Key result
XGBoost model incorporating patient network features improves length of stay prediction accuracy to 0.375 R2.
Why the study?
Limited data at the point of admission makes it difficult to accurately forecast hospital length of stay to optimize medical resource allocation for elderly patients with chronic diseases.
Does integrating multimorbidity and patient similarity network features into machine learning models improve the prediction of hospital length of stay in elderly patients with chronic diseases at admission?
Observational (n=2,543,758)
Yes
Does integrating multimorbidity and patient similarity network features into machine learning models improve the prediction of hospital length of stay in elderly patients with chronic diseases at admission?
Integrating multimorbidity and patient similarity network features into machine learning models significantly improves the prediction of hospital length of stay for elderly patients with chronic diseases at admission.
Answers are grounded in this paper and cite their sources.
Network features may improve ML-based LOS prediction in elderly chronic disease patients; hypothesis-generating pending prospective validation.
BACKGROUND: An aging population with a burden of chronic diseases puts increasing pressure on health care systems. Early prediction of the hospital length of stay (LOS) can be useful in optimizing the allocation of medical resources, and improving healthcare quality. However, the data available at the point of admission (PoA) are limited, making it difficult to forecast the LOS accurately. METHODS: In this study, we proposed a novel approach combining network analytics and machine learning to predict the LOS in elderly patients with chronic diseases at the PoA. Two networks, including multimorbidity network (MN) and patient similarity network (PSN), were constructed and novel network features were created. Five machine learning models (eXtreme Gradient Boosting, Gradient Boosting Decision Tree, Random Forest, Linear Support Vector Machine, and Deep Neural Network) with different input feature sets were developed to compare their performance. RESULTS: The experimental results indicated that the network features can bring significant improvements to the performances of the prediction models, suggesting that the MN and PSN are useful for LOS predictions. CONCLUSION: Our predictive framework which integrates network science with data mining can forecast the LOS effectively at the PoA and provide decision support for hospital managers, which highlights the potential value of network-based machine learning in healthcare field.
No takes yet. Share an insight, caveat, or question.
Hu et al. (2022) conducted an observational in Chronic diseases (n=2,543,758). Machine learning with Multimorbidity Network and Patient Similarity Network features vs. Baseline features alone was evaluated on Length of stay prediction accuracy (R2). The XGBoost model incorporating Multimorbidity Network and Patient Similarity Network features achieved an R2 of 0.375 for predicting length of stay, improving performance over baseline models.
Synapse has enriched 10 related papers. Consider them for comparative context: