Identification of pancreatic cancer risk factors from clinical notes using natural language processing.

OBJECTIVES: Screening for pancreatic ductal adenocarcinoma (PDAC) is considered in high-risk individuals (HRIs) with established PDAC risk factors, such as family history and germline mutations in PDAC susceptibility genes. Accurate assessment of risk factor status is provider knowledge-dependent and requires extensive manual chart review by experts. Natural Language Processing (NLP) has shown promise in automated data extraction from the electronic health record (EHR). We aimed to use NLP for automated extraction of PDAC risk factors from unstructured clinical notes in the EHR. METHODS: We first developed rule-based NLP algorithms to extract PDAC risk factors at the document-level, using an annotated corpus of 2091 clinical notes. Next, we further improved the NLP algorithms using a cohort of 1138 patients through patient-level training, validation, and testing, with comparison against a pre-specified reference standard. To minimize false-negative results we prioritized algorithm recall. RESULTS: In the test set (n = 807), the NLP algorithms achieved a recall of 0.933, precision of 0.790, and F1-score of 0.856 for family history of PDAC. For germline genetic mutations, the algorithm had a high recall of 0.851, while precision and F1-score were lower at 0.350 and 0.496 respectively. Most false positives for germline mutations resulted from erroneous recognition of tissue mutations. CONCLUSIONS: Rule-based NLP algorithms applied to unstructured clinical notes are highly sensitive for automated identification of PDAC risk factors. Further validation in a large primary-care patient population is warranted to assess real-world utility in identifying HRIs for pancreatic cancer screening.

Artificial intelligence assisted whole organ pancreatic fat estimation on magnetic resonance imaging and correlation with pancreas attenuation on computed tomography.

BACKGROUND: Fatty pancreas is associated with inflammatory and neoplastic pancreatic diseases. Magnetic resonance imaging (MRI) is the diagnostic modality of choice for measuring pancreatic fat. Measurements typically use regions of interest limited by sampling and variability. We have previously described an artificial intelligence (AI)-aided approach for whole pancreas fat estimation on computed tomography (CT). In this study, we aimed to assess the correlation between whole pancreas MRI proton-density fat fraction (MR-PDFF) and CT attenuation. METHODS: We identified patients without pancreatic disease who underwent both MRI and CT between January 1, 2015 and June 1, 2020. 158 paired MRI and CT scans were available for pancreas segmentation using an iteratively trained convolutional neural network (CNN) with manual correction. Boxplots were generated to visualize slice-by-slice variability in 2D-axial slice MR-PDFF. Correlation between whole pancreas MR-PDFF and age, BMI, hepatic fat and pancreas CT-Hounsfield Unit (CT-HU) was assessed. RESULTS: Mean pancreatic MR-PDFF showed a strong inverse correlation (Spearman -0.755) with mean CT-HU. MR-PDFF was higher in males (25.22 vs 20.87; p = 0.0015) and in subjects with diabetes mellitus (25.95 vs 22.17; p = 0.0324), and was positively correlated with age and BMI. The pancreatic 2D-axial slice-to-slice MR-PDFF variability increased with increasing mean whole pancreas MR-PDFF (Spearman 0.51; p < 0.0001). CONCLUSION: Our study demonstrates a strong inverse correlation between whole pancreas MR-PDFF and CT-HU, indicating that both imaging modalities can be used to assess pancreatic fat. 2D-axial pancreas MR-PDFF is variable across slices, underscoring the need for AI-aided whole-organ measurements for objective and reproducible estimation of pancreatic fat.

Primary Sclerosing Cholangitis-Associated Pouchitis: A Distinct Clinical Phenotype.

BACKGROUND & AIMS: Patients with primary sclerosing cholangitis (PSC) commonly undergo ileal pouch-anal anastomosis (IPAA) for medically-refractory ulcerative colitis (UC) or colorectal dysplasia. Pouchitis develops more frequently in patients with PSC, potentially leading to increased morbidity. We aimed to assess clinical characteristics and treatment outcomes for pouchitis in patients with PSC compared to a matched, non-PSC cohort. METHODS: All patients with PSC who underwent IPAA and were diagnosed with pouchitis (PSC-pouchitis) were identified. A matched cohort composed of non-PSC patients who underwent IPAA for UC and subsequently developed pouchitis (UC-pouchitis) was developed. Relevant demographic, clinical, endoscopic, histologic, and treatment data were collected and compared between groups. RESULTS: Of those with PSC-pouchitis (n=182), 53.9% and 46.1% underwent IPAA for medically-refractory disease and dysplasia, respectively, compared to 88.7% and 11.3% in the UC-pouchitis group (P < .001). Patients with PSC-pouchitis were more likely to develop chronic pouchitis (68.1% vs 34.1%; P < .001), have moderate-to-severe pouch inflammation (54.9% vs 32.4%; P < .001), and prepouch ileitis (34.1% vs 11.5%; P < .001) compared to UC-pouchitis. Of those with PSC-pouchitis, 50.6% and 17.6% developed chronic antibiotic-dependent or antibiotic-refractory pouchitis, respectively, compared to 25.8% and 7.7% with UC-pouchitis. There was no difference in treatment response between the two groups with use of thiopurines, anti-tumor necrosis factor agents, and newer biologics. CONCLUSIONS: PSC-associated pouchitis presents with a unique clinical phenotype, characterized by increased risk of chronic pouchitis, moderate-to-severe pouch inflammation, prepouch ileitis, and less response to conventional antimicrobial therapy.

