Large language models' responses to liver cancer surveillance, diagnosis, and management questions: accuracy, reliability, readability.

PURPOSE: To assess the accuracy, reliability, and readability of publicly available large language models in answering fundamental questions on hepatocellular carcinoma diagnosis and management. METHODS: Twenty questions on liver cancer diagnosis and management were asked in triplicate to ChatGPT-3.5 (OpenAI), Gemini (Google), and Bing (Microsoft). Responses were assessed by six fellowship-trained physicians from three academic liver transplant centers who actively diagnose and/or treat liver cancer. Responses were categorized as accurate (score 1; all information is true and relevant), inadequate (score 0; all information is true, but does not fully answer the question or provides irrelevant information), or inaccurate (score - 1; any information is false). Means with standard deviations were recorded. Responses were considered as a whole accurate if mean score was > 0 and reliable if mean score was > 0 across all responses for the single question. Responses were also quantified for readability using the Flesch Reading Ease Score and Flesch-Kincaid Grade Level. Readability and accuracy across 60 responses were compared using one-way ANOVAs with Tukey's multiple comparison tests. RESULTS: Of the twenty questions, ChatGPT answered nine (45%), Gemini answered 12 (60%), and Bing answered six (30%) questions accurately; however, only six (30%), eight (40%), and three (15%), respectively, were both accurate and reliable. There were no significant differences in accuracy between any chatbot. ChatGPT responses were the least readable (mean Flesch Reading Ease Score 29; college graduate), followed by Gemini (30; college) and Bing (40; college; p < 0.001). CONCLUSION: Large language models provide complex responses to basic questions on hepatocellular carcinoma diagnosis and management that are seldomly accurate, reliable, or readable.

Accuracy of Information Provided by ChatGPT Regarding Liver Cancer Surveillance and Diagnosis.

ChatGPT did not reliably provide accurate information to 20 questions about liver cancer surveillance and diagnosis, as assessed by six physicians who actively diagnose and/or treat liver cancer. Answers deemed inaccurate commonly related to questions on specific LI-RADS categories and included contradictory or falsely reassuring, if not wrong, information.

Posttransplant Lymphoproliferative Disorder Isolated to the Adrenal Gland in a Liver Transplant Patient.

Posttransplant lymphoproliferative disorder (PTLD) is a serious complication that accounts for up to 20% of malignancies after solid organ transplantation. We describe a rare case of isolated PTLD in the adrenal gland occurring 7 months after liver transplant in a patient who developed a primary Epstein-Barr virus infection. He was treated with rituximab and his immunosuppression regimen was minimized. We review the incidence, pathogenesis, presentation, and management of PTLD in the liver-transplant population. Our case highlights the variation in the presentation of PTLD and the importance of a high index of suspicion among the at-risk group.

Acute Fatty Liver Disease of Pregnancy: Updates in Pathogenesis, Diagnosis, and Management.

Acute fatty liver of pregnancy (AFLP) is an obstetric emergency characterized by maternal liver failure and may have complications for the mother and fetus, including death. This review examines recent literature on the epidemiology, pathogenesis, diagnosis, and treatment of acute fatty liver of pregnancy. Pathogenesis of this disease has been linked to defects in fatty acid metabolism during pregnancy, especially in the setting of fetal genetic defects in fatty acid oxidation. The value of screening all patients for these genetic defects remains to be determined. Distinguishing AFLP from other high-risk liver diseases of pregnancy that have overlap features, such as HELLP and preeclampsia, can be challenging. Although sensitive diagnostic tools such as the Swansea criteria have been developed, further work is needed to diagnose AFLP more quickly. Although survival rates have improved in the past 30 years, delay in diagnosis and treatment of AFLP has life-threatening consequences; an algorithmic approach to AFLP may be a valuable resource for clinicians. Future epidemiological and long-term studies will improve our prediction of women at risk for developing AFLP and determine the long-term consequences of this condition.