Medical management or surgery for acute cholecystitis: Enhancing treatment selection with decision trees.

BACKGROUND

This study aimed to create an algorithm using the decision tree method to classify patients with suspected acute cholecystitis into those who may improve with medical treatment, those who should undergo surgery for acute cholecystitis, and those with complicated cholecystitis, using laboratory parameters alone.

METHODS

A total of 1,352 patients treated for acute cholecystitis at our hospital over four years were retrospectively analyzed. Patients were divided into groups based on whether they received medical treatment or surgery. Various demographic and laboratory parameters were recorded. A decision tree algorithm was used to classify patients based on these parameters. Statistical analyses were performed using SPSS, and the decision tree's performance was evaluated with 10-fold cross-validation. An additional decision tree was created for gangrenous cholecystitis using the same methods.

RESULTS

The decision tree identified the platelet-to-lymphocyte ratio (PLR) as the most critical parameter for distinguishing between patients requiring surgery and those suitable for conservative treatment. The algorithm demonstrated an 82.17% diagnostic accuracy for predicting operative need and a 73.86% accuracy for identifying gangrenous cholecystitis. C-reactive protein (CRP) levels, platelet (PLT) values, white blood cell (WBC) counts, and patient age were also significant factors in the decision-making process. The neutrophil-to-lymphocyte ratio (NLR) was the most useful for diagnosing necrosis.

CONCLUSION

The decision tree algorithm effectively differentiates between uncomplicated and complicated cholecystitis using easily obtainable laboratory parameters. This method offers a cost-effective, rapid alternative to imaging studies, facilitating timely and appropriate treatment decisions, ultimately improving patient outcomes and reducing healthcare costs.