A decision support system to facilitate management of patients with acute gastrointestinal bleeding

https://doi.org/10.1016/j.artmed.2007.10.003Get rights and content

Summary

Objective

To develop a model to predict the bleeding source and identify the cohort amongst patients with acute gastrointestinal bleeding (GIB) who require urgent intervention, including endoscopy. Patients with acute GIB, an unpredictable event, are most commonly evaluated and managed by non-gastroenterologists. Rapid and consistently reliable risk stratification of patients with acute GIB for urgent endoscopy may potentially improve outcomes amongst such patients by targeting scarce healthcare resources to those who need it the most.

Design and methods

Using ICD-9 codes for acute GIB, 189 patients with acute GIB and all available data variables required to develop and test models were identified from a hospital medical records database. Data on 122 patients was utilized for development of the model and on 67 patients utilized to perform comparative analysis of the models. Clinical data such as presenting signs and symptoms, demographic data, presence of co-morbidities, laboratory data and corresponding endoscopic diagnosis and outcomes were collected. Clinical data and endoscopic diagnosis collected for each patient was utilized to retrospectively ascertain optimal management for each patient. Clinical presentations and corresponding treatment was utilized as training examples. Eight mathematical models including artificial neural network (ANN), support vector machine (SVM), k-nearest neighbor, linear discriminant analysis (LDA), shrunken centroid (SC), random forest (RF), logistic regression, and boosting were trained and tested. The performance of these models was compared using standard statistical analysis and ROC curves.

Results

Overall the random forest model best predicted the source, need for resuscitation, and disposition with accuracies of approximately 80% or higher (accuracy for endoscopy was greater than 75%). The area under ROC curve for RF was greater than 0.85, indicating excellent performance by the random forest model.

Conclusion

While most mathematical models are effective as a decision support system for evaluation and management of patients with acute GIB, in our testing, the RF model consistently demonstrated the best performance. Amongst patients presenting with acute GIB, mathematical models may facilitate the identification of the source of GIB, need for intervention and allow optimization of care and healthcare resource allocation; these however require further validation.

Introduction

Acute gastrointestinal bleeding (GIB) continues to be a significant healthcare problem due to rising NSAID use and an aging population [1]. Further reductions in mortality will most likely require introduction of novel strategies to aid identification of the cohort requiring aggressive resuscitation and endoscopic intervention to prevent complications and death from ongoing bleeding [2], [3]. Delays in intervention usually result from failure to adequately recognize the source and severity of the bleed. Although several models and scores have been developed to risk-stratify patients, no single model aids the identification of the subgroup of patients presenting with acute upper or lower GIB that would most likely benefit from urgent intervention [4], [5]. Our goal was to utilize mathematical models to formulate a decision support system utilizing clinical and laboratory information available within a few hours of patient presentation to predict the source, need for intervention and disposition in patients with acute upper, mid- and lower GIB.

There are a number of well-known classification tools for analyzing data, including artificial neural networks (ANN), k-nearest neighbor (kNN), decision trees, support vector machines (SVM), and shrunken centroid (SC) [6], [7]. These classification tools are supervised learning methods where the algorithm learns from a training set and establishes a prediction rule to classify new samples using statistical approaches for class prediction. Logistic regression, an alternative to these classification methods, and Fisher's linear discriminant analysis (LDA) are both parametric approaches. Logistic regression and LDA do not differ in functional form, and differ only in the estimation of coefficients; LDA assumes normal distribution of the explanatory variables, while logistic regression does not. If the Gaussian assumptions are met, then LDA is a more powerful and efficient model than logistic regression. Standard statistical model building relies on an a priori collection of predictor variables for identifying outcomes of clinical interest. Often it may be computationally impossible for standard models to overcome the complexities of problems with large dimensionality. Support vector machines (SVM), introduced by Vapnik [6] can overcome the high dimensionality problem computationally and is consistently a good classifier and hence widely utilized as a classification method. Following the recent introduction of ensemble-voting approaches, two ensemble voting methods, boosting and bagging, have also gained wide popularity [8], [9]. An ensemble uses the predictions of multiple base classifiers through majority voting. Boosting, a meta-classifier, combines weak classifiers and takes a weighted majority vote of their predictors. Breiman [10] developed the random forest (RF) method by combining classification tree predictors. The bagging algorithm in RF uses bootstrap samples to build base trees. Each bootstrap sample is formed by randomly sampling, with replacement, the same number of observations as the training set. The final classification produced by the ensemble of these base classifiers is obtained using equal weight voting.

