An Artificial Neural Networks Model for Early Predicting In-Hospital Mortality in Acute Pancreatitis in MIMIC-III.

Biomed Res Int

Department of Emergency Medicine, The Second Xiangya Hospital, Emergency Medicine and Difficult Diseases Institute, Central South University, China.

Published: May 2021

Background: Early and accurate evaluation of severity and prognosis in acute pancreatitis (AP), especially at the time of admission is very significant. This study was aimed to develop an artificial neural networks (ANN) model for early prediction of in-hospital mortality in AP.

Methods: Patients with AP were identified from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. Clinical and laboratory data were utilized to perform a predictive model by back propagation ANN approach.

Results: A total of 337 patients with AP were analyzed in the study, and the in-hospital mortality rate was 11.2%. A total of 12 variables that differed between patients in survivor group and nonsurvivor group were applied to construct ANN model. Three independent variables were identified as risk factors associated with in-hospital mortality by multivariate logistic regression analysis. The predictive performance based on the area under the receiver operating characteristic curve (AUC) was 0.769 for ANN model, 0.607 for logistic regression, 0.652 for Ranson score, and 0.401 for SOFA score.

Conclusion: An ANN predictive model for in-hospital mortality in patients with AP in MIMIC-III database was first performed. The patients with high risk of fatal outcome can be screened out easily in the early stage of AP by our model.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7864739PMC
http://dx.doi.org/10.1155/2021/6638919DOI Listing

Publication Analysis

Top Keywords

in-hospital mortality
20
ann model
12
artificial neural
8
neural networks
8
model early
8
acute pancreatitis
8
mimic-iii database
8
predictive model
8
logistic regression
8
model
7

Similar Publications

Objectives: Despite the advances in medicine, aortic dissection remains a cardiac surgery emergency with high mortality and morbidity rates. This study examined the effects of the Glue + Felt technique, which uses biological glue and felt to repair the proximal anastomotic site, on the outcomes of patients with acute type A aortic dissection.

Methods: A total of 108 patients who underwent surgery for acute type A aortic dissection at our clinic between 2007 and 2020 were included in the study.

View Article and Find Full Text PDF

Inborn errors of immunity (primary immunodeficiencies).

Allergy Asthma Clin Immunol

January 2025

Division of Allergy and Clinical Immunology, Department of Pediatrics, Montreal Children's Hospital, McGill University Health Centre, Montreal, QC, Canada.

Primary immunodeficiencies (PID), now often referred to as inborn errors of immunity (IEI), are a large heterogeneous group of disorders that result from deficiencies in immune system development and/or function. IEIs can be broadly classified as disorders of adaptive immunity (e.g.

View Article and Find Full Text PDF

Background: Near-infrared spectroscopy (NIRS) enables a non-invasive measurement of tissue oxygen saturation (StO) in regions illuminated by near-infrared lights. Vascular occlusion test (VOT) serves as a model to artificially induce forearm ischemia-reperfusion. The combination of StO monitoring and VOT allows for dynamic evaluation of the balance between oxygen delivery and consumption in tissue, as well as the functional reserve of microcirculation.

View Article and Find Full Text PDF

Introduction: Purulent bacterial pericarditis is a potentially fatal disease with mortality rates reaching 100% if left untreated.

Case Presentation: We present the case of a 33-year-old Caucasian male patient who developed cardiac tamponade, most likely caused by a pyogenic liver abscess communicating with the pericardium. Treatment with antibiotics, extended sepsis therapy, and drainage of the abscess led to a full recovery.

View Article and Find Full Text PDF

Background: Among hypertensive cohorts across different nations, the relationship between the triglyceride-glucose index (TyG) and its conjunction with obesity metrics in relation to cardiovascular disease (CVD) incidence and mortality remains to be elucidated.

Methods: This study enrolled 9,283, 164,357, and 5,334 hypertensives from the National Health and Nutrition Examination Survey (NHANES), UK Biobank (UKBB), and Shanghai Pudong cohort. The related outcomes for CVD were defined by multivariate Cox proportional hazards models, Generalized Additive Models and Mendelian randomization analysis.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!