Critical Appraisal of Content Quality of YouTube Videos on the Whipple Pancreaticoduodenectomy.

INTRODUCTION: The coronavirus pandemic has demonstrated profound issues with using the Internet to research health information. For patients recommended a complex operation, such as the Whipple pancreaticoduodenectomy, the quality of health information online has not been appraised. The objective of this study was to define the readability and content quality of YouTube search results for the Whipple pancreaticoduodenectomy. METHODS: The first 100 search results for "whipple procedure" less than 10 min long in English with audio and or text were transcribed. The Flesch-Kincaid Grade defined the reading grade level. High content quality videos were accredited by YouTube in accordance with principles specified by the National Academy of Medicine or mentioned the standard components for a surgical consent. The Anderson-Lau score is a composite of these consent criteria out of a maximum of 8/8. The simplicity of videos for patient education was defined by the DISCERN tool. RESULTS: The reading level of 23% of the top 100 search results met the American average (8th grade). Accreditation was present for 45% and associated with an earlier median search ranking (36 versus 68, P = 0.002) and more 5th-8th grade level material (70% versus 38%, P = 0.014). The median Anderson-Lau score was 3/8 (range = 0/8-7/8) with only 5% achieving 7/8. Only 4% were high quality per DISCERN. CONCLUSIONS: Although accredited videos were more readable, most videos, especially those targeting patients, were beyond the comprehension of the average American. Simpler and higher quality educational materials are needed to inform patients on Whipple pancreaticoduodenectomy beyond their date of clinical diagnosis or surgical consenting.

Development of a portable device to quantify hepatic steatosis in potential donor livers.

An accurate estimation of liver fat content is necessary to predict how a donated liver will function after transplantation. Currently, a pathologist needs to be available at all hours of the day, even at remote hospitals, when an organ donor is procured. Even among expert pathologists, the estimation of liver fat content is operator-dependent. Here we describe the development of a low-cost, end-to-end artificial intelligence platform to evaluate liver fat content on a donor liver biopsy slide in real-time. The hardware includes a high-resolution camera, display, and GPU to acquire and process donor liver biopsy slides. A deep learning model was trained to label and quantify fat globules in liver tissue. The algorithm was deployed on the device to enable real-time quantification and characterization of fat content for transplant decision-making. This information is displayed on the device and can also be sent to a cloud platform for further analysis.