OBJECTIVE: To explore the predictive potential of serial computed tomography (CT) radiology reports for pancreatic cancer survival using natural language processing (NLP).
METHODS: Deep-transfer-learning-based NLP models were retrospectively trained and tested with serial, free-text CT reports, and survival information of consecutive patients diagnosed with pancreatic cancer in a Korean tertiary hospital was extracted. Randomly selected patients with pancreatic cancer and their serial CT reports from an independent tertiary hospital in the United States were included in the external testing data set. The concordance index (c-index) of predicted survival and actual survival, and area under the receiver operating characteristic curve (AUROC) for predicting 1-year survival were calculated.
RESULTS: Between January 2004 and June 2021, 2,677 patients with 12,255 CT reports and 670 patients with 3,058 CT reports were allocated to training and internal testing data sets, respectively. ClinicalBERT (Bidirectional Encoder Representations from Transformers) model trained on the single, first CT reports showed a c-index of 0.653 and AUROC of 0.722 in predicting the overall survival of patients with pancreatic cancer. ClinicalBERT trained on up to 15 consecutive reports from the initial report showed an improved c-index of 0.811 and AUROC of 0.911. On the external testing set with 273 patients with 1,947 CT reports, the AUROC was 0.888, indicating the generalizability of our model. Further analyses showed our model\'s contextual interpretation beyond specific phrases.
CONCLUSIONS: Deep-transfer-learning-based NLP model of serial CT reports can predict the survival of patients with pancreatic cancer. Clinical decisions can be supported by the developed model, with survival information extracted solely from serial radiology reports.

BACKGROUND: Pancreatic cancer risk has been associated with increased serum cholesterol level, which is in turn partially influenced by diet. This study aimed at evaluating the association between pancreatic cancer risk and the adherence to a plant-based cholesterol-lowering diet.
METHODS: Data were derived from an Italian case-control study including 258 pancreatic cancer patients and 551 controls. The cholesterol-lowering diet score was based on seven components: high intakes of (i) non-cellulosic polysaccharides (a proxy of viscous fibers), (ii) monounsaturated fatty acids, (iii) legumes, and (iv) seeds/corn oils (a proxy of phytosterols); and low intakes of (v) saturated fatty acids, (vi) dietary cholesterol, and (vii) food with a high glycemic index. The score was calculated adding one point for each fulfilled component, thus ranging from zero (no adherence) to seven (complete adherence). The odds ratios (ORs) and 95% confidence intervals (CIs) were estimated through the logistic regression model.
RESULTS: Scores 5-7 were associated with reduced cancer risk (OR = 0.30; 95% CI: 0.18-0.52) compared to scores 0-2.
CONCLUSIONS: Adherence to a plant-based cholesterol-lowering diet was associated with a reduced risk of pancreatic cancer.

BACKGROUND: Knowledge about environmental pancreatic adenocarcinoma (PA) risk factors, including pesticide exposure, remains limited. Organochlorine (OC) accumulates in adipose tissue and can help reflect long-term exposure.
METHODS: Age and body mass index (BMI) of patients with PA were matched with those undergoing a surgery for a benign disease on age and BMI (1:1). Targeted analyses screened 345 pesticides and metabolites, including 29 OC, in adipose tissue and urine samples. The primary aim was to investigate the association between organochlorine concentrations in visceral fat or urine, and PA. Adjusted conditional logistic regressions were carried out accounting for multiple testing.
RESULTS: Trans-nonachlor (odds ratio [OR] = 1.325, 95% confidence interval [CI] [1.108-1.586]), cis-nonachlor (OR = 15.433, 95% CI [2.733-87.136]), Mirex (OR = 2.853, 95% CI [1.213-6.713]) and 4,4 DDE (OR = 1.019, 95% CI [1.005-1.034]) in fat and a greater number of positive samples (OR = 1.758 95% CI [1.11-2.997]) were significantly associated with higher odds of PA. In contrast, as awaited, urine samples did not yield any statistically significant associations for all tested pesticides.
CONCLUSIONS: Some OCs were associated with higher odds of PA. The underlying mechanisms of pancreatic aggression need to be investigated to refine these findings.
BACKGROUND: Clinicaltrials.gov NCT04429490.

BACKGROUND Minimally invasive pancreatectomy has become the standard practice for the management of benign and malignant pancreatic tumors. Techniques such as robotic and laparoscopic approaches are known to reduce morbidity by offering benefits such as less blood loss, reduced pain, shorter hospital stays, and quicker recovery times. The indication for repeated minimally invasive pancreatectomy for recurrent or de novo pancreatic neoplasm after primary pancreatic surgery remains debated. CASE REPORT A 50-year-old woman was admitted to our hospital with a diagnosis of an intraductal papillary mucinous neoplasm in the pancreatic head. In 2010, she underwent laparoscopic single-branch resection for a branch-type tumor in the pancreatic uncinate process. During a 5-year follow-up, a de novo intraductal papillary mucinous neoplasm was detected, showing gradual growth and the presence of a mural nodule over the next 7 years. The patient\'s CEA level was elevated to 7.0 ng/mL. Considering the tumor\'s progression and the appearance of a mural nodule, we recommended a robot-assisted Whipple procedure. The operation began with laparoscopic adhesiolysis. After detachment of the adhesions and remobilization of the duodenum using the Kocher maneuver, the operation continued with the Da Vinci surgical system. The postoperative period was uneventful, and the patient was discharged on postoperative day 20. Pathological examination revealed intraductal papillary mucinous carcinoma in situ with negative resection margins. CONCLUSIONS This case verifies the safety and feasibility of performing a robotic Whipple procedure for a newly diagnosed pancreatic neoplasm in patients who have previously undergone minimally invasive pancreatic surgery.

