Article Text

Download PDFPDF
Is there a place for a computer based asthma hazard prediction model in clinical practice?
  1. Jacques André Pralong1,
  2. Martin J Seed2,
  3. André Cartier1,
  4. Raymond M Agius2,
  5. Manon Labrecque1
  1. 1Department of Chest Medicine, Hôpital du Sacré—Coeur de Montréal, University of Montreal, Montreal, Quebec, Canada
  2. 2Centre for Occupational and Environmental Health, University of Manchester, Manchester, UK
  1. Correspondence to Professor Manon Labrecque, Department of Chest Medicine, Hôpital du Sacré—Coeur de Montréal, 5400 Boulevard Gouin Ouest, Montreal H4J 1C5, Canada; martin.seed{at}

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Modelling of the relationship between chemical structure and toxicological end-points offers a quick and efficient means of hazard prediction using a computer.1 Agius et al have developed and validated a quantitative structure-activity relationship (QSAR) model to predict the potential of low molecular weight (LMW) organic agents to cause asthma due to sensitisation, as determined by the hazard index (HI).2–5 Using a cut-point HI of 0.5, it has demonstrated a sensitivity of 79% and a specificity of 93%4 with a high negative predictive value (91–100%) suggesting that the use of such a HI could play a …

View Full Text


  • Competing interests None.

  • Patient consent Obtained.

  • Provenance and peer review Not commissioned; internally peer reviewed.