Analysis of the power of common diagnostic tools in the management of acute pancreatitis

Radiomics and 256-slice-dual-energy CT in the automated diagnosis of mild acute pancreatitis: the innovation of formal methods and high-resolution CT

INTRODUCTION

Acute pancreatitis (AP) is a common disease, and several scores aim to assess its prognosis. Our study aims to automatically recognize mild AP from computed tomography (CT) images in patients with acute abdominal pain but uncertain diagnosis from clinical and serological data through Radiomic model based on formal methods (FMs).

METHODS

We retrospectively reviewed the CT scans acquired with Dual Source 256-slice CT scanner (Somatom Definition Flash; Siemens Healthineers, Erlangen, Germany) of 80 patients admitted to the radiology unit of Antonio Cardarelli hospital (Naples) with acute abdominal pain. Patients were divided into 2 groups: 40 underwent showed a healthy pancreatic gland, and 40 affected by four different grades (CTSI 0, 1, 2, 3) of mild pancreatitis at CT without clear clinical presentation or biochemical findings. Segmentation was manually performed. Radiologists identified 6 patients with a high expression of diseases (CTSI 3) to formulate a formal property (Rule) to detect AP in the testing set automatically. Once the rule was formulated, and Model Checker classified 70 patients into "healthy" or "unhealthy".

RESULTS

The model achieved: accuracy 81%, precision 78% and recall 81%. Combining FMs results with radiologists agreement, and applying the mode in clinical practice, the global accuracy would have been 100%.

CONCLUSIONS

Our model was reliable to automatically detect mild AP at primary diagnosis even in uncertain presentation and it will be tested prospectively in clinical practice.

Acute peripancreatic fluid collection in acute pancreatitis: Incidence, outcome, and association with inflammatory markers

Background

The hospital outcomes and predictors of acute peripancreatic fluid collection (APFC) have not been well-characterized. In this study, we aimed to investigate the clinical outcomes of APFC in patients with acute pancreatitis (AP) and the role of the systemic immune-inflammation index (SII), systemic inflammation response index (SIRI), and C-reactive protein (CRP) level in predicting the occurrence of APFC.

Methods

In this retrospective study, the complicated group (patients with APFC) and the uncomplicated group (patients without APFC) were compared for their clinical characteristics, hospital outcomes (mortality rate, intensive care unit admission rate, and length of hospital stay), pseudocyst formation, CRP levels, SII, and SIRI on admission and at 48 hours.

Results

Of 132 patients with AP, 51 (38.6%) had APFC and eight (6.1%) had pancreatic pseudocysts. Of 51 patients with APFC, 15.7% had pancreatic pseudocysts. Pseudocyst did not develop in the uncomplicated group. SII value at 48 h [median 859 (541-1740) x 109/L vs. 610 (343-1259) x 109/L, P = 0.01] and CRP level at 48 h [89 (40-237) mg/L vs. 38 (12-122) mg/L, P = 0.01] were higher in the complicated group than in the uncomplicated group. The length of hospital stay was longer in the complicated group, compared with the uncomplicated group [median 8 days (5-15), vs. 4 days (3-7), P < 0.001, respectively]. No significant difference was detected between the two study groups' mortality rates and intensive care unit admission rates.

Conclusions

While 38.6% of the AP patients had APFC, 6.1% of all patients and 15.7% of the patients with APFC had pancreatic pseudocysts. APFC was found to lengthen the hospital stay and to be associated with the SII value and CRP level measured at 48 h.

Corrigendum to "Analysis of the Power of Common Diagnostic Tools in the Management of Acute Pancreatitis"

[This corrects the article DOI: 10.1155/2014/438697.].