Neil Sengupta1, Elliot B Tapper2. 1. Section of Gastroenterology, Hepatology, and Nutrition, Department of Medicine, University of Chicago Medical Center, Ill. Electronic address: nsengupta@medicine.bsd.uchicago.edu. 2. Division of Gastroenterology, Department of Internal Medicine, University of Michigan Health System, Ann Arbor.
Abstract
BACKGROUND: There are limited data to predict which patients with lower gastrointestinal bleeding are at risk for adverse outcomes. We aimed to develop a clinical tool based on admission variables to predict 30-day mortality in lower gastrointestinal bleeding. METHODS: We used a validated machine learning algorithm to identify adult patients hospitalized with lower gastrointestinal bleeding at an academic medical center between 2008 and 2015. The cohort was split randomly into derivation and validation cohorts. In the derivation cohort, we used multiple logistic regression on all candidate admission variables to create a prediction model for 30-day mortality, using area under the receiving operator characteristic curve and misclassification rate to estimate prediction accuracy. Regression coefficients were used to derive an integer score, and mortality risk associated with point totals was assessed. RESULTS: In the derivation cohort (n = 4044), 8 variables were most associated with 30-day mortality: age, dementia, metastatic cancer, chronic kidney disease, chronic pulmonary disease, anticoagulant use, admission hematocrit, and albumin. The model yielded a misclassification rate of 0.06 and area under the curve of 0.81. The integer score ranged from -10 to 26 in the derivation cohort, with a misclassification rate of 0.11 and area under the curve of 0.74. In the validation cohort (n = 2060), the score had an area under the curve of 0.72 with a misclassification rate of 0.12. After dividing the score into 4 quartiles of risk, 30-day mortality in the derivation and validation sets was 3.6% and 4.4% in quartile 1, 4.9% and 7.3% in quartile 2, 9.9% and 9.1% in quartile 3, and 24% and 26% in quartile 4, respectively. CONCLUSIONS: A clinical tool can be used to predict 30-day mortality in patients hospitalized with lower gastrointestinal bleeding.
BACKGROUND: There are limited data to predict which patients with lower gastrointestinal bleeding are at risk for adverse outcomes. We aimed to develop a clinical tool based on admission variables to predict 30-day mortality in lower gastrointestinal bleeding. METHODS: We used a validated machine learning algorithm to identify adult patients hospitalized with lower gastrointestinal bleeding at an academic medical center between 2008 and 2015. The cohort was split randomly into derivation and validation cohorts. In the derivation cohort, we used multiple logistic regression on all candidate admission variables to create a prediction model for 30-day mortality, using area under the receiving operator characteristic curve and misclassification rate to estimate prediction accuracy. Regression coefficients were used to derive an integer score, and mortality risk associated with point totals was assessed. RESULTS: In the derivation cohort (n = 4044), 8 variables were most associated with 30-day mortality: age, dementia, metastatic cancer, chronic kidney disease, chronic pulmonary disease, anticoagulant use, admission hematocrit, and albumin. The model yielded a misclassification rate of 0.06 and area under the curve of 0.81. The integer score ranged from -10 to 26 in the derivation cohort, with a misclassification rate of 0.11 and area under the curve of 0.74. In the validation cohort (n = 2060), the score had an area under the curve of 0.72 with a misclassification rate of 0.12. After dividing the score into 4 quartiles of risk, 30-day mortality in the derivation and validation sets was 3.6% and 4.4% in quartile 1, 4.9% and 7.3% in quartile 2, 9.9% and 9.1% in quartile 3, and 24% and 26% in quartile 4, respectively. CONCLUSIONS: A clinical tool can be used to predict 30-day mortality in patients hospitalized with lower gastrointestinal bleeding.
Authors: Antonio Tarasconi; Gennaro Perrone; Justin Davies; Raul Coimbra; Ernest Moore; Francesco Azzaroli; Hariscine Abongwa; Belinda De Simone; Gaetano Gallo; Giorgio Rossi; Fikri Abu-Zidan; Vanni Agnoletti; Gianluigi de'Angelis; Nicola de'Angelis; Luca Ansaloni; Gian Luca Baiocchi; Paolo Carcoforo; Marco Ceresoli; Alain Chichom-Mefire; Salomone Di Saverio; Federica Gaiani; Mario Giuffrida; Andreas Hecker; Kenji Inaba; Michael Kelly; Andrew Kirkpatrick; Yoram Kluger; Ari Leppäniemi; Andrey Litvin; Carlos Ordoñez; Vittoria Pattonieri; Andrew Peitzman; Manos Pikoulis; Boris Sakakushev; Massimo Sartelli; Vishal Shelat; Edward Tan; Mario Testini; George Velmahos; Imtiaz Wani; Dieter Weber; Walter Biffl; Federico Coccolini; Fausto Catena Journal: World J Emerg Surg Date: 2021-09-16 Impact factor: 5.469
Authors: Kathryn Oakland; Sandeepkumar Kothiwale; Tyler Forehand; Edmund Jackson; Cliff Bucknall; Michael S L Sey; Siddharth Singh; Vipul Jairath; Jonathan Perlin Journal: JAMA Netw Open Date: 2020-07-01
Authors: Kalpit Devani; Dhruvil Radadiya; Paris Charilaou; Tyler Aasen; Chakradhar M Reddy; Mark Young; Bhaumik Brahmbhatt; Don C Rockey Journal: Endosc Int Open Date: 2021-05-27