chapter  16
20 Pages

Fever Mass Screening Tool for Infectious Diseases Outbreak: Integrated Artifical Intelligence with Bio-Statistical Approach in Thermogram Analysis

A worldwide pandemic from mutated H5N1 bird flu virus could kill any number of people from 7 to 100 million if left unchecked,∗ according to worst case scenarios being studied by the World Health Organisation (WHO) and scientists. The mutated virus could sicken 20% of the world’s population, with nearly 30 million people in need of hospital treatment and a quarter of these eventually dying.† As at 16

Nikolas: “9027_c016” — 2007/5/31 — 14:51 — page 3 — #3

Jan. 2007, bird flu has killed at least 161 people worldwide since it started ravaging Asian poultry stocks in late 2003, and millions of birds have been destroyed, causing estimated losses of between U.S.$10 and $15 billion for the poultry industry. But the ultimate impact of the virus depends on its virulence. As known, early detection of virus in which fever is one of the most important diagnostic symptoms, isolation of patients and proper medical care could help contain an epidemic and delay or stop it from becoming a pandemic. Monitoring personal temperature at hospital, airports, and border-crossing points are thus critical to prevent outbreak for such an endemic disaster [1-7], although the point prevalence of fever in such subjects would be very low. Traditional tools to measure the body temperature are through the mouth and ear canal. Oral and aural temperature measurements are accurate but are fairly invasive, time consuming, labor intensive, and skill dependent [8,9]. The ideal device for blind mass fever screening should be speedy, noninvasive, and be able to detect accurately those patients with fever [4]. Infrared thermography has been used to detect several inflammatory abnormalities and has the potential to serve as a tool for mass screening for fever [6].