The article discusses the critical issue of hospital readmissions, focusing on the use of text mining and advanced machine learning techniques to predict readmissions within 30 days of discharge. The authors applied the Bio-Discharge Summary Bert (BDSS) model in combination with principal component analysis (PCA) to preprocess data from electronic health records. Their findings from the MIMIC-III dataset indicate that their predictive model, which uses a multilayer perceptron, demonstrates significant performance, achieving a recall of 94% and an area under the curve of 75%. This research illustrates the potential of integrating text mining and deep learning to enhance patient care and resource allocation in healthcare settings.
This study focuses on predicting patient readmission within less than 30 days using text mining techniques applied to discharge report texts from electronic health records (EHR).
A novel aspect of this research involves leveraging the Bio-Discharge Summary Bert (BDSS) model along with principal component analysis (PCA) feature extraction to preprocess data for deep learning model input.
Our analysis of the MIMIC-III dataset indicates that our approach, which combines the BDSS model with a multilayer perceptron (MLP), outperforms state-of-the-art methods.
This study contributes to the advancement of predictive modeling in healthcare by integrating text mining techniques with deep learning algorithms to improve patient outcomes and optimize resource allocation.
Collection
[
|
...
]