Apolipoprotein A2 isoforms associated with exocrine pancreatic insufficiency in early chronic pancreatitis

BACKGROUND AND AIM

Apolipoprotein A2 (apoA2) isoforms have been reported to undergo the aberrant processing in pancreatic cancer and pancreatic risk populations compared with that in healthy subjects. This study aimed to clarify whether apoA2 isoforms were as useful as N-benzoyl-p-aminobenzoic acid (BT-PABA) test for exocrine pancreatic dysfunction markers in patients with early chronic pancreatitis (ECP).

METHODS

Fifty consecutive patients with functional dyspepsia with pancreatic enzyme abnormalities (FD-P) (n = 18), with ECP (n = 20), and asymptomatic patients with pancreatic enzyme abnormalities (AP-P) (n = 12) based on the Rome IV classification and the Japan Pancreatic Association were enrolled in this study. The enrolled patients were evaluated using endoscopic ultrasonography and endoscopic ultrasonography elastography. Five pancreatic enzymes were estimated. Pancreatic exocrine function was analyzed using the BT-PABA test. Lighter and heavier apoA2 isoforms, AT and ATQ levels were measured by enzyme-linked immunosorbent assay methods.

RESULTS

There were no significant differences in clinical characteristics such as age, gender, body mass index, alcohol consumption and smoking among patients with AP-P, FD-P, and ECP. The BT-PABA test and lighter apoA2 isoform, AT level in the enrolled patients had a significant correlation (P < 0.01). The BT-PABA test in patients with ECP was significantly lower (P = 0.04) than that in AP-P. ApoA2-AT level in patients with ECP was lower than that in AP-P, albeit, insignificantly. Interestingly, apo A2-AT level was significantly (P = 0.041) associated with exocrine pancreatic insufficiency by multiple logistic regression analysis.

CONCLUSIONS

ApoA2-AT level is a useful tool to evaluate exocrine pancreatic insufficiency in the early stage of chronic pancreatitis.

Octreotide-related exocrine pancreatic insufficiency (EPI) in congenital hyperinsulinism

Background Congenital hyperinsulinism (CH) is the most frequent cause of persistent hypoglycemia in the newborn. Octreotide, a long-acting somatostatin receptor analog (SSRA), is a second line treatment for diazoxide unresponsive CH patients. Although it has been found to be a safe and effective treatment, long-term benefits and side effects, have not been thoroughly evaluated. Case presentation Some authors have indicated that exocrine pancreatic insufficiency (EPI) is a common but under-recognized adverse reaction in adults treated with octreotide. However, no pediatric patient with SSRA-induced EPI has been reported to date. Here we report a case of an infant with diazoxide unresponsive, diffuse CH, caused by a heterozygous pathogenic paternally inherited mutation in the ABCC8 gene (NM_000352.4:c.357del), that developed exocrine pancreatic insufficiency and secondary vitamin K deficiency associated to chronic octreotide therapy. Conclusions We point out the atypical clinical onset with a cutaneous hemorrhagic syndrome, emphasizing the clinical relevance of this potential side effect.

Applying Machine Learning Techniques to Identify Undiagnosed Patients with Exocrine Pancreatic Insufficiency

BACKGROUND

Exocrine pancreatic insufficiency (EPI) is a serious condition characterized by a lack of functional exocrine pancreatic enzymes and the resultant inability to properly digest nutrients. EPI can be caused by a variety of disorders, including chronic pancreatitis, pancreatic cancer, and celiac disease. EPI remains underdiagnosed because of the nonspecific nature of clinical symptoms, lack of an ideal diagnostic test, and the inability to easily identify affected patients using administrative claims data.

OBJECTIVES

To develop a machine learning model that identifies patients in a commercial medical claims database who likely have EPI but are undiagnosed.

METHODS

A machine learning algorithm was developed in Scikit-learn, a Python module. The study population, selected from the 2014 Truven MarketScan® Commercial Claims Database, consisted of patients with EPI-prone conditions. Patients were labeled with 290 condition category flags and split into actual positive EPI cases, actual negative EPI cases, and unlabeled cases. The study population was then randomly divided into a training subset and a testing subset. The training subset was used to determine the performance metrics of 27 models and to select the highest performing model, and the testing subset was used to evaluate performance of the best machine learning model.

RESULTS

The study population consisted of 2088 actual positive EPI cases, 1077 actual negative EPI cases, and 437 530 unlabeled cases. In the best performing model, the precision, recall, and accuracy were 0.91, 0.80, and 0.86, respectively. The best-performing model estimated that the number of patients likely to have EPI was about 12 times the number of patients directly identified as EPI-positive through a claims analysis in the study population. The most important features in assigning EPI probability were the presence or absence of diagnosis codes related to pancreatic and digestive conditions.

CONCLUSIONS

Machine learning techniques demonstrated high predictive power in identifying patients with EPI and could facilitate an enhanced understanding of its etiology and help to identify patients for possible diagnosis and treatment.