Farees T. Farooq

Clinical triage decision vs risk scores in predicting the need for endotherapy in upper gastrointestinal bleeding.

BACKGROUND Acute upper gastrointestinal hemorrhage (UGIH) is a common reason for hospitalization with substantial associated morbidity, mortality, and cost. Differentiation of high- and low-risk patients using established risk scoring systems has been advocated. The aim of this study was to determine whether these scoring systems are more accurate than an emergency physicians clinical decision making in predicting the need for endoscopic intervention in acute UGIH. METHODS Patients presenting to a tertiary care medical center with acute UGIH from 2003 to 2006 were identified from the hospital database, and their clinical data were abstracted. One hundred ninety-five patients met the inclusion criteria and were included in the analysis. The clinical Rockall score and Blatchford score (BS) were calculated and compared with the clinical triage decision (intensive care unit vs non-intensive care unit admission) in predicting the need for endoscopic therapy. RESULTS Clinical Rockall score greater than 0 and BS greater than 0 were sensitive predictors of the need for endoscopic therapy (95% and 100%) but were poorly specific (9% and 4%), with overall accuracies of 41% and 39%. At higher score cutoffs, clinical Rockall score greater than 2 and BS greater than 5 remained sensitive (84% and 87%) and were more specific (29% and 33%), with overall accuracies of 48% and 52%. Clinical triage decision, as a surrogate for predicting the need for endoscopic therapy, was moderately sensitive (67%) and specific (75%), with an overall accuracy (73%) that exceeded both risk scores. CONCLUSIONS The clinical use of risk scoring systems in acute UGIH may not be as good as clinical decision making by emergency physicians.

In vivo characterization of pancreatic and lymph node tissue by using EUS spectrum analysis: a validation study.

BACKGROUND Quantitative spectral analysis of the radiofrequency (RF) signals that underlie grayscale EUS images can be used to provide additional, objective information about tissue state. OBJECTIVE Our purpose was to validate RF spectral analysis as a method to distinguish between (1) benign and malignant lymph nodes and (2) normal pancreas, chronic pancreatitis, and pancreatic cancer. DESIGN AND SETTING A prospective validation study of eligible patients was conducted to compare with pilot study RF data. PATIENTS Forty-three patients underwent EUS of the esophagus, stomach, pancreas, and surrounding intra-abdominal and mediastinal lymph nodes (19 from a previous pilot study and 24 additional patients). MAIN OUTCOME MEASUREMENTS Midband fit, slope, intercept, and correlation coefficient from a linear regression of the calibrated RF power spectra were determined. RESULTS Discriminant analysis of mean pilot-study parameters was then performed to classify validation-study parameters. For benign versus malignant lymph nodes, midband fit and intercept (both with t test P < .058) provided classification with 67% accuracy and area under the receiver operating curve (AUC) of 0.86. For diseased versus normal pancreas, midband fit and correlation coefficient (both with analysis of variance P < .001) provided 93% accuracy and an AUC of 0.98. For pancreatic cancer versus chronic pancreatitis, the same parameters provided 77% accuracy and an AUC of 0.89. Results improved further when classification was performed with all data. LIMITATIONS Moderate sample size and spatial averaging inherent to the technique. CONCLUSIONS This study confirms that mean spectral parameters provide a noninvasive method to quantitatively discriminate benign and malignant lymph nodes as well as normal and diseased pancreas.

Characterization of pancreatic cancer and intra-abdominal lymph node malignancy using spectrum analysis of endoscopic ultrasound imaging

This study assessed the ability of spectral analysis of endoscopic ultrasound (EUS) RF signals acquired in humans in vivo to distinguish between (1) benign and malignant intraabdominal and mediastinal lymph nodes and (2) pancreatic cancer, chronic pancreatitis, and normal pancreas. Mean midband fit, slope, intercept, and correlation coefficient from a linear regression of the calibrated RF power spectra were computed over regions of interest defined by the endoscopist. Linear discriminant analysis was then performed to develop a classification of the resulting spectral parameters. For lymph nodes, classification based on the midband fit and intercept provided 67% sensitivity, 82% specificity, and 73% accuracy for malignant vs. benign nodes. For pancreas, classification based on midband fit and correlation coefficient provided 95% sensitivity, 93% specificity, and 93% accuracy for diseased vs. normal pancreas and 85% sensitivity, 71% specificity, and 85% accuracy for pancreatic cancer vs. chronic pancreatitis. These promising results suggest that mean spectral parameters can provide a non-invasive method to quantitatively characterize pancreatic cancer and lymph malignancy in vivo.

Artificial Neural Network (ANN) Is Superior to the Pre-Endoscopic Rockall Score in Predicting Which Patients Will Benefit From Urgent EGD in Acute Upper GI Bleeding (UGIB)

Artificial Neural Network (ANN) Is Superior to the PreEndoscopic Rockall Score in Predicting Which Patients Will Benefit From Urgent EGD in Acute Upper GI Bleeding (UGIB) Ananya Das, Farees Farooq, Richard Wong, Tamir Ben-Menachem, Gregory Cooper, Amitabh Chak, Michael Sivak Introduction: In practice, not all patients with acute UGIB can receive urgent EGD (within 12 hours). A model for predicting need for urgent EGD based on nonendoscopic, clinical variables would be an important tool in patient triage. We have previously shown that ANN accurately predicts outcome in acute LGI bleeding (Lancet 2003;362:1261). Methods: We constructed an ANN to predict endoscopic stigmata of recent hemorrhage (SRH) and need for endoscopic therapy (ET) using prospectively collected data from 194 patients at an academic medical center who presented with acute UGIB over a 6-month period (training group). Confirmed variceal bleeding was excluded. The ANN model was a multi-layered perceptron network trained by back propagation using pre-endoscopic clinical input variables available at the time of triage. The trained ANN was applied to an internal validation (IV) group of 193 patients with UGIB during the same time period. The ANN was then applied to an external validation (EV) group of 200 patients at a tertiary care center in a different city over a 6-month period. The performance of the ANN was also compared to the widely used Rockall score. A pre-endoscopic Rockall score of 0 is considered low risk for adverse outcome. Results: The clinical characteristics of the EV group were different then the training and IV groups (increased men, CAD, cirrhosis, hematemesis, shock, ICU admit, rebleeding, and death). Using ANN, the areas under the ROC curve for predicting SRH and ETwere 0.94 & 0.84 in the IV group and 0.81 & 0.78 in the EV group, respectively. ANN had better specificity and predictive values than pre-endoscopic Rockall score in both validation groups and was comparable to total (post-endoscopic) Rockall score. Conclusions: ANN is an effective tool in the pre-endoscopic triage of patients with acute UGIB, even in a dissimilar external cohort. ANN is more specific than the preendoscopic Rockall score in identifying patients who may benefit from urgent EGD and may be used to exclude low risk patients.