Impact of data quality assessment on development of clinical predictive models

Stud Health Technol Inform. 2015:216:1069.

Abstract

Data quality plays a very important role in predicting clinical outcomes. Data quality is multi dimensional and most relevant studies consider just one or two dimensions. In this study a systematic data quality assessment is performed using four data dimensions. The results demonstrate that performance of predictive models improves when the quality of the data is assessed and addressed systematically.

MeSH terms

  • Computer Simulation
  • Critical Care / statistics & numerical data
  • Critical Illness / mortality*
  • Data Accuracy*
  • Datasets as Topic / standards
  • Decision Support Systems, Clinical / standards*
  • Electronic Health Records / standards*
  • Electronic Health Records / statistics & numerical data*
  • Hospital Mortality
  • Incidence
  • Models, Statistical
  • New South Wales
  • Prognosis
  • Quality Assurance, Health Care / methods*
  • Risk Assessment / standards
  • Survival Analysis