Dataset Information

Prediction of Adverse Events in Stable Non-Variceal Gastrointestinal Bleeding Using Machine Learning.

ABSTRACT: Clinical risk-scoring systems are important for identifying patients with upper gastrointestinal bleeding (UGIB) who are at a high risk of hemodynamic instability. We developed an algorithm that predicts adverse events in patients with initially stable non-variceal UGIB using machine learning (ML). Using prospective observational registry, 1439 out of 3363 consecutive patients were enrolled. Primary outcomes included adverse events such as mortality, hypotension, and rebleeding within 7 days. Four machine learning algorithms, namely, logistic regression with regularization (LR), random forest classifier (RF), gradient boosting classifier (GB), and voting classifier (VC), were compared with the Glasgow-Blatchford score (GBS) and Rockall scores. The RF model showed the highest accuracies and significant improvement over conventional methods for predicting mortality (area under the curve: RF 0.917 vs. GBS 0.710), but the performance of the VC model was best in hypotension (VC 0.757 vs. GBS 0.668) and rebleeding within 7 days (VC 0.733 vs. GBS 0.694). Clinically significant variables including blood urea nitrogen, albumin, hemoglobin, platelet, prothrombin time, age, and lactate were identified by the global feature importance analysis. These results suggest that ML models will be useful early predictive tools for identifying high-risk patients with initially stable non-variceal UGIB admitted at an emergency department.

SUBMITTER: Seo DW

PROVIDER: S-EPMC7464777 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Adverse Events in Stable Non-Variceal Gastrointestinal Bleeding Using Machine Learning.

Seo Dong-Woo DW Yi Hahn H Park Beomhee B Kim Youn-Jung YJ Jung Dae Ho DH Woo Ilsang I Sohn Chang Hwan CH Ko Byuk Sung BS Kim Namkug N Kim Won Young WY

Journal of clinical medicine 20200811 8

Clinical risk-scoring systems are important for identifying patients with upper gastrointestinal bleeding (UGIB) who are at a high risk of hemodynamic instability. We developed an algorithm that predicts adverse events in patients with initially stable non-variceal UGIB using machine learning (ML). Using prospective observational registry, 1439 out of 3363 consecutive patients were enrolled. Primary outcomes included adverse events such as mortality, hypotension, and rebleeding within 7 days. Fo ...[more]

PMID: 32796647

Similar Datasets

Project description:IntroductionThis study aims to construct a mortality prediction model for patients with non-variceal upper gastrointestinal bleeding (NVUGIB) in the intensive care unit (ICU), employing advanced machine learning algorithms. The goal is to identify high-risk populations early, contributing to a deeper understanding of patients with NVUGIB in the ICU.MethodsWe extracted NVUGIB data from the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.2.2) database spanning from 2008 to 2019. Feature selection was conducted through LASSO regression, followed by training models using 11 machine learning methods. The best model was chosen based on the area under the curve (AUC). Subsequently, Shapley additive explanations (SHAP) was employed to elucidate how each factor influenced the model. Finally, a case was randomly selected, and the model was utilized to predict its mortality, demonstrating the practical application of the developed model.ResultsIn total, 2716 patients with NVUGIB were deemed eligible for participation. Following selection, 30 out of a total of 64 clinical parameters collected on day 1 after ICU admission remained associated with prognosis and were utilized for developing machine learning models. Among the 11 constructed models, the Gradient Boosting Decision Tree (GBDT) model demonstrated the best performance, achieving an AUC of 0.853 and an accuracy of 0.839 in the validation cohort. Feature importance analysis highlighted that shock, Glasgow Coma Scale (GCS), renal disease, age, albumin, and alanine aminotransferase (ALP) were the top six features of the GBDT model with the most significant impact. Furthermore, SHAP force analysis illustrated how the constructed model visualized the individualized prediction of death.ConclusionsPatient data from the MIMIC database were leveraged to develop a robust prognostic model for patients with NVUGIB in the ICU. The analysis using SHAP also assisted clinicians in gaining a deeper understanding of the disease.

Project description:BackgroundThere are limited data on the safety of colonoscopy in patients with lower gastrointestinal bleeding (LGIB). We examined the various adverse events associated with colonoscopy in acute LGIB compared with non-GIB patients.MethodsEmergency hospitalized LGIB patients (n = 161) and age- and gender-matched non-GIB controls (n = 161) were selected. Primary outcomes were any adverse events during preparation and colonoscopy procedure. Secondary outcomes were five bowel preparation-related adverse events--hypotension, systolic blood pressure <100 mmHg, volume overload, vomiting, aspiration pneumonia and loss of consciousness--and four colonoscopy-related adverse events--including hypotension, perforation, cerebrocardiovascular events and sepsis.ResultsDuring bowel preparation, 16 (9%) LGIB patients experienced an adverse event. None of the LGIB patients experienced volume overload, aspiration pneumonia or loss of consciousness; however, 12 (7%) had hypotension and 4 (2%) vomited. There were no significant differences in the five bowel preparation-related adverse events between LGIB and non-GIB patients. During colonoscopy, 25 (15%) LGIB patients experienced an adverse event. None LGIB patient had perforation or sepsis; however, 23 (14%) had hypotension and 2 (1%) experienced a cerebrocardiovascular event. There was no significant difference in the four colonoscopy-related adverse events between LGIB and non-GIB patients. In addition, no significant difference in any of the nine adverse events was found among subgroups: patients aged ≥65 years, those with comorbidities, and those with antithrombotic drug use.ConclusionsAdverse events in bowel preparation and colonoscopy among acute LGIB patients were low. No significant difference was found in adverse events between LGIB and non-GIB patients. These adverse events were also low in elderly LGIB patients, as well as in those with co-morbidities and antithrombotic drug use, suggesting that colonoscopy performed during acute LGIB did not increase adverse events.

Dataset Information

Prediction of Adverse Events in Stable Non-Variceal Gastrointestinal Bleeding Using Machine Learning.

Publications

Prediction of Adverse Events in Stable Non-Variceal Gastrointestinal Bleeding Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets