This study investigates the use of computational frameworks for sepsis. We consider two dimensions for investigation – early diagnosis of sepsis (EDS) and mortality prediction rate for sepsis patients (MPS). We concentrate on the clinical parameters on which sepsis diagnosis and prognosis are currently done, including customized treatment plans based on historical data of the patient. We identify the most notable literature that uses computational models to address EDS and MPS based on those clinical parameters. In addition to the review of the computational models built upon the clinical parameters, we also provide details regarding the popular publicly available data sources. We provide brief reviews for each model in terms of prior art and present an analysis of their results, as claimed by the respective authors. With respect to the use of machine learning models, we have provided avenues for model analysis in terms of model selection, model validation, model interpretation, and model comparison. We further present the challenges and limitations of the use of computational models, providing future research directions. This study intends to serve as a benchmark for first-hand impressions on the use of computational models for EDS and MPS of sepsis, along with the details regarding which model has been the most promising to date. We have provided details regarding all the ML models that have been used to date for EDS and MPS of sepsis.
This study aimed to explore the correlation between hyperglycemia at intensive care unit (ICU) admission and the incidence of acute kidney injury (AKI) in patients after cardiac surgery.
We conducted a retrospective cohort study, in which clinical data were extracted from the Medical Information Mart for Intensive Care (MIMIC)-IV database. Adults (≥18 years) in the database who were admitted to the cardiovascular intensive care unit after cardiac surgery were enrolled. The primary outcome was the incidence of AKI within 7 days following ICU admission. Secondary outcomes included ICU mortality, hospital mortality, ICU length of stay, and the 28-day and 90-day mortality. Multivariable Cox regression analysis was used to assess the association between ICU-admission hyperglycemia and AKI incidence within 7 days of ICU admission. Different adjustment strategies were used to adjust for potential confounders. Patients were divided into three groups according to their highest blood glucose levels recorded within 24 h of ICU admission: no hyperglycemia (<140 mg/dL), mild hyperglycemia (140–200 mg/dL), and severe hyperglycemia (≥200 mg/dL).
Of the 6905 included patients, 2201 (31.9%) were female, and the median (IQR) age was 68.2 (60.1–75.9) years. In all, 1836 (26.6%) patients had severe hyperglycemia. The incidence of AKI within 7 days of ICU admission, ICU mortality, and hospital mortality was significantly higher in patients with severe admission hyperglycemia than those with mild hyperglycemia or no hyperglycemia (80.3% vs. 73.6% and 61.2%, respectively; 2.8% vs. 0.9% and 1.9%, respectively; and 3.4% vs. 1.2% and 2.5%, respectively; all P <0.001). Severe hyperglycemia was a risk factor for 7-day AKI (Model 1: hazard ratio [HR]=1.4809, 95% confidence interval [CI]: 1.3126 to 1.6707; Model 2: HR=1.1639, 95% CI: 1.0176 to 1.3313; Model 3: HR=1.2014, 95% CI: 1.0490 to 1.3760; all P <0.050). Patients with normal glucose levels (glucose levels <140 mg/dL) had a higher 28-day mortality rate than those with severe hyperglycemia (glucose levels ≥200 mg/dL) (4.0% vs. 3.8%, P <0.001).
In post-cardiac surgery patients, severe hyperglycemia within 24 h of ICU admission increases the risk of 7-day AKI, ICU mortality, and hospital mortality. Clinicians should be extra cautious regarding AKI among patients with hyperglycemia at ICU admission after cardiac surgery.