UNASSIGNED: Multiple Endocrine Neoplasia type 1 (MEN1) is an autosomal dominant disorder marked by pathogenic variants in the MEN1 tumor suppressor gene, leading to tumors in the parathyroid glands, pancreas, and pituitary. The occurrence of ACTH-producing pancreatic neuroendocrine carcinoma is exceedingly rare in MEN1.
UNASSIGNED: This report details a Colombian family harboring a novel MEN1 variant identified through genetic screening initiated by the index case. Affected family members exhibited primary hyperparathyroidism (PHPT) symptoms from their 20s to 50s. Uniquely, the index case developed an ACTH-secreting pancreatic neuroendocrine carcinoma, a rarity in MEN1 syndromes. Proactive screening enabled the early detection of pituitary neuroendocrine tumors (PitNETs) as microadenomas in two carriers, with subsequent surgical or pharmacological intervention based on the clinical presentation.
UNASSIGNED: Our findings underscore the significance of cascade screening in facilitating the early diagnosis and individualized treatment of MEN1, contributing to better patient outcomes. Additionally, this study brings to light a novel presentation of ACTH-producing pancreatic neuroendocrine carcinoma within the MEN1 spectrum, expanding our understanding of the disease\'s manifestations.

Insulinoma is the most common functional neuroendocrine tumor of the pancreas, with the main clinical symptom being hypoglycemia. The standard treatment is surgery, but some patients are not eligible for surgery, while in those operated on, the risk of perioperative complications is up to 30%. Diazoxide treatment to prevent hypoglycemia is effective only in 50% of patients. To prevent tumor growth and hormonal excess, stereotactic radiotherapy may be an alternative to surgical treatment. In our paper, we present two cases of patients with insulinoma treated successfully with stereotactic body radiation therapy (SBRT).

Primary pancreatic lymphomas (PPLs) are a subgroup of gastrointestinal (GI) lymphomas. They are an exceedingly rare entity, both in terms of pancreatic malignancies and also extranodal lymphomas. Epidemiological investigations have been challenging to do because of their rarity. This has resulted in a lack of clarity on the clinicopathological characteristics, differential diagnosis, best course of treatment, and prognosis of PPL. Because the clinical signs are frequently non-specific, it can lead to a diagnostic hazard for the unwary physician. Preoperatively, it is imperative to distinguish between adenocarcinoma and PPL, as they present similarly, but have vastly different treatment modalities and prognosis. We herein present a case of an elderly man who presented with obstructive jaundice and was found to have PPL.

Pancreatic ductal adenocarcinoma (PDAC) is an aggressive disease with poor survival. Novel biomarkers are urgently needed to improve the outcome through early detection. Here, we aimed to discover novel biomarkers for early PDAC detection using multi-omics profiling in pre-diagnostic plasma samples biobanked after routine health examinations. A nested case-control study within the Northern Sweden Health and Disease Study was designed. Pre-diagnostic plasma samples from 37 future PDAC patients collected within 2.3 years before diagnosis and 37 matched healthy controls were included. We analyzed metabolites using liquid chromatography mass spectrometry and gas chromatography mass spectrometry, microRNAs by HTG edgeseq, proteins by multiplex proximity extension assays, as well as three clinical biomarkers using milliplex technology. Supervised and unsupervised multi-omics integration were performed as well as univariate analyses for the different omics types and clinical biomarkers. Multiple hypothesis testing was corrected using Benjamini-Hochberg\'s method and a false discovery rate (FDR) below 0.1 was considered statistically significant. Carbohydrate antigen (CA) 19-9 was associated with PDAC risk (OR [95 % CI] = 3.09 [1.31-7.29], FDR = 0.03) and increased closer to PDAC diagnosis. Supervised multi-omics models resulted in poor discrimination between future PDAC cases and healthy controls with obtained accuracies between 0.429-0.500. No single metabolite, microRNA, or protein was differentially altered (FDR < 0.1) between future PDAC cases and healthy controls. CA 19-9 levels increase up to two years prior to PDAC diagnosis but extensive multi-omics analysis including metabolomics, microRNAomics and proteomics in this cohort did not identify novel early biomarkers for PDAC.

An 87-year-old woman presented to the emergency department with left thigh pain, and sciatic nerve pain was diagnosed. A chest CT scan showed bronchiectasis and tree-in buds and an acid-fast stain test of gastric juice was positive; further, M. avium-PCR of sputum and culture results were positive leading to a diagnosis of pulmonary nontuberculous mycobacterial infection(NTM). Abdominal CT showed dilatation of the main pancreatic duct and a multifocal cystic tumor in the pancreatic tail, which was found to be complicated with an intraductal papillary mucinous tumor(IPMN).

Distal pancreatectomy with splenectomy is considered the standard operation for pancreas tail and body cancer. However, splenectomy may be option for benign or low-grade malignant tumors including mucinous cystadenoma and intraductal papillary mucinous neoplasm. If spleen-preserving distal pancreatectomy (SPDP) with borderline lesion is performed and pancreas cancer is diagnosed on postoperative pathologic finding, if it is R0 resection, the necessity of additional splenectomy remains questionable. The authors would like report two clinical cases diagnosed as pancreatic cancer on postoperative pathology after SPDP and under observation without additional splenectomy.