AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
Predicting hospital admission for Emergency Department (ED) patients at the time of triage may improve throughput. To predict admission we created and validated a Bayesian Network from 47,993 encounters (training: n=23,996, validation: n=9,599, test: n=14,398). The area under the receiver operator characteristic curve was 0.833 (0.8260.840) for the network and 0.790 (0.7810.799) for the control variable (acuity only). Predicting hospital admission early during an encounter may help anticipate ED workload and potential overcrowding.
-
AMIA Annu Symp Proc · Jan 2007
Using term frequency to identify trends in the media's coverage of health.
This poster describes a method of analyzing news reports to detect emerging trends in the media's coverage of health. The method examines term frequency and term usage in overall and health-specific news coverage. Term frequency calculation and analysis algorithms have been implemented in SalientNews, a news aggregation and analysis system. By using term frequency, SalientNews is now able to assist in the identification and analysis of emerging trends in the media's coverage of health.
-
Maintaining critically-ill patients' blood glucose levels within the normoglycemic range has been shown to reduce mortality and morbidity, but it has not been achieved consistently using existing insulin infusion protocols. This study examines blood glucose monitoring in an intensive care unit (ICU) and how blood glucose levels change in response to therapy. Our findings confirm the commonly observed poor compliance of blood glucose levels and motivate for more effective glycemic control.
-
AMIA Annu Symp Proc · Jan 2007
The effect of implementing computerized provider order entry on medication prescribing errors in an emergency department.
Medication errors are a major concern in the Emergency Department (ED). We examined medication prescribing errors among consecutive adult ED patients during two 10-day periods before and during one 9-day period after implementing computerized provider order entry in an adult ED. 2,073 patients had 5,950, orders. Before (after) implementation there were 3.7 (2.8) potential adverse drug events, 222.0 (21.0) medication prescribing errors, and 5.1 (0) rule violations per 100 orders.
-
AMIA Annu Symp Proc · Jan 2007
Predicting ambulance diversion in an adult Emergency Department using a Gaussian process.
When the Emergency Department (ED) reaches a critical level of overcrowding, it diverts ambulances to other hospitals. We evaluated the accuracy of a Gaussian process for prediction of ambulance diversion using March 1, 2005 November 30, 2005 data. The area under the receiver operating curve (AUC) for 120 minutes in advance was 0.93 (SE: 0.19). The instrument demonstrated a high AUC and may be used to alert ED managers earlier of a diversion episode.