A data-driven approach to forecast the length of stay and overall treatment cost for resistant bacterial infections.

Abstract The length of stay (LOS) and healthcare expenses for patients are drastically impacted by antimicrobial resistance (AMR). In addition to building a prediction model for AMR infection outcomes, the study will examine how AMR influences the attributable cost and length of stay in hospitalized patients. WEKA-ML version 3.8.6 was used to build the models. The discretization of LOS and cost into distinct bins is normalized. Utilizing a number of feature selection techniques, the best characteristics associated with the outcome were selected. The optimal feature selection strategy was selected, and several methods were used to the training (66 percent / 80 percent) and test (34 percent /20 percent) data sets to prevent underfitting and overfitting. Using ROC curves, prediction error, and accuracy metrics, the best-predicted model is selected. In terms of forecasting LOS, RF performed better (accuracy=69.6, ROC=0.852) than bagging (accuracy=69.6, ROC=0.862) while using the cfs subset attribute evaluation+greedy stepwise approach and the Infogain+ranker method. The majority of patients fell between the ranges of 7 and 14 days. With 34% of test data sets, RF outperformed marginally better using the infogain attribute selection+ranker technique (Accuracy=80.8 ROC=0.967) in predicting cost. Most fell into the >$1720 range, then came the $814 range. Effective LOS and treatment cost prediction for resistant infections gives crucial data that helps hospital administration, and the medical staff make crucial decisions. While avoiding a significant loss of resources, hospital administration can provide the appropriate and essential resources and the best medical team for treating the patient.