AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
AMIA Annu Symp Proc · Jan 2013
Developing predictive models using electronic medical records: challenges and pitfalls.
While Electronic Medical Records (EMR) contain detailed records of the patient-clinician encounter - vital signs, laboratory tests, symptoms, caregivers' notes, interventions prescribed and outcomes - developing predictive models from this data is not straightforward. These data contain systematic biases that violate assumptions made by off-the-shelf machine learning algorithms, commonly used in the literature to train predictive models. ⋯ We highlight the importance of carefully considering both the special characteristics of EMR as well as the intended clinical use of the predictive model and show that failure to do so could lead to developing models that are less useful in practice. Finally, we describe approaches for training and evaluating models on EMR using early prediction of septic shock as our example application.
-
AMIA Annu Symp Proc · Jan 2013
Supporting information use and retention of pre-hospital information during trauma resuscitation: a qualitative study of pre-hospital communications and information needs.
Pre-hospital communication is a critical first step towards ensuring efficient management of critically injured patients during trauma resuscitation. Information about incoming patients received from the field and en route serves a critical role in helping emergency medical teams prepare for patient care. ⋯ Our findings show that Emergency Medical Services (EMS) teams report a great deal of information from the field, most of which match the needs of trauma teams. We discuss design implications for a computerized system to support the use and retention of pre-hospital information during trauma resuscitation.
-
AMIA Annu Symp Proc · Jan 2012
A clinical decision tool for predicting patient care characteristics: patients returning within 72 hours in the emergency department.
The primary purpose of this study was to develop a clinical tool capable of identifying discriminatory characteristics that can predict patients who will return within 72 hours to the Pediatric emergency department (PED). We studied 66,861 patients who were discharged from the EDs during the period from May 1 2009 to December 31 2009. We used a classification model to predict return visits based on factors extracted from patient demographic information, chief complaint, diagnosis, treatment, and hospital real-time ED statistics census. ⋯ The resulting tool could enable ED staff and administrators to use patient specific values for each of a small number of discriminatory factors, and in return receive a prediction as to whether the patient will return to the ED within 72 hours. Our prediction accuracy can be as high as over 85%. This provides an opportunity for improving care and offering additional care or guidance to reduce ED readmission.
-
AMIA Annu Symp Proc · Jan 2012
Optimizing perioperative decision making: improved information for clinical workflow planning.
Perioperative care is complex and involves multiple interconnected subsystems. Delayed starts, prolonged cases and overtime are common. Surgical procedures account for 40-70% of hospital revenues and 30-40% of total costs. ⋯ Perioperative leaders desire a broad range of tools for planning and assessing alternate solutions. Our modeled solutions generated feasible solutions that varied as expected, based on resource and policy assumptions and found better utilization of scarce resources. Combinatorial optimization modeling can effectively evaluate alternatives to support key decisions for planning clinical workflow and improving care efficiency and satisfaction.