Diagnostic Workup and Therapeutic Intervention of Hiatal Hernias Discovered as Incidental Findings on Computed Tomography.

BACKGROUND: Computed tomography imaging routinely detects incidental findings; most research focuses on malignant findings. However, benign diseases such as hiatal hernia also require identification and follow-up. Natural language algorithms can help identify these non-malignant findings. METHODS: Imaging of adult trauma patients from 2010 to 2020 who underwent CT chest/abdomen/pelvis was evaluated using an open-source natural language processor to query for hiatal hernias. Patients who underwent subsequent imaging, endoscopy, fluoroscopy, or operation were retrospectively reviewed. RESULTS: 1087(10.6%) of 10 299 patients had incidental hiatal hernias: 812 small (74.7%) and 275 moderate/large (25.3%). 224 (20.7%) had subsequent imaging or endoscopic evaluation. Compared to those with small hernias, patients with moderate/large hernias were older (66.3 ± 19.4 vs 79.6 ± 12.6 years, P < .001) and predominantly female (403[49.6%] vs 199[72.4%], P < .001). Moderate/large hernias were not more likely to grow (small vs moderate/large: 13[7.6%] vs 8[15.1%], P = .102). Patients with moderate/large hernias were more likely to have an intervention or referral (small vs moderate/large: 6[3.5%] vs 7[13.2%], P = .008). No patients underwent elective or emergent hernia repair. Three patients had surgical referral; however, only one was seen by a surgeon. One patient death was associated with a large hiatal hernia. CONCLUSIONS: We demonstrate a novel utilization of natural language processing to identify patients with incidental hiatal hernia in a large population, and found a 10.6% incidence with only 1.2%. (13/1087) of these receiving a referral for follow-up. While most incidental hiatal hernias are small, moderate/large and symptomatic hernias have high risk of loss-to-follow-up and need referral pipelines to improve patient outcomes.

Utilization of Natural Language Processing Software to Identify Worrisome Pancreatic Lesions.

BACKGROUND: Computed tomography (CT) imaging is routinely obtained for diagnostics, especially in trauma and emergency rooms, often identifying incidental findings. We utilized a natural language processing (NLP) algorithm to quantify the incidence of clinically relevant pancreatic lesions in CT imaging. PATIENTS AND METHODS: We utilized the electronic medical record to perform a retrospective chart review of adult patients admitted for trauma to a level 1 tertiary care center between 2010 and 2020 who underwent abdominal CT imaging. An open-source NLP software was used to identify patients with intrapapillary mucinous neoplasms (IPMN), pancreatic cysts, pancreatic ductal dilation, or pancreatic masses after optimizing the algorithm using a test group of patients who underwent pancreatic surgery. RESULTS: The algorithm identified pancreatic lesions in 27 of 28 patients who underwent pancreatic surgery and excluded 1 patient who had a pure ampullary mass. The study cohort consisted of 18,769 patients who met our inclusion criteria admitted to the hospital. Of this population, 232 were found to have pancreatic lesions of interest. There were 48 (20.7%) patients with concern for IPMN, pancreatic cysts in 36 (15.5%), concerning masses in 30 (12.9%), traumatic findings in 44 (19.0%), pancreatitis in 41 (17.7%), and ductal abnormalities in 19 (18.2%) patients. Prior pancreatic surgery and other findings were identified in 14 (6.0%) patients. CONCLUSIONS: In this study, we propose a novel use of NLP software to identify potentially malignant pancreatic lesions annotated in CT imaging performed for other purposes. This methodology can significantly increase the screening and automated referral for the management of precancerous lesions.