Early Prediction of 30-day ICU Re-admissions Using Natural Language Processing and Machine Learning
This work addresses ICU readmission prediction for clinicians to potentially improve patient outcomes and reduce costs, but it is incremental as it applies existing methods to a specific healthcare domain.
The paper tackled the problem of predicting 30-day ICU readmissions by using natural language processing on discharge summaries and machine learning classifiers, achieving a competitive AUC of 0.748.
ICU readmission is associated with longer hospitalization, mortality and adverse outcomes. An early recognition of ICU re-admission can help prevent patients from worse situation and lower treatment cost. As the abundance of Electronics Health Records (EHR), it is popular to design clinical decision tools with machine learning technique manipulating on healthcare large scale data. We designed data-driven predictive models to estimate the risk of ICU readmission. The discharge summary of each hospital admission was carefully represented by natural language processing techniques. Unified Medical Language System (UMLS) was further used to standardize inconsistency of discharge summaries. 5 machine learning classifiers were adopted to construct predictive models. The best configuration yielded a competitive AUC of 0.748. Our work suggests that natural language processing of discharge summaries is capable to send clinicians warning of unplanned 30-day readmission upon discharge.