ABSTRACT
Background: Sepsis is a leading cause of morbidity and mortality in the critical care setting. The analysis of hemostatic parameters at admission have been proven to be a predictive marker for development of sepsis in the ICU. The present study aims to develop a machine learning model which can predict the development of sepsis after 72 hours of ICU admission, from initial assessment of hemostatic parameters.Methods: A total of 170 ICU admissions over six months (May 2018 - Dec 2018) period were included in the study. Hemostatic parameters including platelet counts, prothrombin time and Sonoclot assay were assayed at time of admission. The patients were followed up for development of sepsis. The data was split in two sets: training (100) and test (70). A machine learning model was developed using the linear discriminant analysis (LDA) model, in the R programming environment. The statistical parameters employed were sensitivity, specificity, positive and negative predictive value.Results: A comparison of incidence of development of clinical sepsis and predicted sepsis by the model showed 74.19% sensitivity and 84.61% specificity over the testing set. 06 false positives and 08 false negative predictions were encountered.Conclusions: The model shows potential to be used as a predictive tool for development of sepsis in the critical care ward. Moderate sensitivity and good specificity were achieved by the model, highlighting the role of hematologic assessment at admission in prediction of development of sepsis. However, further studies with larger datasets are required before implementation in clinical practice.
ABSTRACT
Background: The adequacy of haemodialysis in patients of type 2 diabetes mellitus with chronic kidney disease stage 5 depends on several clinical as well as laboratory parameters. Previous studies from Western literature have identified several clinical and laboratory markers for predicting adequacy of dialysis. There is a dearth of literature regarding the same in Indian patient populace. Authors aimed to find correlation, if any, between glycemic control and adequacy of dialysis in this cohort of patients.Methods: A set of 200 patients of type 2 diabetes mellitus who have undergone hemodialysis at a tertiary care hospital were included in the study. Random blood sugar (RBS), Glycated hemoglobin (HbA1c) were measured at admission. After 4 hours of dialysis, the urea reduction ratio (URR) and Kt/V was measured for each patient. The correlation coefficient as well as linear equation of the association between these variables were calculated. Standard statistical method and software were used in the process.Results: The study revealed a linear negative correlation between the variables RBS, HbA1c and URR as well as Kt/V. This suggests the importance of pre dialysis glycemic control in patients undergoing hemodialysis.Conclusions: Authors formulate the hypothesis that glycated hemoglobin and random blood sugar at admission correlate well with the outcome and adequacy of dialysis in patients of stage 5 chronic kidney disease undergoing haemodialysis. Good glycemic control (HbA1c <6.5 % and RBS <120 mg/dL) have shown to be important predictive markers of adequate dialysis. The hypothesis needs to be tested with a larger study.