Predictors and outcomes of recurrent diabetic ketoacidosis in Israeli adults

Golbets, Evgeny; Brandstaetter, Evgenia; Sagy, Iftach; Zimhony-Nissim, Noa; Lipnitzki, Inna; Musa, Hadeel; Jotkowitz, Alan; Schwarzfuchs, Dan; Barski, Leonid

doi:10.1016/j.dsx.2021.102276

Cited by 5 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…stated that the predominant precipitating factor was noncompliance with an insulin regimen (54.2%)[2]. Our results also showed that missed insulin doses, high random blood sugar, and pH < 7.3 were predictors of DKA recurrence, in agreement with a previous study byGolbets et al (2021) [25]. This study found that patients with HbA1C more than 9.0% and younger age are related to recurrent DKA development.…”

supporting

confidence: 92%

Contributing Clinical Presentation, Risk Factors, and Outcomes for Diabetic Ketoacidosis Patients: A Single-Center Retrospective Study

Alsukhayri¹,

Biek²,

Khozana³

et al. 2022

Int J Pharm Res Allied Sci

View full text Add to dashboard Cite

In patients with diabetes mellitus, diabetic ketoacidosis (DKA) is the most common acute metabolic complication and occurs more frequently in those with type 1 diabetes (DM1). DKA is a hyperglycemic crisis that develops due to insulin insufficiency. It can be due to insulin noncompliance, newly diagnosed diabetes mellitus, a subtherapeutic dose, and conditions that cause hyperglycemia leading to elevated ketone bodies (e.g., urinary/ respiratory tract infections), and some drugs. As reported by the World Health Organization in 2014, Saudi Arabia ranks seventh highest in the world for diabetes prevalence. The high prevalence of diabetes in Saudi Arabia contributes to the high incidence of patients with DKA. To evaluate the precipitating risks of DKA in diabetic patients and its clinical presentation and outcomes at King Faisal Hospital at Makkah in Saudi Arabia. A retrospective review of patients with (DM1) at King Faisal Hospital in Makkah who presented with DKA from September 2020 to February 2022 was performed. Symptoms and risk factors were compared across age and sex. We found that the symptoms of polyuria, nausea and vomiting, weight loss, and fever significantly differed at the 10% level depending on the patient's age. No signs were statistically significant concerning sex. Of the precipitating factors, patient failure to comply, inadequate insulin dose, and infections were statistically significant in the older age group. It was observed that missed insulin doses, high random blood sugar, and pH less than 7.3 were the most significant predictors of DKA recurrence.

show abstract

supporting

confidence: 92%

Contributing Clinical Presentation, Risk Factors, and Outcomes for Diabetic Ketoacidosis Patients: A Single-Center Retrospective Study

Alsukhayri¹,

Biek²,

Khozana³

et al. 2022

Int J Pharm Res Allied Sci

View full text Add to dashboard Cite

show abstract

“…By replacing ( 31) into (28), we get (21), which concludes the Theorem's proof. Remark 1: A) According to (25), ( 21) is provided when the patient readmission decision is made based on the accuracies A…”

Section: B Global and Local Optimal Sub-intervalmentioning

confidence: 99%

Mathematical Modeling and Optimal Stopping Theory-based additional layers for 30-Day Rate Risk Prediction of Readmission to Intensive Care Units

hassouny¹,

Bouanani²,

Qaraqe³

2022

Preprint

View full text Add to dashboard Cite

The importance of 30-day patients’ readmissions (PRs) to intensive unit care stems from the significant cost and mortality risk when the patient’s chosen class (i.e., readmitted or not to the hospital) is incorrect. The overall accuracy (OA) of the PRs classification obtained in the literature is still moderate, particularly for machine learning (ML)-enabled ANNs, where OA is around 65%, resulting in 35% critical wrong decisions. To improve such an OA, a three-stage ML-assisted algorithm employing both support vector machines (SVMs) and artificial neural networks (ANNs) techniques is proposed. Starting with a well-fitted PR accuracies distribution and using mathematical modeling, the global optimal accuracies’ interval of misclassified patients (OIMP) is obtained, and a novel theorem for the generalized secretary problem is introduced and used to select the most likely well-classified patients. The algorithm’s final phase consists of flipping the remaining incorrectly classified patients in the OIMP. Using the presented approach with ANN and SVM, the OA was raised by 5% and 19%, respectively. The proposed approach may be used for any binary classification application and expanded to any multi-class problem.

show abstract