Determining age and sex-specific distribution of pancreatic whole-gland CT attenuation using artificial intelligence aided image segmentation: Associations with body composition and pancreatic cancer risk.

BACKGROUND & AIMS: Increased intrapancreatic fat is associated with pancreatic diseases; however, there are no established objective diagnostic criteria for fatty pancreas. On non-contrast computed tomography (CT), adipose tissue shows negative Hounsfield Unit (HU) attenuations (-150 to -30 HU). Using whole organ segmentation on non-contrast CT, we aimed to describe whole gland pancreatic attenuation and establish 5th and 10th percentile thresholds across a spectrum of age and sex. Subsequently, we aimed to evaluate the association between low pancreatic HU and risk of pancreatic ductal adenocarcinoma (PDAC). METHODS: The whole pancreas was segmented in 19,456 images from 469 non-contrast CT scans. A convolutional neural network was trained to assist pancreas segmentation. Mean pancreatic HU, volume, and body composition metrics were calculated. The lower 5th and 10th percentile for mean pancreatic HU were identified, examining the association with age and sex. Pre-diagnostic CT scans from patients who later developed PDAC were compared to cancer-free controls. RESULTS: Less than 5th percentile mean pancreatic HU was significantly associated with increase in BMI (OR 1.07; 1.03-1.11), visceral fat (OR 1.37; 1.15-1.64), total abdominal fat (OR 1.12; 1.03-1.22), and diabetes mellitus type 1 (OR 6.76; 1.68-27.28). Compared to controls, pre-diagnostic scans in PDAC cases had lower mean whole gland pancreatic HU (-0.2 vs 7.8, p = 0.026). CONCLUSION: In this study, we report age and sex-specific distribution of pancreatic whole-gland CT attenuation. Compared to controls, mean whole gland pancreatic HU is significantly lower in the pre-diagnostic phase of PDAC.

EUS-guided gastrojejunostomy using a pre-existing PEG with jejunal extension for target bowel opacification.

Video 1Contrast instillation into the jejunum using the pre-existing jejunal extension tubing from the PEG with jejunal extension followed by lumen-apposing metal stent deployment under endosonographic vision, securing the gastrojejunostomy.

The Impact of Vedolizumab on Pre-Existing Extraintestinal Manifestations of Inflammatory Bowel Disease: A Multicenter Study.

BACKGROUND: There are limited data on how vedolizumab (VDZ) impacts extraintestinal manifestations (EIMs) in inflammatory bowel disease (IBD). The aim of this study was to determine the clinical outcomes of EIMs after initiation of VDZ for patients with IBD. METHODS: A multicenter retrospective study of patients with IBD who received at least 1 dose of VDZ between January 1, 2014 and August 1, 2019 was conducted. The primary outcome was the rate of worsening EIMs after VDZ. Secondary outcomes were factors associated with worsening EIMs and peripheral arthritis (PA) specifically after VDZ. RESULTS: A total of 201 patients with IBD (72.6% with Crohn disease; median age 38.4 years (interquartile range, 29-52.4 years); 62.2% female) with EIMs before VDZ treatment were included. The most common type of EIM before VDZ was peripheral arthritis (PA) (68.2%). Worsening of EIMs after VDZ occurred in 34.8% of patients. There were no statistically significant differences between the worsened EIM (n = 70) and the stable EIM (n = 131) groups in term of age, IBD subtype, or previous and current medical therapy. We found that PA was significantly more common in the worsening EIM group (84.3% vs 59.6%; P < 0.01). Worsening of EIMs was associated with a higher rate of discontinuation of VDZ during study follow-up when compared with the stable EIM group (61.4% vs 44%; P = 0.02). Treatment using VDZ was discontinued specifically because of EIMs in 9.5% of patients. CONCLUSIONS: Almost one-third of patients had worsening EIMs after VDZ, which resulted in VDZ discontinuation in approximately 10% of patients. Previous biologic use or concurrent immunosuppressant or corticosteroid therapy did not predict EIM course after VDZ.