Login / Signup

Which Chart Elements Accurately Identify Emergency Department Visits for Suicidal Ideation or Behavior?

Sarah A AriasEdwin D BoudreauxElizabeth ChenIvan MillerCarlos Arturo CamargoRichard N JonesLisa Uebelacker
Published in: Archives of suicide research : official journal of the International Academy for Suicide Research (2019)
In an emergency department (ED) sample, we investigated the concordance between identification of suicide-related visits through standardized comprehensive chart review versus a subset of 3 specific chart elements: ICD-9-CM codes, free-text presenting complaints, and free-text physician discharge diagnoses. The method for this study was review of medical records for adults (≥18 years) at 8 EDs across the United States. A total of 3,776 charts were reviewed. A combination of the 3 chart elements (ICD-9-CM, presenting complaints, and discharge diagnoses) provided the most robust data with 85% sensitivity, 96% specificity, 92% PPV, and 92% NPV. These findings highlight the use of key discrete fields in the medical record that can be extracted to facilitate identification of whether an ED visit was suicide-related.
Keyphrases
  • emergency department
  • healthcare
  • case report
  • bioinformatics analysis
  • electronic health record
  • mass spectrometry
  • deep learning
  • artificial intelligence