Hyperchloremia is associated with aute kidney injury in critical ill patients: an analysis of the MIMIC-III database

2020 ◽  
Author(s):  
Jie Gu ◽  
Tingting Zuo ◽  
Qingqing Zhu ◽  
Hui Chen ◽  
Yanbin Chen ◽  
...  
Keyword(s):  
Intensive Care ◽  
Medical Information ◽  
Gastrointestinal Disease ◽  
Kidney Injury ◽  
Cerebral Disease ◽  
Icu Patients ◽  
Increased Risk ◽  
Critical Ill Patients ◽  
Mimic Iii ◽  
Critical Ill

Abstract Objective: Balanced fluid with no critical increase of chloride in serum was recommended in clinic. Whether hyperchloremia could make a difference for intensive care unit (ICU) patients with a higher acute kidney injury (AKI) occurrence remains controversial.Methods: The Medical Information Mart for Intensive Care III (MIMIC-III) database was searched to identify patients hyperchloremia or non-hyperchloremia, and relationship between level of chloride and AKI incidence was analyzed using the univariate and multivariate logistic regression. Patients were divided into four disease subgroups based on the diagnosis at admission: cardiac, cerebral, gastrointestinal, respiratory. The association between maximum chloride (chloride_max) and incidence of AKI in each subgroup was evaluated using the Lowess Smoothing technique. Receiver operating characteristic curves were applied to analyze the diagnostic value of hyperchloremia (chloride_max>110mmol/L) in these four subgroup patients.Results: A total of 34,617 patients were included in our study, of which 12667 patients (36.6%) was diagnosed with hyperchloremia. The risk of incidence of AKI was increased in the hyperchloremia group. As the higher level of hyperchlorimia, the bigger adjusted odds ratio (OR) presented in terms of AKI, with the OR increasing from 1.13 (95%CI 1.06-1.21; P<0.001) to 4.09 (95%CI 3.04-5.52; P<0.001). Normal level of chloride (95-110mmol/L) was associated with the lower incidence of AKI rate compared to the hypochloremia (<95mmol/L) or the hyperchloremia (>110mmol/L) in any subgroup of cerebral, cardiac, respiratory and gastrointestinal disease. The diagnostic performance was good for cerebral disease (AUC=0.617), cardiac disease (AUC=0.636), respiratory disease (AUC=0.623) and gastrointestinal disease (AUC=0.633). The optimal cut-off value in terms of chloride_max for diagnosing AKI was 116mmol/L for the subgroup of cerebral, respiratory and gastrointestinal diseases, and 115 mmol/L for cardiac patients.Conclusion: Hyperchloremia was associated with increased risk adjusted AKI incidence among critical ill patients. For ICU patients with cerebral, gastrointestinal and respiratory admission diagnose, the predictive threshold was at 116mmoL/L, and cardiac diagnose was at 115 mmol/L.

scholarly journals Early Coagulation Disorder Is Associated With an Increased Risk of Atrial Fibrillation in Septic Patients

2021 ◽  
Vol 8 ◽  
Author(s):  
Yunxiang Long ◽  
Yingmu Tong ◽  
Runchen Miao ◽  
Rong Fan ◽  
Xiangqi Cao ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Intensive Care ◽  
Medical Information ◽  
International Normalized Ratio ◽  
Coagulation Disorder ◽  
Increased Risk ◽  
Coagulation Tests ◽  
Independent Risk Factors ◽  
The Relationship ◽  
Mimic Iii

Background: Atrial fibrillation (AF) and coagulation disorder, two common complications of sepsis, are associated with the mortality. However, the relationship between early coagulation disorder and AF in sepsis remains elusive. This study aimed to evaluate the interaction between AF and early coagulation disorder on mortality.Methods: In this retrospective study, all data were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Septic patients with coagulation tests during the first 24 h after admission to intensive care units (ICUs) meeting study criteria were included in the analysis. Early coagulation disorder is defined by abnormalities in platelet count (PLT), international normalized ratio (INR) and activated partial thromboplastin time (APTT) within the first 24 h after admission, whose score was defined with reference to sepsis-induced coagulopathy (SIC) and coagulopathy. Patients meeting study criteria were divided into AF and non-AF groups.Results: In total, 7,528 septic patients were enrolled, including 1,243 (16.51%) with AF and 5,112 (67.91%) with early coagulation disorder. Compared with patients in the non-AF group, patients in the AF group had higher levels of INR and APTT (P &lt; 0.001). Multivariable logistic regression analyses showed that stroke, early coagulation disorder, age, gender, congestive heart failure (CHF), chronic pulmonary disease, renal failure, and chronic liver disease were independent risk factors for AF. In addition, AF was related to in-hospital mortality and 90-day mortality. In the subgroup analysis stratified by the scores of early coagulation disorder, AF was associated with an increased risk of 90-day mortality when the scores of early coagulation disorder were 1 or 2 and 3 or 4.Conclusion: In sepsis, coagulation disorder within the first 24 h after admission to the ICUs is an independent risk factor for AF. The effect of AF on 90-day mortality varies with the severity of early coagulation disorder.

