An Acute-Trauma Index.

Abstract

Thirty-nine parameters commonly measured when a patient with major trauma is admitted to a hospital were evaluated by pattern-recognition techniques in an attempt to define an acute prognostic index. The resulting index was a euclidean distance using single pretreatment estimates of arterial pH, hematocrit, prothrombin time, and the systolic blood pressure. Prospective validation of the index resulted in a 98% accuracy of prediction of survival rate with an individual misclassification rate of 15%. When used in conjunction with an anatomical index, the expected misclassification rate was reduced to 8%, and the actual misclassification rate experienced was 3.4%. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1977
Accession Number
ADA040766

Entities

People

  • C. L. Swann
  • E. S. Johnson
  • H. R. Champion
  • W. Gill
  • W. J. Sacco

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Accuracy
  • Blood
  • Cardiovascular Physiological Phenomena
  • Data Science
  • Head Injuries
  • Health
  • Health Care
  • Health Services
  • Information Science
  • Measurement
  • Medical Personnel
  • Models
  • New York
  • Pattern Recognition
  • Public Health
  • Therapy
  • Wounds And Injuries

Fields of Study

  • Medicine

Readers

  • Cardiovascular Physiology
  • Computer Vision.
  • Trauma or Military Medicine

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks