A novel model by researchers from the Massachusetts General Hospital, Boston, uses natural language processing to predict readmission risk by incorporating physical function, cognitive status, and psychosocial support--three areas that may impact readmission but are poorly captured with structured data sources.
The final model had 16 variables, a validated C-statistic of 0.74, and it was calibrated.
The model performed similarly to better performing models previously published with the added advantage of being based on clinically relevant factors and also automated and scalable, the researchers say.
Background: With the increasing focus on reducing hospital readmissions in the United States, numerous readmissions risk prediction models have been proposed, mostly developed through analyses of structured data fields in electronic medical records and administrative databases. Three areas that m...Read More >>