scholarly journals Association Between Base Excess and Mortality Among Patients in ICU With Acute Kidney Injury

2021 ◽  
Vol 8 ◽  
Author(s):  
Yi Cheng ◽  
You Zhang ◽  
Boxiang Tu ◽  
Yingyi Qin ◽  
Xin Cheng ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Intensive Care ◽  
Medical Information ◽  
Proportional Hazards ◽  
Base Excess ◽  
Proportional Hazards Model ◽  
Kidney Injury ◽  
Cox Proportional Hazards ◽  
Cox Proportional Hazards Model ◽  
Icu Patients

Objective: This study aimed to explore the association between base excess (BE) and the risk of 30-day mortality among patients with acute kidney injury (AKI) in the intensive care unit (ICU).Methods: This retrospective study included patients with AKI from the Medical Information Mart for Intensive Care (MIMIC)-IV database. We used a multivariate Cox proportional-hazards model to obtain the hazard ratio (HR) for the risk of 30-day mortality among patients with AKI. Furthermore, we utilized a Cox proportional-hazard model with restricted cubic splines (RCS) to explore the potential non-linear associations.Results: Among the 14,238 ICU patients with AKI, BE showed a U-shaped relationship with risk of 30-day mortality for patients with AKI, and higher or lower BE values could increase the risk. Compared with normal base excess (−3~3 mEq/L), patients in different groups (BE ≤ −9 mEq/L, −9 mEq/L &lt; BE ≤ −3 mEq/L, 3 mEq/L &lt; BE ≤ 9 mEq/L, and BE &gt; 9 mEq/L) had different HRs for mortality: 1.57 (1.40, 1.76), 1.26 (1.14, 1.39), 0.97 (0.83, 1.12), 1.53 (1.17, 2.02), respectively. The RCS analyses also showed a U-shaped curve between BE and the 30-day mortality risk.Conclusion: Our results suggest that higher and lower BE in patients with AKI would increase the risk of 30-day mortality. BE measured at administration could be a critical prognostic indicator for ICU patients with AKI and provide guidance for clinicians.

scholarly journals Predicting acute kidney injury in critically ill patients using comorbid conditions utilizing machine learning

2020 ◽  
Author(s):  
Khaled Shawwa ◽  
Erina Ghosh ◽  
Stephanie Lanius ◽  
Emma Schwager ◽  
Larry Eshelman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Intensive Care ◽  
Mayo Clinic ◽  
Medical Information ◽  
Kidney Injury ◽  
Feature Model ◽  
Receiver Operating Curve ◽  
Gradient Boosting ◽  
Mimic Iii

Abstract Background Acute kidney injury (AKI) carries a poor prognosis. Its incidence is increasing in the intensive care unit (ICU). Our purpose in this study is to develop and externally validate a model for predicting AKI in the ICU using patient data present prior to ICU admission. Methods We used data of 98 472 adult ICU admissions at Mayo Clinic between 1 January 2005 and 31 December 2017 and 51 801 encounters from Medical Information Mart for Intensive Care III (MIMIC-III) cohort. A gradient-boosting model was trained on 80% of the Mayo Clinic cohort using a set of features to predict AKI acquired in the ICU. Results AKI was identified in 39 307 (39.9%) encounters in the Mayo Clinic cohort. Patients who developed AKI in the ICU were older and had higher ICU and in-hospital mortality compared to patients without AKI. A 30-feature model yielded an area under the receiver operating curve of 0.690 [95% confidence interval (CI) 0.682–0.697] in the Mayo Clinic cohort set and 0.656 (95% CI 0.648–0.664) in the MIMIC-III cohort. Conclusions Using machine learning, AKI among ICU patients can be predicted using information available prior to admission. This model is independent of ICU information, making it valuable for stratifying patients at admission.

scholarly journals Hyperchloremia in critically ill patients: association with outcomes and prediction using electronic health record data

