Literature DB >> 31562847

Validation of a Machine Learning Model That Outperforms Clinical Risk Scoring Systems for Upper Gastrointestinal Bleeding.

Dennis L Shung1, Benjamin Au2, Richard Andrew Taylor2, J Kenneth Tay3, Stig B Laursen4, Adrian J Stanley5, Harry R Dalton6, Jeffrey Ngu7, Michael Schultz8, Loren Laine9.   

Abstract

BACKGROUND & AIMS: Scoring systems are suboptimal for determining risk in patients with upper gastrointestinal bleeding (UGIB); these might be improved by a machine learning model. We used machine learning to develop a model to calculate the risk of hospital-based intervention or death in patients with UGIB and compared its performance with other scoring systems.
METHODS: We analyzed data collected from consecutive unselected patients with UGIB from medical centers in 4 countries (the United States, Scotland, England, and Denmark; n = 1958) from March 2014 through March 2015. We used the data to derive and internally validate a gradient-boosting machine learning model to identify patients who met a composite endpoint of hospital-based intervention (transfusion or hemostatic intervention) or death within 30 days. We compared the performance of the machine learning prediction model with validated pre-endoscopic clinical risk scoring systems (the Glasgow-Blatchford score [GBS], admission Rockall score, and AIMS65). We externally validated the machine learning model using data from 2 Asia-Pacific sites (Singapore and New Zealand; n = 399). Performance was measured by area under receiver operating characteristic curve (AUC) analysis.
RESULTS: The machine learning model identified patients who met the composite endpoint with an AUC of 0.91 in the internal validation set; the clinical scoring systems identified patients who met the composite endpoint with AUC values of 0.88 for the GBS (P = .001), 0.73 for Rockall score (P < .001), and 0.78 for AIMS65 score (P < .001). In the external validation cohort, the machine learning model identified patients who met the composite endpoint with an AUC of 0.90, the GBS with an AUC of 0.87 (P = .004), the Rockall score with an AUC of 0.66 (P < .001), and the AIMS65 with an AUC of 0.64 (P < .001). At cutoff scores at which the machine learning model and GBS identified patients who met the composite endpoint with 100% sensitivity, the specificity values were 26% with the machine learning model versus 12% with GBS (P < .001).
CONCLUSIONS: We developed a machine learning model that identifies patients with UGIB who met a composite endpoint of hospital-based intervention or death within 30 days with a greater AUC and higher levels of specificity, at 100% sensitivity, than validated clinical risk scoring systems. This model could increase identification of low-risk patients who can be safely discharged from the emergency department for outpatient management.
Copyright © 2020 AGA Institute. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Artificial Intelligence; Mortality; Prediction; Prognostic Factor

Mesh:

Year:  2019        PMID: 31562847      PMCID: PMC7004228          DOI: 10.1053/j.gastro.2019.09.009

Source DB:  PubMed          Journal:  Gastroenterology        ISSN: 0016-5085            Impact factor:   22.682


  37 in total

1.  An epidemiological study of acute upper gastrointestinal bleeding in Crete, Greece.

Authors:  G A Paspatis; E Matrella; A Kapsoritakis; C Leontithis; N Papanikolaou; G J Chlouverakis; E Kouroumalis
Journal:  Eur J Gastroenterol Hepatol       Date:  2000-11       Impact factor: 2.566

2.  Acute upper gastrointestinal haemorrhage in west of Scotland: case ascertainment study.

Authors:  O Blatchford; L A Davidson; W R Murray; M Blatchford; J Pell
Journal:  BMJ       Date:  1997-08-30

3.  Automated, electronic alerts for acute kidney injury: a single-blind, parallel-group, randomised controlled trial.

Authors:  F Perry Wilson; Michael Shashaty; Jeffrey Testani; Iram Aqeel; Yuliya Borovskiy; Susan S Ellenberg; Harold I Feldman; Hilda Fernandez; Yevgeniy Gitelman; Jennie Lin; Dan Negoianu; Chirag R Parikh; Peter P Reese; Richard Urbani; Barry Fuchs
Journal:  Lancet       Date:  2015-02-26       Impact factor: 79.321

4.  Validation in prediction research: the waste by data splitting.

Authors:  Ewout W Steyerberg
Journal:  J Clin Epidemiol       Date:  2018-07-29       Impact factor: 6.437

5.  Epidemiology and course of acute upper gastro-intestinal haemorrhage in four French geographical areas.

Authors:  P Czernichow; P Hochain; J B Nousbaum; J M Raymond; A Rudelli; J L Dupas; M Amouretti; H Gouérou; M H Capron; H Herman; R Colin
Journal:  Eur J Gastroenterol Hepatol       Date:  2000-02       Impact factor: 2.566

6.  A simplified prognostic model to predict mortality in patients with acute variceal bleeding.

Authors:  Han Hee Lee; Jae Myung Park; Seunghoon Han; Sung Min Park; Hee Yeon Kim; Jung Hwan Oh; Chang Wook Kim; Seung Kew Yoon; Myung-Gyu Choi
Journal:  Dig Liver Dis       Date:  2017-11-24       Impact factor: 4.088

