|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Predicting readmissions of COPD patients using machine learning algorithms can help identify high-risk patients who are likely to be readmitted, and allow healthcare providers to intervene early and prevent readmissions. Achieving the highest accuracy in predicting readmission is a great achievement, but it's important to note that accuracy alone may not be the only important metric for evaluating the performance of the predictive models. Other metrics such as precision, recall, F1-score, and area under the prediction within 90 days using Machine Learning can provide a more comprehensive evaluation of the model's performance, particularly for imbalanced datasets where the number of readmissions is much lower than the number of non-readmissions. It's also important to ensure that the predictive models are interpretable and transparent, so that healthcare providers can understand how the models make predictions and use the information to guide their clinical decision-making. This can help build trust in the models and improve their adoption in clinical practice. Finally, developing accurate and interpretable predictive models for COPD readmissions using machine learning algorithms and deep learning methods can significantly improve the healthcare service and lead to better patient outcomes.
Keyword
Machine learning, readmissions, COPD, Classification algorithms
PDF Download (click here)
|
|
|
|
|