Correlation of acidosis-adjusted potassium level and cardiovascular outcomes in diabetic ketoacidosis: a systematic review

Development of Machine Learning Models for the Identification of Elevated Ketone Bodies During Hyperglycemia in Patients with Type 1 Diabetes

Aims: Diabetic ketoacidosis (DKA) is a serious life-threatening condition caused by a lack of insulin, which leads to elevated plasma glucose and metabolic acidosis. Early identification of developing DKA is important to start treatment and minimize complications and risk of death. The aim of the present study is to develop and test prediction model(s) that gives an alarm about their risk of developing elevated ketone bodies during hyperglycemia. Methods: We analyzed data from 138 type 1 diabetes patients with measurements of ketone bodies and continuous glucose monitoring (CGM) data from over 30,000 days of wear time. We utilized a supervised binary classification machine learning approach to identify elevated levels of ketone bodies (≥0.6 mmol/L). Data material was randomly divided at patient level in 70%/30% (training/test) dataset. Logistic regression (LR) and random forest (RF) classifier were compared. Results: Among included patients, 913 ketone samples were eligible for modeling, including 273 event samples with ketone levels ≥0.6 mmol/L. An area under the receiver operating characteristic curve from the RF classifier was 0.836 (confidence interval [CI] 90%, 0.783-0.886) and 0.710 (CI 90%, 0.646-0.77) for the LR classifier. Conclusions: The novel approach for identifying elevated ketone levels in patients with type 1 diabetes utilized in this study indicates that CGM could be a valuable resource for the early prediction of patients at risk of developing DKA. Future studies are needed to validate the results.

Early prediction models for prognosis of diabetic ketoacidosis in the emergency department: A protocol for systematic review and meta-analysis

BACKGROUND

Diabetic ketoacidosis (DKA) is one of the most serious complications after diabetes poor control, which seriously threatens human life, health, and safety. DKA can rapidly develop within hours or days leading to death. Early evaluation of the prognosis of DKA patients and timely and effective intervention are very important to improve the prognosis of patients. The combination of several variables or characteristics is used to predict the poor prognosis of DKA, which can allocate resources reasonably, which is beneficial to the early classification intervention and clinical treatment of the patients.

METHODS

For the acquisition of required data of eligible prospective/retrospective cohort study or randomized controlled trials (RCTs), we will search for publications from PubMed, Web of science, EMBASE, Cochrane Library, Google scholar, China national knowledge infrastructure (CNKI), Wanfang and China Science and Technology Journal Database (VIP). Two independent reviewers will read the full English text of the articles, screened and selected carefully, removing duplication. Then we evaluate the quality and analyses data by Review Manager (V.5.4). Results data will be pooled and meta-analysis will be conducted if there's 2 eligible studies considered.

RESULTS

This systematic review and meta-analysis will evaluate the value of the prediction models for the prognosis of DKA in the emergency department.

CONCLUSIONS

This systematic review and meta-analysis will provide clinical basis for predicting the prognosis of DKA. It helps us to understand the value of predictive models in evaluating the early prognosis of DKA. The conclusions drawn from this study may be beneficial to patients, clinicians, and health-related policy makers.

STUDY REGISTRATION NUMBER

INPLASY202150023.

Diabetic Ketoacidosis Management and Treatment Outcome at Medical Ward of Shashemene Referral Hospital, Ethiopia: A Retrospective Study

Background:

Diabetic Ketoacidosis (DKA) is the most common and yet potentially life-threatening acute complication of diabetes that progresses rapidly to death and requires immediate medical intervention.

Objective:

To assess the DKA management and treatment outcome/in-hospital mortality and its predictors among hospitalized patients with DKA at the Medical ward of Shashemene Referral Hospital (SRH).

Method:

A retrospective study was conducted at the Medical Ward of SRH from 01 February 2015 to 31 January 2017. A systematic random sampling technique was used to select study subjects based on the inclusion criteria. Thus, of 236 reviewed charts, only 225 patients with DKA fulfilled inclusion criteria. Treatment outcome was considered good for patients who have shown improvement at discharge, while poor for patients who left against medical advice or died in the hospital. Logistic regression analysis was done to determine independent predictors for treatment outcome/in-hospital mortality using SPSS version 20 with statistical significant at P ⩽ .05.

Results:

Of 225 patients with DKA, 124 (55.1%) were male. Regular insulin was prescribed to all patients and antibiotics were administered to 87 (38.7%). Potassium supplementation was given only for 28 (12.4%). Non-adherence to insulin treatment (n = 91; 40.4%) and infection (n = 66; 29.3%) were the principal DKA precipitating factors. Even though 73.8% of hospitalized patients with DKA have shown good treatment outcomes, DKA contributed 12% in-hospital mortality. The result of multivariate logistic regression analysis shown that hypoglycemia is the only independent predictor for in-hospital mortality[P = .03]. Moreover, the independent predictors for poor DKA treatment outcome were found to be smoker [P = .04], Urinary tract infection (UTI) relative to other co-morbid condition [P < .001], severe hypokalemia which increase risk of poor treatment outcome by around 4 times [P = .02], and use of Metronidazole as a concurrent medication relative to other concurrent medication [P = .03].

Conclusion:

There was a high in-hospital mortality rate due to correctable causes. This mortality is unacceptable as it was majorly related to the poor practice of potassium supplementation and hypoglycemia due to insulin. Thus, clinicians and stakeholders should have to focus on modifiable factors (hypokalemia, UTI, and hypoglycemia) to reduce poor treatment outcome/in-hospital mortality.