2020 ◽  
Vol 20 (S14) ◽  
Author(s):  
Pete Yeh ◽  
Yiheng Pan ◽  
L. Nelson Sanchez-Pinto ◽  
Yuan Luo
Keyword(s):  
Intensive Care ◽  
Supervised Learning ◽  
Medical Information ◽  
Kidney Injury ◽  
Learning Model ◽  
Multiple Organ ◽  
Icu Mortality ◽  
Electronic Health Record Data ◽  
Icu Patients ◽  
Clinical Records

Abstract Background Increased chloride in the context of intravenous fluid chloride load and serum chloride levels (hyperchloremia) have previously been associated with increased morbidity and mortality in select subpopulations of intensive care unit (ICU) patients (e.g patients with sepsis). Here, we study the general ICU population of the Medical Information Mart for Intensive Care III (MIMIC-III) database to corroborate these associations, and propose a supervised learning model for the prediction of hyperchloremia in ICU patients. Methods We assessed hyperchloremia and chloride load and their associations with several outcomes (ICU mortality, new acute kidney injury [AKI] by day 7, and multiple organ dysfunction syndrome [MODS] on day 7) using regression analysis. Four predictive supervised learning classifiers were trained to predict hyperchloremia using features representative of clinical records from the first 24h of adult ICU stays. Results Hyperchloremia was shown to have an independent association with increased odds of ICU mortality, new AKI by day 7, and MODS on day 7. High chloride load was also associated with increased odds of ICU mortality. Our best performing supervised learning model predicted second-day hyperchloremia with an AUC of 0.76 and a number needed to alert (NNA) of 7—a clinically-actionable rate. Conclusions Our results support the use of predictive models to aid clinicians in monitoring for and preventing hyperchloremia in high-risk patients and offers an opportunity to improve patient outcomes.

scholarly journals Colonization of central venous catheter in the intensive care units at the Institute of Cardiovascular Disease "Dedinje": One year study

2005 ◽  
Vol 52 (3) ◽  
pp. 33-37
Author(s):  
Ivana Cirkovic ◽  
Vera Mijac ◽  
Milena Svabic-Vlahovic ◽  
S. Dukic ◽  
I. Ilic ◽  
...  
Keyword(s):  
Intensive Care ◽  
Intensive Care Units ◽  
Antimicrobial Agents ◽  
Microbial Colonization ◽  
Central Venous ◽  
Candida Spp ◽  
Icu Patients ◽  
Gram Negative ◽  
Microbiological Methods ◽  
Increased Risk

Objectives: The application of Central Venous Catheters (CVC) is associated with increased risk of microbial colonization and infection. The aim of present study was to assess the frequency of pathogens colonizing CVC and to determine their susceptibility pattern to various antimicrobial agents. Materials and methods: A total of 253 samples of CVC from intensive care units (ICU) patients were received for culture during 2003. All microorganisms were identified by standard microbiological methods and the susceptibility to antimicrobial agents was determined according to NCCLS recommendations. Results: A total of 184 (72.7%) cultures were positive and 223 pathogens were isolated. Coagulase negative staphylococci (CNS) were the dominant isolates (24.7%), followed by Enterobacter spp. (12.1%), Pseudomonas spp. (11.7%), Enterococcus spp. (9.9%), Klebsiella spp. (8.6%), Candida spp. (7.6%), Acinetobacter spp. (7.6%), other Gram negative nonfermentative bacilli (5.8%), Serratia spp. (4.5%), Staphylococcus aureus (2.6%), Proteus mirabilis (2.2%), E. coli (1.8%) and Citrobacter spp. (0.9%). Meropenem (84.5%) and vancomycin (100%) remain the most effective antimicrobial agents against Gram negative and Gram positive bacteria, respectively. Conclusion: Gram negative bacilli and CNS are the commonest microorganisms colonizing CVC from ICU patients. The increasing resistance of the bacteria to antimicrobial agents is the major problem in spite of restricted policy of using antimicrobial agents in ICU.

scholarly journals Secondary Bacterial Infections in Critical Ill Patients With Coronavirus Disease 2019

2020 ◽  
Vol 7 (6) ◽  
Author(s):  
Yiqi Fu ◽  
Qing Yang ◽  
Min Xu ◽  
Haishen Kong ◽  
Hongchao Chen ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Nosocomial Infection ◽  
Bacterial Infection ◽  
Critically Ill Patients ◽  
Bacterial Infections ◽  
Critical Ill Patients ◽  
Prevention Of Nosocomial Infection ◽  
Critical Ill

Secondary bacterial infections occurred in 13.9% (5 of 36) of critical ill patients with coronavirus disease 2019. All 5 patients had been admitted to intensive care unit and received mechanical ventilation before developing bacterial infection. Active surveillance of culture should be performed for critically ill patients. Prevention of nosocomial infection should to be taken seriously.

