RESUMEN
OBJECTIVE: To assess ChatGPT's capability of grading postoperative complications using the Clavien-Dindo classification (CDC) via Artificial Intelligence (AI) with Natural Language Processing (NLP). BACKGROUND: The CDC standardizes grading of postoperative complications. However, consistent, and precise application in dynamic clinical settings is challenging. AI offers a potential solution for efficient automated grading. METHODS: ChatGPT's accuracy in defining the CDC, generating clinical examples, grading complications from existing scenarios, and interpreting complications from fictional clinical summaries, was tested. RESULTS: ChatGPT 4 precisely mirrored the CDC, outperforming version 3.5. In generating clinical examples, ChatGPT 4 showcased 99% agreement with minor errors in urinary catheterization. For single complications, it achieved 97% accuracy. ChatGPT was able to accurately extract, grade, and analyze complications from free text fictional discharge summaries. It demonstrated near perfect performance when confronted with real-world discharge summaries: comparison between the human and ChatGPT4 grading showed a κ value of 0.92 (95% CI 0.82-1) (P<0.001). CONCLUSIONS: ChatGPT 4 demonstrates promising proficiency and accuracy in applying the CDC. In the future, AI has the potential to become the mainstay tool to accurately capture, extract, and analyze CDC data from clinical datasets.
RESUMEN
Malnutrition is a known risk factor for postoperative morbidity and mortality in patients awaiting liver transplantation (LT). Malnutrition is a potentially reversible risk factor, though there are no clear guidelines on the best mechanism for an improvement. It also remains unclear if preoperative nutritional interventions have benefits to post-transplant outcomes for transplant recipients. Primary objective: To identify if preoperative optimization of nutritional status is associated with improved short-term outcomes after LT. Secondary Objectives: To determine if preoperative improvement of malnutrition improves short-term outcomes after LT, as well as, if weight loss in obese patients affects short-term outcomes after LT. Ovid MEDLINE, Embase, Scopus, Google Scholar, and Cochrane Central. Systematic review following PRISMA guidelines and recommendations using the GRADE approach derived from an international expert panel. POSPERO Protocol ID: CRD42021237450 3851 records were identified in searching the databases, 3843 records were excluded by not fulfilling eligibility criteria. Seven full-text articles were included for the final analysis of which three were randomized controlled trials, one was prospective observational studies, and three were retrospective observational studies. No appreciable difference in mortality, post-transplant complication rate was noted across the studies. Length of stay (LOS) was noted to be shorter in two observational studies of Vitamin D deficiency in liver transplant patients. We have made a weak recommendation supporting pre-transplant nutritional supplementation due to possible benefit in reducing LOS as well as the lack of harms (Quality of Evidence low | Grade of Recommendation; Weak). No effective conclusions were reached for the secondary objectives due to the conflicting evidence.