Risk scoring systems to predict need for clinical intervention for patients with nonvariceal upper gastrointestinal tract bleeding

Abstract

Background: Several risk score systems are designed for triage patients with acute nonvariceal upper gastrointestinal bleeding (UGIB). Blatchford score, which relies on only clinical and laboratory data, is used to identify patients with acute UGIB who need clinical intervention (before endoscopy). Clinical Rockall score, which relies on only clinical variables, is used to identify patients with acute UGIB who have adverse outcome, such as death or recurrent bleeding. Complete Rockall score, which relies on clinical and endoscopic variables, is also used to identify patients with acute UGIB who died or have recurrent bleeding. In our study, we define patients who need clinical intervention (ie, blood transfusion, endoscopic or surgical management for bleeding control) as high-risk patients. Our study aims to compare Blatchford score with clinical Rockall score and complete Rockall score in their utilities in identifying high-risk cases in patients with acute nonvariceal UGIB.

Methods: International Classification of Diseases, Ninth Revision, Clinical Modification codes for admission diagnosis were used to recognize a cohort of patients (N = 354) with acute UGIB admitted to a tertiary care, university-affiliated hospital. Medical record data were abstracted by 1 research assistant blinded to the study purpose. Blatchford and Rockall scores were calculated for each enrolled patient. High risk was defined as a Blatchford score of greater than 0, a clinical Rockall score of greater than 0, and a complete Rockall score of greater than 2. Patients were defined as needing clinical intervention if they had a blood transfusion or any operative or endoscopic intervention to control their bleeding. Such patients were defined as high-risk patients.

Results: The Blatchford score identified 326 (92.1%) of the 354 patients as those with high risk for clinical intervention (ie, blood transfusion, endoscopic or surgical management for bleeding control). The clinical Rockall score identified 289 (81.6%) of the 354 patients as high-risk, and the complete Rockall score identified 248 (70.1%) of the 354 patients as high-risk. The yield of identifying high-risk cases with the Blatchford score was significantly greater than with the clinical Rockall score (P < .0001) or with the complete Rockall score (P < .0001). In our total 354 patients, 246 (69.5%) patients were categorized as those with high risk for clinical intervention (ie, blood transfusion, endoscopic or surgical management for bleeding control, as aforementioned) in our study. The Blatchford score identified 245 (99.6%) of 246 patients as high-risk. Only 1 patient who met the study definition of needing clinical intervention was not identified via Blatchford score. This patient did not have recurrent bleeding nor die and did not receive blood transfusion. The clinical Rockall score identified 222 (90.2%) of 246 patients as high-risk. Twenty-four patients who met the study definition of needing clinical intervention were not recognized via clinical Rockall score. Of these patients, 0 died, 7 developed recurrent bleeding, and 6 needed blood transfusion. The complete Rockall score identified 224 (91.1%) of 246 patients as high-risk. Twenty-two patients who met the study definition of needing clinical intervention were not recognized via complete Rockall score. Of these patients, 2 died, 3 developed recurrent bleeding, and 20 needed blood transfusion.

Conclusions: The Blatchford score, which is based on clinical and laboratory variables, may be a useful risk stratification tool in detecting which patients need clinical intervention in patients with acute nonvariceal UGIB. It does not need urgent endoscopy for scoring and has higher sensitivity than the clinical Rockall score and the complete Rockall score in identifying high-risk patients.