Prediction of hearing preservation after acoustic neuroma surgery based on SMOTE-XGBoost

Prior to the surgical removal of an acoustic neuroma, the majority of patients anticipate that their hearing will be preserved to the greatest possible extent following surgery. This paper pro-poses a postoperative hearing preservation prediction model for the characteristics of class-imbalanced hospital real data based on the extreme gradient boost tree (XGBoost). In order to eliminate sample imbalance, the synthetic minority oversampling technique (SMOTE) is applied to increase the number of underclass samples in the data. Multiple machine learning models are also used for the accurate pre-diction of surgical hearing preservation in acoustic neuroma patients. In comparison to research results from existing literature, the experimental results found the model proposed in this paper to be superior. In summary, the method this paper proposes can make a significant contribution to the development of personalized preoperative diagnosis and treatment plans for patients, leading to effective judgment for the hearing retention of patients with acoustic neuroma following surgery, a simplified long medical treatment process and saved medical resources.

Automated summary

This paper proposes a postoperative hearing preservation prediction model based on extreme gradient boost tree (XGBoost) for class-imbalanced hospital real data. The synthetic minority oversampling technique (SMOTE) is applied to address sample imbalance. Multiple machine learning models are used to accurately predict surgical hearing preservation in acoustic neuroma patients. Experimental results show that the proposed model outperforms existing research. In summary, this paper's method contributes significantly to the development of personalized preoperative diagnosis and treatment plans, allowing for effective judgment of hearing retention in patients with acoustic neuroma following surgery, simplifying the lengthy medical process, and saving medical resources.