Seventy-Two Hour Mortality Prediction Model in Patients with Diabetic Ketoacidosis: A Retrospective Cohort Study

Abstract

Objective. This study aims to identify predictors of 72-hour mortality in patients with diabetic ketoacidosis (DKA).Methodology. In this retrospective cohort study, data were obtained from medical records of adult patients with DKA in Cipto Mangunkusumo General Hospital from January 2011 to June 2017. Associations of predictors (age, type of diabetes, history of DKA, comorbidities, level of consciousness, renal function, bicarbonate, potassium, lactate, betahydroxybutyrate levels, and anion gap status) and 72-hour mortality were analyzed. The mortality prediction model was formulated by dividing the coefficient B by the standard error for all variables with p<0.05 in the multivariate analysis.Results. Eighty-six of 301 patients did not survive 72 hours after hospital admission. Comorbidities (HR 2.407; 95% CI 1.181-4.907), level of consciousness (HR 10.345; 95% CI 4.860-22.019), history of DKA (HR 2.126; 95% CI 1.308-3.457), and lactate level (HR 5.585; 95% CI 2.966-10.519) were significant predictors from multivariate analysis and were submitted to the prediction model. The prediction model had good performance. Patients with total score less than 3 points were at 15.41 % risk of mortality, 3 -4 points were 78.01% and 5 -6 points were 98.22% risk of mortality. Conclusion.The 72-hour mortality rate in Cipto Mangunkusumo General Hospital was 28.57%. The mortality prediction model had a good performance and consisted of comorbidities, history of DKA, level of consciousness and lactate level.

A retrospective cross-sectional study for predicting 72-h mortality in patients with serum aspartate aminotransferase levels ≥ 3000 U/L

“…The primary outcome was defined as 72-h mortality 11 , 12 following the AST test, regardless of symptom onset, hospitalisation, or setting (i.e., emergency or outpatient). Cases were defined as patients with extremely high outlier values of AST who died in the hospital during the first 72 h after the test, whereas controls were defined as patients with extremely high outlier values of AST who survived beyond 72 h.…”

“…This retrospective study aimed to investigate the association between very early mortality risk, defined as death within 72 h 11 , 12 following testing, of patients exhibiting extremely high outlier values of AST, and validity risks. In clinical practice, predicting 72-h mortality is extremely important for estimating and improving patient outcome in both primary and critical care settings.…”

“…In clinical practice, predicting 72-h mortality is extremely important for estimating and improving patient outcome in both primary and critical care settings. Siregar et al described a 72-h mortality prediction model for patients with diabetic ketoacidosis in Indonesia 11 . Another study involving a Singaporean cohort validated 72-h mortality among patients with sepsis by using the emergency department sepsis score 12 .…”

Towards transparent machine learning models using feature sensitivity algorithm

“…However, they used a limited number of observations. N. N. Siregar et al [22] identified the predictors of 72-hour mortality in patients with DKA. They used 301 health records of adult patients; the results showed that 11 predictors are associated with DKA complications and mortality.…”

Predicting 72-h mortality in patients with extremely high random plasma glucose levels

“…[ 15 ] Siregar et al showed that the 72-hours mortality prediction model performed well; this model includes comorbidities, history of diabetic ketoacidosis (DKA), level of consciousness, and lactate levels in patients with DKA at a general hospital in Indonesia. [ 16 ] In patients with DKA, Efstathiou et al reported that serum glucose ≥500 mg/dl was predictive of 72-hours mortality. [ 17 ] It is important to understand what risk factors could predict poor 72-hours mortality in patients with extremely high RPG to improve the earlier management in clinical settings.…”