AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
AMIA Annu Symp Proc · Jan 2006
Developing an intelligent phone-based emergency triage communication and support system.
In this study, the emergency triage support system was taken as an example. We develop new call flow style and combine traditional passive call flow. ⋯ Then the recognition term come from voice term database. Voice management center is an ER triage decision system.
-
AMIA Annu Symp Proc · Jan 2006
An early warning system for overcrowding in the emergency department.
Overcrowding of emergency departments impedes health care access and quality nationwide. A real-time early warning system for overcrowding may allow administrators to alleviate the problem before reaching a crisis state. Two original probabilistic models - a logistic regression and a recurrent neural network - were created to predict overcrowding crises one hour in the future. ⋯ All models showed high discriminatory ability in terms of area under the receiver operating characteristic curve (logistic regression = .954; recurrent neural network = .957; EDWIN = .879; NEDOCS = .924). At comparable rates of false alarms, the logistic regression gave more advance notice of crises than other models (logistic regression = 62 min; recurrent neural network = 13 min; EDWIN = 0 min; NEDOCS = 0 min). These results demonstrate the feasibility of using models based on key operational variables to anticipate overcrowding crises in real time.
-
AMIA Annu Symp Proc · Jan 2006
Comparative StudyEvaluating the safety and efficiency of a CPOE system for continuous medication infusions in a pediatric ICU.
Critically ill children often require continuous intravenous infusions of life-supporting medications. The complexity of ordering such infusions makes this an error prone process, and such errors can result in serious adverse events. A CPOE system was developed and evaluated to assess its impact on the safety and efficiency of prescribing continuous medication infusions.
-
AMIA Annu Symp Proc · Jan 2006
Combining image features, case descriptions and UMLS concepts to improve retrieval of medical images.
This paper evaluates a system, UBMedTIRS, for retrieval of medical images. The system uses a combination of image and text features as well as mapping of free text to UMLS concepts. ⋯ Our experimental results indicate that the proposed approach yields significant improvements in retrieval performance. Our system performs 156% above the GIFT system and 42% above the text retrieval system.
-
AMIA Annu Symp Proc · Jan 2006
A novel method for the efficient retrieval of similar multiparameter physiologic time series using wavelet-based symbolic representations.
An important challenge in data mining is in identifying "similar" temporal patterns that may illuminate hidden information in a database of time series. We are actively engaged in the development of a temporal database of several thousand ICU patient records that contains time-varying physiologic measurements recorded over each patient's ICU stay. The discovery of multiparameter temporal patterns that are predictive of physiologic instability may aid clinicians in optimizing care for critically-ill patients. ⋯ The results of this study demonstrate that similarities between different patient time series may have meaningful physiologic interpretations in the detection of impending hemodynamic deterioration. Thus, our framework may be of potential use in clinical decision-support systems. As a generalized time series similarity metric, the algorithms that are described have applications in several other domains as well.