Predicting Hospital Stay Length During COVID-19
Author Information
Author(s): Liu Yang, Liang Renzhao, Zhang Chengzhi
Primary Institution: Wuhan University
Hypothesis
This study aims to identify the primary factors impacting length of stay (LOS) for patients before and during the COVID-19 pandemic.
Conclusion
Machine learning is effective in predicting length of stay before and during the COVID-19 pandemic, providing valuable guidance for hospital resource allocation.
Supporting Evidence
- Machine learning models outperformed traditional statistical models in predicting length of stay.
- The top predictive factors for length of stay were out-of-pocket amount, medical insurance, and admission deplanement.
- XGBoost achieved the best performance among the machine learning algorithms used.
Takeaway
The study uses computer programs to guess how long patients will stay in the hospital, helping doctors plan better.
Methodology
The study collected electronic medical record data and employed six machine learning algorithms to predict the probability of length of stay.
Potential Biases
The model may not generalize well to populations outside of Wuhan, leading to potential inequities in treatment recommendations.
Limitations
The study is based on data from a single hospital, which may limit the generalizability of the findings.
Participant Demographics
The study included a diverse patient population from Wuhan, with various demographics and medical histories.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website