Heart rate is associated with mortality in patients undergoing continuous renal replacement therapy

Lee, Soo Jin; Lee, Yeon-Hee; Jang, Heejoon; Moon, Hongran; Kim, Yon Su; Han, Seung Seok

doi:10.23876/j.krcp.2017.36.3.250

Cited by 7 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these models did not focus on patients initiating CRRT for AKI. A few studies have identified risk factors of mortality in patients receiving CRRT [29,30]. Nevertheless, it is necessary to develop a mortality prediction model because a few clinical variables may not be sufficient to precisely predict patient outcome.…”

Section: Discussionmentioning

confidence: 99%

Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy

Kang

Kim

et al. 2020

Crit Care

Self Cite

View full text Add to dashboard Cite

Background Previous scoring models such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) and the Sequential Organ Failure Assessment (SOFA) scoring systems do not adequately predict mortality of patients undergoing continuous renal replacement therapy (CRRT) for severe acute kidney injury. Accordingly, the present study applies machine learning algorithms to improve prediction accuracy for this patient subset. Methods We randomly divided a total of 1571 adult patients who started CRRT for acute kidney injury into training (70%, n = 1094) and test (30%, n = 477) sets. The primary output consisted of the probability of mortality during admission to the intensive care unit (ICU) or hospital. We compared the area under the receiver operating characteristic curves (AUCs) of several machine learning algorithms with that of the APACHE II, SOFA, and the new abbreviated mortality scoring system for acute kidney injury with CRRT (MOSAIC model) results. Results For the ICU mortality, the random forest model showed the highest AUC (0.784 [0.744–0.825]), and the artificial neural network and extreme gradient boost models demonstrated the next best results (0.776 [0.735–0.818]). The AUC of the random forest model was higher than 0.611 (0.583–0.640), 0.677 (0.651–0.703), and 0.722 (0.677–0.767), as achieved by APACHE II, SOFA, and MOSAIC, respectively. The machine learning models also predicted in-hospital mortality better than APACHE II, SOFA, and MOSAIC. Conclusion Machine learning algorithms increase the accuracy of mortality prediction for patients undergoing CRRT for acute kidney injury compared with previous scoring models.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy

Kang

Kim

et al. 2020

Crit Care

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several factors are associated with high mortality during CRRT. The physical condition of patients undergoing CRRT is already poor, and most of them have multiple comorbidities including sepsis and problems with the heart and lungs . The seven significant variables that were selected for the MOSAIC model incorporated hypotension, respiratory failure, unconsciousness, electrolyte and acid–base imbalance, liver dysfunction, and adverse immune response.…”

Section: Discussionmentioning

confidence: 99%

“…The physical condition of patients undergoing CRRT is already poor, and most of them have multiple comorbidities including sepsis and problems with the heart and lungs. [23][24][25][26] The seven significant variables that were selected for the MOSAIC model incorporated hypotension, respiratory failure, unconsciousness, electrolyte and acidbase imbalance, liver dysfunction, and adverse immune response. However, serum creatinine was not a relevant factor in high mortality, which suggests that the original prediction models needed modification.…”

Section: Discussionmentioning

confidence: 99%

Development of a new mortality scoring system for acute kidney injury with continuous renal replacement therapy

et al. 2019

Self Cite

View full text Add to dashboard Cite

Aim On the basis of the worst outcomes of patients undergoing continuous renal replacement therapy (CRRT) in intensive care unit, previously developed mortality prediction model, Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) and the Sequential Organ Failure Assessment (SOFA) needs to be modified. Methods A total of 828 patients who underwent CRRT were recruited. Mortality prediction model was developed for the prediction of death within 7 days after starting the CRRT. Based on regression analysis, modified scores were assigned to each variable which were originally used in the APACHE II and SOFA scoring models. Additionally, a new abbreviated Mortality Scoring system for AKI with CRRT (MOSAIC) was developed after stepwise selection analysis. Results We used all the variables included in the APACHE II and SOFA scoring models. The prediction powers indicated by C‐statistics were 0.686 and 0.683 for 7‐day mortality by the APACHE II and SOFA systems, respectively. After modification of these models, the prediction powers increased up to 0.752 for the APACHE II and 0.724 for the SOFA systems. Using multivariate analysis, seven significant variables were selected in the MOSAIC model wherein its C‐statistic value was 0.772. These models also showed good performance with 0.720, 0.734 and 0.773 of C‐statistics in the modified APACHE II, modified SOFA and MOSAIC scoring models in the external validation cohort (n = 497). Conclusion The modified APACHE II/SOFA and newly developed MOSAIC models could be more useful tool for predicting mortality for patients receiving CRRT.

show abstract

“…AKI is an important risk factor for chronic kidney disease (CKD), rapid progression to end-stage renal disease (ESRD), development of cardiovascular events (stroke, myocardial infarction), disability, diminished quality of life, high cost of treatment and death [1, 2]. According to Hoste & Schurgers , 2-3 cases of AKI are estimated per 1000 persons [3]. Nash et al .…”

Section: Introductionmentioning

confidence: 99%

Factors associated with acute kidney injury recovery in a tertiary hospital in Ghana: a prospective study

Okyere¹,

Okyere²,

Ndanu³

et al. 2019

Pan Afr Med J

View full text Add to dashboard Cite

IntroductionAcute kidney injury (AKI) is a challenging problem in developing countries due to late presentation of its victims to health care facilities. Data on the pattern of AKI, its outcome and factors associated with its recovery is scanty in developing countries therefore impeding AKI management. Aim: to study AKI recovery rate and its associated factors.MethodsAn observational study conducted from September 2013 to June 2014 at Korle-Bu Teaching Hospital (KBTH). Participants were adults, admitted with AKI at KBTH. Kidney Disease: Improving Global Outcomes (KDIGO) criteria was used to diagnose and stage AKI.ResultsMean age (SD) of the participants was 41.9 (± 19.2) years. About a third of the patients (34.6%) were less than 29 years with 30-39 years and 40-60 years constituting 23.0% and 23.6% respectively. Females were in the majority (56.0%). AKI stages I, II and III accounted for 11.0%, 6.8% and 70.7% respectively. Majority, 82.2% of the patients recovered their kidney function. Stage III AKI was significantly associated with decreasing odds of recovery [OR = 0.4, 95%CI = 0.4-2.6, p = 0.002]. In addition, normal blood sodium was associated with recovery from AKI [OR, 95%CI = 2.3, (1.1-5.3), p = 0.043]. Almost half (45.5%) presented with fever whereas 32.5% and 22.5% presented with peripheral oedema and pulmonary oedema respectively.ConclusionThe study demonstrated high kidney function recovery following AKI. Dominant clinical features were fever, peripheral and pulmonary oedema. Advanced stage was associated with poor recovery whereas normal serum sodium level improves kidney function recovery.

show abstract

Heart rate is associated with mortality in patients undergoing continuous renal replacement therapy

Cited by 7 publications

References 26 publications

Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy

Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy

Development of a new mortality scoring system for acute kidney injury with continuous renal replacement therapy

Factors associated with acute kidney injury recovery in a tertiary hospital in Ghana: a prospective study

Contact Info

Product

Resources

About