Anesthesia Prediction For Optimizing Patient Sedation Using Support Vector Regression,XG Boost And Transformer Model

To maximize patient safety and comfort during medical procedures, effective anesthesia management requires closely monitoring and administering anesthesia for every procedure performed. If medications are not given to the appropriate degree of sedation, there could be potential complications or issues with correctly and efficiently completing the procedure. This paper will cover the development of an AI-based system using machine learning algorithms, including support vector regression (SVR), extreme gradient boosting (XGBoost), and transformer-based (Txb) models, to predict dosage(s) of anesthesia based on clinical information from the patient (demographics/vital signs/medical history) as well as characteristics associated with the procedure. Previous experiments have shown that the advanced machine learning methods discussed above yield greater accuracy and reliability than established methodology currently employed in anesthesia practice to estimate ideal anesthesia dosages. The proposed system will allow anesthesiologists to determine the appropriate dosage(s) of anesthesia to reduce exposure to risk and improve healthcare delivery efficiency through quality data to support better informed decisions.