Neural network prediction of severe lower intestinal bleeding and the need for surgical intervention

• Published in: The Journal of surgical research Vol. 212; pp. 42 - 47
• Main Authors: Loftus, Tyler J., MD, Brakenridge, Scott C., MD, MSCS, Croft, Chasen A., MD, FACS, Smith, R. Stephen, MD, FACS, Efron, Philip A., MD, FACS, FCCM, Moore, Frederick A., MD, FACS, MCCM, Mohr, Alicia M., MD, FACS, FCCM, Jordan, Janeen R., MD, FACS
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.05.2017
• Subjects: Adolescent; Adult; Aged; Aged, 80 and over; Area Under Curve; Colonic Diseases - diagnosis; Colonic Diseases - etiology; Colonic Diseases - surgery; Decision Support Techniques; Female; Gastrointestinal bleeding; Gastrointestinal Hemorrhage - diagnosis; Gastrointestinal Hemorrhage - etiology; Gastrointestinal Hemorrhage - surgery; Humans; Male; Middle Aged; Neural network; Neural Networks (Computer); Prognosis; Rectal Diseases - diagnosis; Rectal Diseases - etiology; Rectal Diseases - surgery; Retrospective Studies; Risk Assessment; Risk Factors; ROC Curve; Severe bleeding; Severity of Illness Index; Strate; Surgery; Transfusion; Young Adult; transfusion; severe bleeding; Strate; neural network; gastrointestinal bleeding; surgery; Transfusion; Neural network; Gastrointestinal bleeding; Surgery; Severe bleeding
• ISSN: 0022-4804; 1095-8673
• DOI: 10.1016/j.jss.2016.12.032

Abstract Background The prognosis for patients with severe acute lower intestinal bleeding (ALIB) may be assessed by complex artificial neural networks (ANNs) or user-friendly regression-based models. Comparisons between these modalities are limited, and predicting the need for surgical intervention remains elusive. We hypothesized that ANNs would outperform the Strate rule to predict severe bleeding, and would also predict the need for surgical intervention. Methods We performed a four-year retrospective analysis of 147 adult patients who underwent endoscopy, angiography, or surgery for ALIB. Baseline characteristics, Strate risk factors, management parameters, and outcomes were analyzed. The primary outcomes were severe bleeding and surgical intervention. ANNs were created in SPSS. Models were compared by area under the receiver operating characteristic curve (AUROC) with 95% confidence intervals. Results The number of Strate risk factors for each patient correlated significantly with the outcome of severe bleeding (r=0.29, p <0.001). However, the Strate model was less accurate than an ANN (AUROC 0.66 (0.57-0.75) vs. 0.98 (0.95-1.00), respectively) which incorporated six variables present on admission: hemoglobin, systolic blood pressure, outpatient prescription for Aspirin 325 mg daily, Charlson comorbidity index, base deficit ≥5 mEq/L, and INR ≥1.5. A similar ANN including hemoglobin nadir and the occurrence of a 20% decrease in hematocrit was effective in predicting the need for surgery (AUROC 0.95 (0.90-1.00)). Conclusions The Strate prediction rule effectively stratified risk for severe ALIB, but was less accurate than an ANN. A separate ANN accurately predicted the need for surgery by combining risk factors for severe bleeding with parameters quantifying blood loss. Optimal prognostication may be achieved by integrating pragmatic regression-based calculators for quick decisions at the bedside and highly accurate ANNs when time and resources permit.