Survival in acute pancreatitis is a combination of therapy-associated and patient-related factors.
There are only few relevant methods for predicting fatal outcome in acute pancreatitis.
|The optimal prediction model was a logistic model with 4 variables.|
The Ranson, Imrie, Blamey, and APACHE II scores are practical for assessing the severity of the disease.
However, they are not sufficiently validated for predicting fatal outcome among patients with severe acute pancreatitis.
In this study, investigators from Finland developed a novel prediction model for predicting fatal outcome in the early phase of severe acute pancreatitis (SAP). They also compared this model with previously reported predictive systems.
The team evaluated the hospital records of 253 patients with SAP. They included 234 patients who had sufficient data, and constructed 5 logistic regression and 3 artificial neural network (ANN) models.
The team tested 2 of the models in 60 consecutive patients with SAP. They then compared these models with previously reported predictive systems.
The team determined that the optimal prediction model was a logistic model with 4 variables. These variables were age, highest serum creatinine value within 60 to 72 hours from primary admission, need for mechanical ventilation, and chronic health status.
In the validation set of 60 consecutive patients, the predictive accuracy was 0.862 for this model.
Predictive accuracy was 0.847 for the ANN model which used 8 variables, 0.817 for APACHE II, 0.781 for multiple organ dysfunction score, 0.655 for Ranson, and 0.536 for Imrie scores.
Dr Kimmo Halonena's team concluded, "Ranson and Imrie scores are inaccurate indicators of the mortality in SAP".
"A novel predictive model based on 4 variables can reach at least the same predictive performance as the APACHE II system with 14 variables".