Enhancing the Performance of Multi-Objective Regression for Pelvic Organ Prolapse Prediction via Data Augmentation

In healthcare, machine learning has been increasingly applied to predictive models, but the efficacy of these models is often compromised due to limitations in data quality, diversity, and metrics. In other domains, such as image recognition and natural language processing, data augmentation techniques have been successfully applied to mitigate these challenges, but in healthcare such strategies have not been widely applied. Therefore, our research actively explores how these data augmentation techniques can be applied to machine learning models for predicting the outcome of pelvic organ prolapse surgery. We first performed in-depth data preprocessing and then tried innovative data enhancement techniques such as noise injection and self-sampling. The results show that the application of data enhancement techniques significantly improves the performance of predictive models and effectively addresses data scarcity and quality issues, which opens up new possibilities for wider application of data enhancement techniques in the medical field in the future.