Internal and emergency medicine
-
Machine learning, in particular deep learning, may be able to assist in the prediction of the length of stay and timing of discharge for individual patients. Artificial neural networks applied to medical text have previously shown promise in this area. In this study, a previously derived artificial neural network was applied to prospective and external validation datasets. ⋯ The performance in the prediction of discharge within the next 7 days was more limited (area under the receiver operator curve 0.68 and 0.67). This study has shown that in prospective and external validation datasets the previously derived deep learning algorithms have demonstrated moderate performance in the prediction of which patients will be discharged within the next 2 days. Future studies may seek to further refine or evaluate the effect of the implementation of such algorithms.
-
It is important to clarify the severity of acute pancreatitis (AP) in the early stages of the disease. The visceral adiposity index (VAI), calculated using the waist circumference (WC), body mass index (BMI), triglyceride (TG) levels, and high-density lipoprotein cholesterol (HDL-c), indirectly reflects visceral adiposity function and can be used to explore its value in evaluating and predicting the severity of hyperlipidaemic acute pancreatitis (HLAP). The VAIs of 227 patients with HLAP were calculated by retrospective analysis of body parameters and laboratory indicators. ⋯ The multivariate-adjusted odds ratio (HR) for the VAI in the relationship of body parameters and the severity of HLAP was 3.818 (95% CI, 1.395-10.452). Our study shows that the VAI is a valuable indicator for predicting and assessing the severity of hyperlipidaemic acute pancreatitis. Its increase is closely related to poor prognosis in patients with HLAP.