Developing predictive models using electronic medical records: challenges and pitfalls.
Authors:
- 16 November 2013
- journal article
- Vol. 2013, 1109-15
Abstract
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. In this paper, we discuss key issues and subtle pitfalls specific to building predictive models from EMR. 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.Keywords
This publication has 18 references indexed in Scilit:
- Sepsis, severe sepsis and septic shock: changes in incidence, pathogens and outcomesExpert Review of Anti-infective Therapy, 2012
- Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database*Critical Care Medicine, 2011
- Integration of Early Physiological Responses Predicts Later Illness Severity in Preterm InfantsScience Translational Medicine, 2010
- Early prediction of septic shock in hospitalized patientsJournal of Hospital Medicine, 2010
- Clinical review: A review and analysis of heart rate variability and the diagnosis and prognosis of infectionCritical Care, 2009
- Development and Verification of a “Virtual” Cohort Using the National VA Health Information SystemMedical Care, 2006
- The effect of prompt physician visits on intensive care unit mortality and costCritical Care Medicine, 2005
- Septic shockCritical Care Medicine, 1998
- Early prediction of outcome in score-identified, postcardiac surgical patients at high risk for sepsis, using soluble tumor necrosis factor receptor-p55 concentrationsCritical Care Medicine, 1996
- Assessing available information on the burden of sepsis: global estimates of incidence, prevalence and mortalityJournal of Global Health