scholarly journals Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic healthcare data from MIMIC-III and Bristol, UK

BMJ Open ◽  
2019 ◽  
Vol 9 (3) ◽  
pp. e025925 ◽  
Author(s):  
Christopher J McWilliams ◽  
Daniel J Lawson ◽  
Raul Santos-Rodriguez ◽  
Iain D Gilchrist ◽  
Alan Champneys ◽  
...  
Keyword(s):  
Intensive Care ◽  
Decision Support ◽  
Medical Information ◽  
Learning Algorithm ◽  
Adverse Outcomes ◽  
Royal Infirmary ◽  
Automated Method ◽  
Improved Performance ◽  
Discharge Criteria ◽  
Mimic Iii

ObjectiveThe primary objective is to develop an automated method for detecting patients that are ready for discharge from intensive care.DesignWe used two datasets of routinely collected patient data to test and improve on a set of previously proposed discharge criteria.SettingBristol Royal Infirmary general intensive care unit (GICU).PatientsTwo cohorts derived from historical datasets: 1870 intensive care patients from GICU in Bristol, and 7592 from Medical Information Mart for Intensive Care (MIMIC)-III.ResultsIn both cohorts few successfully discharged patients met all of the discharge criteria. Both a random forest and a logistic classifier, trained using multiple-source cross-validation, demonstrated improved performance over the original criteria and generalised well between the cohorts. The classifiers showed good agreement on which features were most predictive of readiness-for-discharge, and these were generally consistent with clinical experience. By weighting the discharge criteria according to feature importance from the logistic model we showed improved performance over the original criteria, while retaining good interpretability.ConclusionsOur findings indicate the feasibility of the proposed approach to ready-for-discharge classification, which could complement other risk models of specific adverse outcomes in a future decision support system. Avenues for improvement to produce a clinically useful tool are identified.

scholarly journals Utilization of Deep Learning for Subphenotype Identification in Sepsis-Associated Acute Kidney Injury

2020 ◽  
Vol 15 (11) ◽  
pp. 1557-1565 ◽  
Author(s):  
Kumardeep Chaudhary ◽  
Akhil Vaid ◽  
Áine Duffy ◽  
Ishan Paranjpe ◽  
Suraj Jaladanki ◽  
...  
Keyword(s):  
Intensive Care ◽  
Deep Learning ◽  
Medical Information ◽  
Tertiary Care ◽  
Vital Signs ◽  
Kidney Injury ◽  
The United States ◽  
Care Hospital ◽  
Electronic Health Record Data ◽  
Electronic Health

Background and objectivesSepsis-associated AKI is a heterogeneous clinical entity. We aimed to agnostically identify sepsis-associated AKI subphenotypes using deep learning on routinely collected data in electronic health records.Design, setting, participants, & measurementsWe used the Medical Information Mart for Intensive Care III database, which consists of electronic health record data from intensive care units in a tertiary care hospital in the United States. We included patients ≥18 years with sepsis who developed AKI within 48 hours of intensive care unit admission. We then used deep learning to utilize all available vital signs, laboratory measurements, and comorbidities to identify subphenotypes. Outcomes were mortality 28 days after AKI and dialysis requirement.ResultsWe identified 4001 patients with sepsis-associated AKI. We utilized 2546 combined features for K-means clustering, identifying three subphenotypes. Subphenotype 1 had 1443 patients, and subphenotype 2 had 1898 patients, whereas subphenotype 3 had 660 patients. Subphenotype 1 had the lowest proportion of liver disease and lowest Simplified Acute Physiology Score II scores compared with subphenotypes 2 and 3. The proportions of patients with CKD were similar between subphenotypes 1 and 3 (15%) but highest in subphenotype 2 (21%). Subphenotype 1 had lower median bilirubin levels, aspartate aminotransferase, and alanine aminotransferase compared with subphenotypes 2 and 3. Patients in subphenotype 1 also had lower median lactate, lactate dehydrogenase, and white blood cell count than patients in subphenotypes 2 and 3. Subphenotype 1 also had lower creatinine and BUN than subphenotypes 2 and 3. Dialysis requirement was lowest in subphenotype 1 (4% versus 7% [subphenotype 2] versus 26% [subphenotype 3]). The mortality 28 days after AKI was lowest in subphenotype 1 (23% versus 35% [subphenotype 2] versus 49% [subphenotype 3]). After adjustment, the adjusted odds ratio for mortality for subphenotype 3, with subphenotype 1 as a reference, was 1.9 (95% confidence interval, 1.5 to 2.4).ConclusionsUtilizing routinely collected laboratory variables, vital signs, and comorbidities, we were able to identify three distinct subphenotypes of sepsis-associated AKI with differing outcomes.