7.  Artificial neural networks accurately predict mortality in patients with nonvariceal upper GI bleeding.

Authors:  Gianluca Rotondano; Livio Cipolletta; Enzo Grossi; Maurizio Koch; Marco Intraligi; Massimo Buscema; Riccardo Marmo
Journal:  Gastrointest Endosc       Date:  2011-02       Impact factor: 9.427

8.  A simple risk score accurately predicts in-hospital mortality, length of stay, and cost in acute upper GI bleeding.

Authors:  John R Saltzman; Ying P Tabak; Brian H Hyett; Xiaowu Sun; Anne C Travis; Richard S Johannes
Journal:  Gastrointest Endosc       Date:  2011-09-10       Impact factor: 9.427

9.  Regularization Paths for Generalized Linear Models via Coordinate Descent.

Authors:  Jerome Friedman; Trevor Hastie; Rob Tibshirani
Journal:  J Stat Softw       Date:  2010       Impact factor: 6.440

Review 10.  Epidemiology of acute upper gastrointestinal bleeding.

Authors:  M E van Leerdam
Journal:  Best Pract Res Clin Gastroenterol       Date:  2008       Impact factor: 3.043

View more
  28 in total

1.  Twitter debate: controversies in management of upper gastrointestinal bleeding.

Authors:  Carly Lamb; James Maurice; Adrian J Stanley
Journal:  Frontline Gastroenterol       Date:  2021-01-05

Review 2.  Machine learning in gastrointestinal surgery.

Authors:  Takashi Sakamoto; Tadahiro Goto; Michimasa Fujiogi; Alan Kawarai Lefor
Journal:  Surg Today       Date:  2021-09-24       Impact factor: 2.549

3.  Comparing the Performance of the ABC, AIMS65, GBS, and pRS Scores in Predicting 90-day Mortality Or Rebleeding Among Emergency Department Patients with Acute Upper Gastrointestinal Bleeding: A Prospective Multicenter Study.

Authors:  Shuang Liu; Xiaoming Zhang; Joseph Harold Walline; Xuezhong Yu; Huadong Zhu
Journal:  J Transl Int Med       Date:  2021-06-16

4.  Endoscopist's Judgment Is as Useful as Risk Scores for Predicting Outcome in Peptic Ulcer Bleeding: A Multicenter Study.

Authors:  Enric Brullet; Pilar Garcia-Iglesias; Xavier Calvet; Michel Papo; Montserrat Planella; Albert Pardo; Félix Junquera; Silvia Montoliu; Raquel Ballester; Eva Martinez-Bauer; David Suarez; Rafel Campo
Journal:  J Clin Med       Date:  2020-02-03       Impact factor: 4.241

5.  Development of a Dynamic Diagnosis Grading System for Infertility Using Machine Learning.

Authors:  ShuJie Liao; Wei Pan; Wan-Qiang Dai; Lei Jin; Ge Huang; Renjie Wang; Cheng Hu; Wulin Pan; Haiting Tu
Journal:  JAMA Netw Open       Date:  2020-11-02

6.  The Impact of Artificial Intelligence in the Endoscopic Assessment of Premalignant and Malignant Esophageal Lesions: Present and Future.

Authors:  Daniela Cornelia Lazăr; Mihaela Flavia Avram; Alexandra Corina Faur; Adrian Goldiş; Ioan Romoşan; Sorina Tăban; Mărioara Cornianu
Journal:  Medicina (Kaunas)       Date:  2020-07-21       Impact factor: 2.430

7.  Neural network predicts need for red blood cell transfusion for patients with acute gastrointestinal bleeding admitted to the intensive care unit.

Authors:  Dennis Shung; Jessie Huang; Egbert Castro; J Kenneth Tay; Michael Simonov; Loren Laine; Ramesh Batra; Smita Krishnaswamy
Journal:  Sci Rep       Date:  2021-04-23       Impact factor: 4.379

8.  Regarding: Shung et al: Validation of a Machine Learning Model That Outperforms Clinical Risk Scoring Systems for Upper Gastrointestinal Bleeding.

Authors:  Hyun-Seok Kim; Frederick B Peng; Juan David Gomez Cifuentes
Journal:  Gastroenterology       Date:  2020-03-19       Impact factor: 22.682

9.  Machine Learning Prognostic Models for Gastrointestinal Bleeding Using Electronic Health Record Data.

Authors:  Dennis Shung; Loren Laine
Journal:  Am J Gastroenterol       Date:  2020-08       Impact factor: 12.045

10.  Prediction model of emergency mortality risk in patients with acute upper gastrointestinal bleeding: a retrospective study.

Authors:  Lan Chen; Han Zheng; Saibin Wang
Journal:  PeerJ       Date:  2021-06-24       Impact factor: 2.984

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.