Outcome analysis of patients with acute pancreatitis by using an artificial neural network.

RATIONALE AND OBJECTIVES: The authors performed this study to evaluate the ability of an artificial neural network (ANN) that uses radiologic and laboratory data to predict the outcome in patients with acute pancreatitis. MATERIALS AND METHODS: An ANN was constructed with data from 92 patients with acute pancreatitis who underwent computed tomography (CT). Input nodes included clinical, laboratory, and CT data. The ANN was trained and tested by using a round-robin technique, and the performance of the ANN was compared with that of linear discriminant analysis and Ranson and Balthazar grading systems by using receiver operating characteristic analysis. The length of hospital stay was used as an outcome measure. RESULTS: Hospital stay ranged from 0 to 45 days, with a mean of 8.4 days. The hospital stay was shorter than the mean for 62 patients and longer than the mean for 30. The 23 input features were reduced by using stepwise linear discriminant analysis, and an ANN was developed with the six most statistically significant parameters (blood pressure, extent of inflammation, fluid aspiration, serum creatinine level, serum calcium level, and the presence of concurrent severe illness). With these features, the ANN successfully predicted whether the patient would exceed the mean length of stay (Az = 0.83 +/- 0.05). Although the Az performance of the ANN was statistically significantly better than that of the Ranson (Az = 0.68 +/- 0.06, P < .02) and Balthazar (Az = 0.62 +/- 0.06, P < .003) grades, it was not significantly better than that of linear discriminant analysis (Az = 0.82 +/- 0.05, P = .53). CONCLUSION: An ANN may be useful for predicting outcome in patients with acute pancreatitis.

Reviewing the reviewers: comparison of review quality and reviewer characteristics at the American Journal of Roentgenology.

OBJECTIVE: The purpose of our study was to determine which manuscript reviewer characteristics are most strongly associated with reviewer performance as judged by editors of the American Journal of Roentgenology (AJR). MATERIALS AND METHODS: At the AJR, manuscript reviews are rated by the journal editors on a subjective scale from 1 (lowest) to 4, on the basis of the value, thoroughness, and punctuality of the critique. We obtained all scores for AJR reviewers and determined the average score for each reviewer. We also sent a questionnaire to 989 reviewers requesting specific information regarding the age, sex, radiology subspecialty, number of years serving as a reviewer, academic rank, and practice type of the reviewer. The demographic profiles were correlated with the average quality score for each reviewer. Statistical analysis included correlation analysis and analysis of variance modeling. Reviewer quality scores were also correlated with the scoring of individual reviews and ultimate disposition of 196 manuscripts sent to the AJR during the same period. RESULTS: Responses to the questionnaire were obtained from 821 reviewers (83.0%), for whom quality scores were available for 714 (87.0%). Correlation analysis shows that the quality score of reviewers strongly correlated with younger age (p = 0.001). A statistically significant correlation between quality score and practice type was seen (p = 0.008), with reviewers from academic institutions receiving higher scores. No significant correlation was found between quality score and sex (p = 0.72), years of reviewing (p = 0.26), academic rank (p = 0.10), or the ultimate disposition of the manuscript (p = 0.40). The quality score of the reviewers showed no variation by subspecialty (p = 0.99). CONCLUSION: The highest-rated AJR reviewers tended to be young and from academic institutions. The quality of peer review did not correlate with the sex, academic rank, or subspecialty of the reviewer.

Comparison of MR cholangiopancreatographic techniques with contrast-enhanced cholangiography in the evaluation of sclerosing cholangitis.

OBJECTIVE: The purpose of our study was to compare MR cholangiopancreatography and contrast-enhanced cholangiography in patients with sclerosing cholangitis. MATERIALS AND METHODS: Twenty patients with sclerosing cholangitis were evaluated on MR cholangiopancreatography using the single-shot fast spin-echo technique at 1.5 T. A group of 19 healthy volunteers underwent MR cholangiopancreatography as controls. Thick-slab (2-cm sections) coronal oblique and thin-slab (5-mm sections) interleaved straight coronal MR images were obtained. All patients with sclerosing cholangitis had an MR cholangiopancreatogram within 12 months of a contrast-enhanced cholangiogram (mean, 3.8 months). Seventy-five percent of patients had an MR cholangiopancreatogram within 3 months of the contrast-enhanced cholangiogram. The MR cholangiopancreatograms and contrast-enhanced cholangiograms were reviewed independently in a random fashion by two radiologists who were unaware of clinical history for the degree of ductal visualization and for the presence and location of strictures of the intrahepatic and extrahepatic bile ducts. All discrepancies were resolved by a consensus, and the contrast-enhanced cholangiograms were regarded as the gold standard. Statistically significant data were calculated using the signed rank test (p < 0.01), and agreement analysis was calculated using Cohen's kappa. RESULTS: All findings on MR cholangiopancreatograms in healthy subjects were interpreted as normal, and all findings on MR cholangiopancreatograms in patients with sclerosing cholangitis were interpreted as abnormal. When compared with the control group, scans of patients with sclerosing cholangitis usually showed good visualization (>50%) of the intrasegmental (86% vs 9%) and peripheral (67% vs 0%) intrahepatic ducts on thick-slab MR cholangiopancreatography. Thick-slab MR cholangiopancreatography showed good visualization in more ducts than contrast cholangiography (84% vs 70%; p = 0.10) and showed more strictured ducts than contrast cholangiography (47% vs 36%; p = 0.22). When comparing those ducts with good visualization on both MR cholangiopancreatography and contrast cholangiography, we found that disagreement occurred regarding 32% of ducts. Most of the discrepancies (60%) resulted when a stricture was noted on MR cholangiopancreatography but not on contrast-enhanced cholangiography. Good interobserver agreement (kappa > 0.4) was noted for detecting strictures of the extrahepatic, left hepatic, left medial, and right posterior ducts, with the greatest agreement for extrahepatic ductal strictures (kappa = 0.8). CONCLUSION: Thick-slab MR cholangiopancreatography is the best technique for depicting normal and strictured bile ducts and allows the differentiation of healthy patients from patients with sclerosing cholangitis. Although endoscopic retrograde cholangiopancreatography was considered the standard, MR cholangiopancreatography was superior for intrahepatic biliary ductal visualization. Therefore, this technique is of value in the diagnosis and follow-up of patients with sclerosing cholangitis.