Novel machine learning approach to predict and personalize length of stay for patients admitted with syncope from the emergency department

HIGHLIGHTS

SUMMARY

Hospitals in the United_States and worldwide rely on Diagnosis Related Groups (DRG) and Utilization Management services to reduce unnecessary and prolonged hospitalizations. This study aimed to design an effective and exploratory model to help ED physicians predict LoS for each patient presenting with syncope. Using a similar approach, the authors subjected a set of input variables to a series of computer training to predict which syncope patients would qualify for an observation unit (predicted hospital stay and amp;lt;48 h) versus an extended inpatient stay (>48 h). True positive (TP) decisions reflect correct . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or Email

Password

Remember me

Lost your password?

If you don't have an account, you can create one here.