A combined predictive model using structured and unstructured data yielded an AUC of 0.6447 for predicting heart failure readmission, offering up to 70% net benefit over alternative strategies.
Cohort (n=1,629)
Sí
Does a combined predictive model using structured and unstructured data improve the prediction of readmission risk in heart failure patients?
Combining structured EMR data with unstructured clinical notes via NLP provides greater net clinical benefit for predicting heart failure readmissions compared to using either data type alone.
Tasa de eventos absoluta: 0.6447% vs 0.6494%
Researchers have studied many models for predicting the risk of readmission for heart failure over the last decade. Most models have used a parametric statistical approach while a few have ventured into using machine learning methods such as statistical natural language processing. We created three predictive models by combining these two techniques for the cohort of 1,629 patients from six hosptials using structured data along with their 136,963 clinical notes till their index admission, stored in the EMR system over five years. The AUCs for structured and combined models were very close (0.6494 and 0.6447) and that for the unstructured model was 0.5219. The clinical impact of the models using decision curve analysis showed that, at a threshold predicted probability of 0.20, the combined model offered 15%, 30%, and 70% net benefit over its individual counterparts, treat-all, and treat-none strategy respectively.
Mahajan et al. (Tue,) conducted a cohort in Heart failure (n=1,629). Combined predictive model (structured and unstructured data) vs. Structured model, unstructured model, treat-all, and treat-none strategies was evaluated on Risk of readmission (AUC). A combined predictive model using structured and unstructured data yielded an AUC of 0.6447 for predicting heart failure readmission, offering up to 70% net benefit over alternative strategies.