Renal injury study in critical ill patients in accordance with the new definition given by the Acute Kidney Injury Network

2011 ◽  
Vol 26 (2) ◽  
pp. 206-212 ◽  
Author(s):  
Nelson Javier Fonseca Ruiz ◽  
Diana Paola Cuesta Castro ◽  
Ana Milena Mesa Guerra ◽  
Francisco Molina Saldarriaga ◽  
Juan Diego Montejo Hernández
Keyword(s):  
Acute Kidney Injury ◽  
Renal Injury ◽  
Kidney Injury ◽  
Acute Kidney Injury Network ◽  
Critical Ill Patients ◽  
Critical Ill

Factors Associated with Risk and Prognosis of Intensive Care Unit Admission in Patients with Acute Myeloid Leukemia: A Danish Nationwide Cohort Study

Blood ◽  
2019 ◽  
Vol 134 (Supplement_1) ◽  
pp. 4783-4783
Author(s):  
Cecilie Velsoe Maeng ◽  
Christian Fynbo Christiansen ◽  
Kathleen Dori Liu ◽  
Lene Sofie Granfeldt Oestgaard
Keyword(s):  
Intensive Care ◽  
High Risk ◽  
Myeloid Leukemia ◽  
Risk Group ◽  
Remission Induction ◽  
First Year ◽  
Icu Patients ◽  
Icu Admission ◽  
Increased Risk ◽  
Acute Myeloid

Significance Patients with acute myeloid leukemia (AML) are at high risk of critical illness requiring admission to the intensive care unit (ICU) due to both disease- and treatment-related complications. A better understanding of risk factors for ICU admission and prognosis may help with prevention of life-threatening complications and informed decision-making when treating AML patients. Methods This study included all adult Danish AML patients, who received remission-induction chemotherapy alone or in combination with allogeneic stem cell transplantation from 2005 to 2016. The cohort was identified using the Danish Acute Leukemia Registry (DNLR) and information on ICU admission was obtained from the Danish Intensive Care Database. We examined risk of ICU admission within 1 and 3 years of diagnosis considering competing risk of death and investigated a number of possible risk factors for ICU admission. We computed 1-, 3-, and 5-year mortality from time of ICU admission and in the matched non-ICU comparison group using a risk set matching (1:1) on time since diagnosis, sex, and age. Finally, we used the pseudo-value approach to compute the relative risk (RR) of death in the ICU admitted cohort compared to the matched cohort. We adjusted for ECOG/WHO performance status (PS), year of diagnosis, cytogenetic risk group, number of comorbidities, and secondary/therapy-related AML. Results A total of 1383 AML patients were included in the study. The median follow-up time was 1.65 (IQR: 0.60-4.36) years. The risk of ICU admission within 1 year of AML diagnosis was 22.7%, and the risk within 3 years was 28.1%. Median time to ICU was 59 (IQR: 15-272) days. Male sex was associated with increased risk of ICU admission after 1 year (adjusted RR: 1.26, 95% CI: 1.01-1.57) and PS >1 was associated with an increased risk after both 1 year (adjusted RR: 1.74, 95% CI: 1.33-1.30) and 3 years (adjusted RR: 1.54, 95% CI: 1.22-1.96). Other factors listed in Table 1 (age, comorbidity, cytogenetic risk group, secondary or therapy-related AML, and year of diagnosis) were not associated with increased risk of ICU admission. In AML patients admitted to the ICU, the 1-year mortality from time of ICU admission was 69.2%, compared to a 1-year mortality rate of 31.0% in the matched non-ICU patients (adjusted RR: 3.25, 95% CI: 2.56-4.12). Long-term mortality was increased in ICU patients; 3-year mortality was 82.1% compared to 49.7% (adjusted RR: 2.43, 95% CI: 1.97-3.01), and the 5-year mortality was 83.1% compared to 60.6%, (adjusted RR: 2.12, 95% CI: 1.70-2.66). Conclusion In this national population-based cohort study, more than one fourth of AML patients treated with remission-induction chemotherapy were admitted to an ICU within 3 years of diagnosis with the majority of ICU admissions occurring within the first year. ICU admission was associated with high mortality, especially within the first year after admission. The risk of mortality decreased over time but remained increased 3 and 5 years after admission compared to the matched cohort. Early monitoring and management of high-risk patients may be effective in preventing ICU admissions and PS may serve as a possible tool to identify patients at high risk of ICU admission. Disclosures No relevant conflicts of interest to declare.

Sign in / Sign up

Export Citation Format

Share Document