Relationship between early serum sodium and potassium levels and AKI severity and prognosis in oliguric AKI patients

Self-powered freestanding multifunctional microneedle-based extended gate device for personalized health monitoring

Online monitoring of prognostic biomarkers is critically important when diagnosing disorders and assessing individuals' health, especially for chronic and infectious diseases. Despite this, current diagnosis techniques are time-consuming, labor-intensive, and performed offline. In this context, developing wearable devices for continuous measurements of multiple biomarkers from body fluids has considerable advantages including availability, rapidity, convenience, and minimal invasiveness over the conventional painful and time-consuming tools. However, there is still a significant challenge in powering these devices over an extended period, especially for applications that require continuous and long-term health monitoring. Herein, a new freestanding, wearable, multifunctional microneedle-based extended gate field effect transistor biosensor is fabricated for online detection of multiple biomarkers from the interstitial fluid including sodium, calcium, potassium, and pH along with excellent electrical response, reversibility, and precision. In addition, a hybrid powering system of triboelectric nanogenerator and solar cell was developed for creating a freestanding, closed-loop platform for continuous charging of the device's battery and integrated with an Internet of Things technology to broadcast the measurements online, suggesting a stand-alone, stable multifunctional tool which paves the way for advanced practical personalized health monitoring and diagnosis.

Exploiting Machine Learning Technologies to Study the Compound Effects of Serum Creatinine and Electrolytes on the Risk of Acute Kidney Injury in Intensive Care Units

Assessing the risk of acute kidney injury (AKI) has been a challenging issue for clinicians in intensive care units (ICUs). In recent years, a number of studies have been conducted to investigate the associations between several serum electrolytes and AKI. Nevertheless, the compound effects of serum creatinine, blood urea nitrogen (BUN), and clinically relevant serum electrolytes have yet to be comprehensively investigated. Accordingly, we initiated this study aiming to develop machine learning models that illustrate how these factors interact with each other. In particular, we focused on ICU patients without a prior history of AKI or AKI-related comorbidities. With this practice, we were able to examine the associations between the levels of serum electrolytes and renal function in a more controlled manner. Our analyses revealed that the levels of serum creatinine, chloride, and magnesium were the three major factors to be monitored for this group of patients. In summary, our results can provide valuable insights for developing early intervention and effective management strategies as well as crucial clues for future investigations of the pathophysiological mechanisms that are involved. In future studies, subgroup analyses based on different causes of AKI should be conducted to further enhance our understanding of AKI.

Serum Potassium Disorders Predict Subsequent Kidney Injury: A Retrospective Observational Cohort Study of Hospitalized Patients

INTRODUCTION

Electrolyte disorders are common findings in kidney diseases and might represent a useful biomarker preceding kidney injury. Serum potassium [K+] imbalance is still poorly investigated for association with acute kidney injury (AKI), and most evidence came from intensive care units. The aim of our study was to comprehensively investigate this association in a large, unselected cohort of hospitalized patients.

METHODS

We performed a retrospective observational cohort study on the inpatient population admitted to Fondazione Policlinico Universitario A. Gemelli IRCCS between January 1, 2010 and December 31, 2014, with inclusion of adult patients with at least 2 [K+] and 3 serum creatinine measurements who did not develop AKI during an initial 10-day window. The outcome of interest was in-hospital AKI. The exposures of interest were [K+] fluctuations and hypo (HoK) and hyperkalemia (HerK). [K+] variability was evaluated using the coefficient of variation. Cox proportional hazards regression models were used to obtain hazard ratios and 95% confidence intervals of the association between the exposures of interest and development of AKI.

RESULTS

About 21,830 hospital admissions from 18,836 patients were included in our study. During a median follow-up of 5 (interquartile range [IQR] 7) days, AKI was observed in 555 hospital admissions (2.9%); median time for AKI development was 5 (IQR 7) days. Higher [K+] variability was independently associated with increased risk of AKI with a statistically significant linear trend across groups (p value = 0.012). A significantly higher incidence of AKI was documented in patients with HerK compared with normokalemia. No statistically significant difference was observed between HoK and HerK (p value = 0.92).

CONCLUSION

[K+] abnormalities including fluctuations even within the normal range are associated with development of AKI.

Visual Analytics for Predicting Disease Outcomes Using Laboratory Test Results

Laboratory tests play an essential role in the early and accurate diagnosis of diseases. In this paper, we propose SUNRISE, a visual analytics system that allows the user to interactively explore the relationships between laboratory test results and a disease outcome. SUNRISE integrates frequent itemset mining (i.e., Eclat algorithm) with extreme gradient boosting (XGBoost) to develop more specialized and accurate prediction models. It also includes interactive visualizations to allow the user to interact with the model and track the decision process. SUNRISE helps the user probe the prediction model by generating input examples and observing how the model responds. Furthermore, it improves the user’s confidence in the generated predictions and provides them the means to validate the model’s response by illustrating the underlying working mechanism of the prediction models through visualization representations. SUNRISE offers a balanced distribution of processing load through the seamless integration of analytical methods with interactive visual representations to support the user’s cognitive tasks. We demonstrate the usefulness of SUNRISE through a usage scenario of exploring the association between laboratory test results and acute kidney injury, using large provincial healthcare databases from Ontario, Canada.

Serum potassium levels and prognosis in HBV-associated decompensated cirrhosis

Background

Serum potassium disorders are commonly seen in patients with advanced cirrhosis and have a detrimental effect on clinical outcome, but its role in HBV‐related decompensated cirrhosis (DeCi) is remained to be illustrated. We aim to assess the effects of serum potassium on outcomes in HBV‐DeCi patients.

Methods

Retrospective study included 155 subjects. Multivariate analysis was used to determine the independent prognostic factor. Predictive ability of mortality for variables was determined using the receiver operating characteristics curves.

Results

The 30‐day in‐hospital mortality was 12.9%. Serum potassium levels differed markedly between survivors and non‐survivors. On multivariate analysis, Model for End‐Stage Liver Disease (MELD) score and serum potassium level were identified as independent predictors of outcomes in HBV‐DeCi patients. The combination of serum potassium and MELD score could improve prognostic accuracy in these patients.

Conclusions

Our findings suggest that serum potassium is an effective predictor for poor outcomes in HBV‐DeCi patients.