AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
AMIA Annu Symp Proc · Jan 2007
A computing platform to support communication and sense-making in intensive care.
We developed a conceptual design of a mobile computing platform to support multi-disciplinary rounds in intensive care units.
-
Shifts in the supply of and demand for emergency department (ED) services have led to ED overcrowding and make the efficient allocation of ED resources increasingly important. Reliable means of modeling and forecasting the demand for resources are critical to any ED resource planning strategy. Vector Autoregression (VAR) is a flexible multivariate time-series forecasting methodology that is well suited to modeling demand for resources in the ED.
-
AMIA Annu Symp Proc · Jan 2007
Identification of misspelled words without a comprehensive dictionary using prevalence analysis.
Misspellings are common in medical documents and can be an obstacle to information retrieval. We evaluated an algorithm to identify misspelled words through analysis of their prevalence in a representative body of text. We evaluated the algorithm's accuracy of identifying misspellings of 200 anti-hypertensive medication names on 2,000 potentially misspelled words randomly selected from narrative medical documents. ⋯ Area under the ROC curve for identification of misspelled words was 0.96. Sensitivity, specificity, and positive predictive value were 99.25%, 89.72% and 82.9% for the prevalence ratio threshold (0.32768) with the highest F-measure (0.903). Prevalence analysis can be used to identify and correct misspellings with high accuracy.
-
AMIA Annu Symp Proc · Jan 2007
Clinical decision support to improve antibiotic prescribing for acute respiratory infections: results of a pilot study.
Acute Respiratory Infections (ARIs) are the number one reason for antibiotic prescribing in the United States, and much antibiotic prescribing for ARIs is inappropriate. We designed an electronic health record-integrated, documentation-based clinical decision support system for the care of patients with ARIs, the ARI Smart Form. To evaluate the ARI Smart Form and assess the feasibility of performing a larger trial, we conducted a pilot study with 10 clinicians who used the ARI Smart Form with 26 patients. ⋯ The average duration of use of the ARI Smart Form was 7.5 (SD+/-4.5) minutes. Eight of 10 respondents reported that the ARI Smart Form was either time-neutral or timesaving. The ARI Smart Form requires further evaluation but has the potential to improve workflow and reduce inappropriate antibiotic prescribing.
-
AMIA Annu Symp Proc · Jan 2007
Semantic query generation from eligibility criteria in clinical trials.
Towards the goal of automated eligibility determination for clinical trials from electronic health records, we propose a method to formulate Semantic Web based queries using the free-text eligibility criteria on clinicaltrials.gov.