhealthy ones.

TRIAL REGISTRATION NUMBER

NCT03290716; Pre-results.

Hospitalizations for Acute Salicylate Intoxication in the United States

BACKGROUND

The objective of this study was to describe inpatient prevalence, characteristics, outcomes, and resource use for acute salicylate intoxication hospitalizations in the United States.

METHODS

A total of 13,805 admissions with a primary diagnosis of salicylate intoxication from 2003 to 2014 in the National Inpatient Sample database were analyzed. Prognostic factors for in-hospital mortality were determined using multivariable logistic regression.

RESULTS

The overall inpatient prevalence of salicylate intoxication among hospitalized patients was 147.8 cases per 1,000,000 admissions in the United States. The average age was 34 ± 19 years. Of these, 35.0% were male and 65.4% used salicylate for suicidal attempts. Overall, 6% required renal replacement therapy. The most common complications of salicylate intoxication were electrolyte and acid-base disorders, including hypokalemia (25.4%), acidosis (19.1%), and alkalosis (11.1%). Kidney failure (9.3%) was the most common observed organ dysfunction. In-hospital mortality was 1.0%. Increased in-hospital mortality was associated with age ≥30, Asian/Pacific Islander race, diabetes mellitus, hyponatremia, ventricular arrhythmia, kidney failure, respiratory failure, and neurological failure, while decreased in-hospital mortality was associated with African American and Hispanic race.

CONCLUSION

hospitalization for salicylate intoxication occurred in 148 per 1,000,000 admissions in the United States. Several factors were associated with in-hospital mortality.