ABSTRACT
Background/Aims@#We aimed to evaluate the histologic features predictive of prognosis and correlate them with endoscopic findings in patients with ulcerative colitis (UC) having complete or partial mucosal healing (MH). @*Methods@#We prospectively collected and reviewed data from patients with UC who underwent colonoscopy or sigmoidoscopy with biopsy. Complete and partial MH were defined as Mayo endoscopic subscores (MESs) of 0 and 1, respectively. Histologic variables, including the Nancy index (NI), predicting disease progression (defined as the need for medication upgrade or hospitalization/surgery), were evaluated and correlated with endoscopic findings. @*Results@#Overall, 441 biopsy specimens were collected from 194 patients. The average follow-up duration was 14.7 ± 7.4 months. There were 49 (25.3%) and 68 (35.1%) patients with MESs of 0 and 1, respectively. Disease progression occurred only in patients with an MES of 1. NI ≥ 3 was significantly correlated with disease progression during follow-up. Mucosal friability on endoscopy was significantly correlated with NI ≥ 3 (61.1% in NI < 3 vs. 88.0% in NI ≥ 3; p = 0.013). @*Conclusions@#Histological activity can help predict the prognosis of patients with UC with mild endoscopic activity. Mucosal friability observed on endoscopy may reflect a more severe histological status, which can be a risk factor for disease progression.
ABSTRACT
Objective@#The number of deaths due to acute poisoning (AP) is on the increase. It is crucial to predict AP patient mortality to identify those requiring intensive care for providing appropriate patient care as well as preserving medical resources. The aim of this study is to predict the risk of in-hospital mortality associated with AP using an artificial neural network (ANN) model. @*Methods@#In this multicenter retrospective study, ANN and logistic regression models were constructed using the clinical and laboratory data of 1,304 patients seeking emergency treatment for AP. The ANN model was first trained on 912/1,304 (70%) randomly selected patients and then tested on the remaining 392/1,304 (30%). Receiver operating characteristic curve analysis was used to evaluate the mortality prediction of the two models. @*Results@#Age, endotracheal intubation status, and intensive care unit admission were significant predictors of mortality in patients with AP in the multivariate logistic regression model. The ANN model indicated age, Glasgow Coma Scale, intensive care unit admission, and endotracheal intubation status were critical factors among the 12 independent variables related to in-hospital mortality. The area under the receiver operating characteristic curve for mortality prediction was significantly higher in the ANN model compared to the logistic regression model. @*Conclusion@#This study establishes that the ANN model could be a valuable tool for predicting the risk of death following AP. Thus, it may facilitate effective patient triage and improve the outcomes.
ABSTRACT
Objective@#The number of deaths due to acute poisoning (AP) is on the increase. It is crucial to predict AP patient mortality to identify those requiring intensive care for providing appropriate patient care as well as preserving medical resources. The aim of this study is to predict the risk of in-hospital mortality associated with AP using an artificial neural network (ANN) model. @*Methods@#In this multicenter retrospective study, ANN and logistic regression models were constructed using the clinical and laboratory data of 1,304 patients seeking emergency treatment for AP. The ANN model was first trained on 912/1,304 (70%) randomly selected patients and then tested on the remaining 392/1,304 (30%). Receiver operating characteristic curve analysis was used to evaluate the mortality prediction of the two models. @*Results@#Age, endotracheal intubation status, and intensive care unit admission were significant predictors of mortality in patients with AP in the multivariate logistic regression model. The ANN model indicated age, Glasgow Coma Scale, intensive care unit admission, and endotracheal intubation status were critical factors among the 12 independent variables related to in-hospital mortality. The area under the receiver operating characteristic curve for mortality prediction was significantly higher in the ANN model compared to the logistic regression model. @*Conclusion@#This study establishes that the ANN model could be a valuable tool for predicting the risk of death following AP. Thus, it may facilitate effective patient triage and improve the outcomes.