AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
AMIA Annu Symp Proc · Jan 2009
Development of an asthma management system in a pediatric emergency department.
Asthma is the leading chronic childhood disease with exacerbations resulting in urgent and emergency care visits. Guidelines adherence improves patient care but is suboptimal. A computerized guideline system can help improve compliance through automatic initiation and reminders to increase adherence. ⋯ The second phase evaluates a computerized asthma management system including temporal reminder elements for scoring and medication orders. The system was developed in conjunction with the pediatric ED multidisciplinary care team. The computerized system is entirely automatic and a prospective evaluation of the diagnostic component is ongoing.
-
AMIA Annu Symp Proc · Jan 2009
Extracting cancer quality indicators from electronic medical records: evaluation of an ontology-based virtual medical record approach.
Measuring quality in clinical care is a time-consuming manual task. The vast amounts of clinical data collected through electronic medical records (EMRs) create an opportunity to develop tools that automatically assess quality indicators; however, the diversity of EMR implementations limits the ability to implement general, reusable methods. We evaluate an ontology-based virtual medical record (VMR) approach as a standardized, sharable methodology for defining data abstractions needed for quality of care assessment. ⋯ We found that the VMR approach needs to be extended to support population-based aggregations of clinical events, models of intended versus completed actions, and models of workflow and delivery systems. Incorporating the patient perspective on quality also requires additional extension of the VMR. We are using these results to create a virtual quality record based on EMR data.
-
AMIA Annu Symp Proc · Jan 2009
Video-mediated communication in hospice interdisciplinary team meetings: examining technical quality and content.
This study aims to determine how videoconferencing quality impacts the style and content of communication between members of hospice interdisciplinary teams and patients and their families. We videotaped video-calls between hospice teams and family caregivers based on the use of low-cost videophones. We assessed their audio and video quality using both a form that was filled out on site and a protocol for retrospective analysis. ⋯ The time spent on general informal talk was significantly correlated to the video and audio quality of the session (r=0.43 and 0.41 respectively, p<0.001). The time spent addressing psychosocial issues and on caregiver education correlated significantly to video and audio quality. This study demonstrates the potential of video-mediated communication that supports shared decision making in hospice.
-
AMIA Annu Symp Proc · Jan 2009
Inductive creation of an annotation schema and a reference standard for de-identification of VA electronic clinical notes.
Accessing both structured and unstructured clinical data is a high priority for research efforts. However, HIPAA requires that data meet or exceed a deidentification standard to assure that protected health information (PHI) is removed. This is a particularly difficult problem in the case of unstructured clinical free text and natural language processing (NLP) systems can be trained to automatically de-identify clinical text. ⋯ Annotation schema must be created that can be used to build reliable and valid reference standards to evaluate NLP systems for the deidentification task. We describe the inductive creation of an annotation schema and subsequent reference standard. We also provide estimates of the accuracy of human annotators for this particular task.
-
AMIA Annu Symp Proc · Jan 2009
Using Bayesian networks and rule-based trending to predict patient status in the intensive care unit.
Multivariate Bayesian models trained with machine learning, in conjunction with rule-based time-series statistical techniques, are explored for the purpose of improving patient monitoring. Three vital sign data streams and known outcomes for 36 intensive care unit (ICU) patients were captured retrospectively and used to train a set of Bayesian net models and to construct time-series models. Models were validated on a reserved dataset from 16 additional patients. ⋯ The model's AUC for predicting declining outcome increased from 70% to 85% when the model was indexed to personalized baselines for each patient. The rule-based trending and alerting system was accurate 100% of the time in alerting a subsequent decline in condition. These techniques promise to improve the monitoring of ICU patients with high-sensitivity alerts, fewer false alarms, and earlier intervention.