The study objective was to develop and compare the performance of eight classification models as described above to predict clinical outcomes in patients presenting with acute GIB.

Section snippets

Definitions

Upper GIB refers to gastrointestinal blood loss whose origin is proximal to the ligament of Treitz; mid-GIB whose source was below the ligament of Trietz but proximal to the ileocecal valve and lower GIB referred to gastrointestinal blood loss emanating from a source distal to the ileocecal valve [11]. Acute GIB was defined as bleeding of less than 5 days duration. Acute upper GIB was diagnosed if there was hematemesis, “coffee ground” colored emesis, the return of red blood via a nasogastric

Models

Table 1, Table 2, Table 3, Table 4 summarize the results for each outcome prediction variable for the evaluation step. Eight models were run (only six of the eight models were utilized to predict source, since logistic regression and boosting can be only used for two-way classification problems (while output source included three outcomes-upper, mid and lower) using the primary approach. Figure 2, Figure 3, Figure 4, Figure 5 depict the accuracies obtained from each individual model and each

Discussion and conclusion

Although superior healthcare outcomes may be expected if gastroenterologists manage all patients with acute GIB [32], it is logistically impossible for every patient with acute GIB to be emergently evaluated and treated by a gastroenterologist, as the onset of acute GIB is unpredictable. It is also impractical and economically unjustifiable to subject every patient with acute GIB to intensive resuscitation and urgent endoscopy as only 20% of patients with acute GIB may require urgent

Acknowledgement

The study was funded by 2005 Research and Outcomes Effectiveness Awards of the American Society of Gastrointestinal Endoscopy (ASGE) to Atul Kumar.

References (40)

  • D. Timmerman et al.

    Artificial neural network models for the preoperative discrimination between malignant and benign adnexal masses

    Ultrasound Obstet Gynecol

    (1999)
  • C.F. Chong et al.

    Stratification of adverse outcomes by preoperative risk factors in coronary artery bypass graft patients: an artificial neural network prediction model

    Proc AMIA Annu Symp

    (2003)
  • P.J. Lisboa

    A review of evidence of health benefit from artificial neural networks in medical intervention

    Neural Networks

    (2002)
  • H. Ahn et al.

    Classification by ensembles from random partitions of high-dimensional data

    Comput Stat Data Anal

    (2007)
  • T.A. Rockall et al.

    Incidence of and mortality from acute upper gastrointestinal haemorrhage in the United Kingdom Steering Committee and members of the National Audit of Acute Upper Gastrointestinal Haemorrhage

    Br Med J

    (1995)
  • R. Baradarian et al.

    Early intensive resuscitation of patients with upper gastrointestinal bleeding decreases mortality

    Am J Gastroenterol

    (2004)
  • V. Vapnik

    The nature of statistical learning theory

    (1995)
  • R. Tibshirani et al.

    Diagnosis of multiple cancer types by shrunken centroids of gene expression

    Proc Natl Acad Sci

    (2002)
  • L. Breiman

    Bagging predictors

    Mach Learn

    (1996)
  • R.E. Schapire

    The strength of weak learnability

    Mach Learn

    (1990)
  • Cited by (58)

    • Using Machine Learning to Make Predictions in Patients Who Fall

      2021, Journal of Surgical Research
      Citation Excerpt :

      LR was chosen because it is a well-recognized algorithm. DTC and RFC were chosen for several reasons including the ability to run it on the computer system mentioned earlier, their ability to run with very little hyperparameter tuning, and ability to examine the variable importance used to make predictions.20-22 For each algorithm type, the data were first split into training data (80%) and a test set (20%).

    • Scalable gastroscopic video summarization via similar-inhibition dictionary selection

      2016, Artificial Intelligence in Medicine
      Citation Excerpt :

      Many computer-aided endoscopy diagnosis systems have been proposed to assist clinicians in improving the accuracy of medical diagnosis using the images or videos recorded in the inspection of a GT tract. According to the specific lesions, these systems can be classified to handle bleeding [30,31], tumors [32,33], Helicobacter pylori [34], cancer [35,36], Crohn's disease [37] and polyps [38]. Moreover, some other applications include pose detection for endoscopy [39], video segmentation [40] and three-dimensional reconstruction of the digestive wall [41].

    View all citing articles on Scopus
    1

    These authors contributed equally to this study.

    View full text