Using algorithms to fight Dengue Fever

Scientists have developed algorithms that can diagnose Dengue Fever from body temperature and blood samples. Photo courtesy of Photocase.com.

The largest markets for medical drugs are found in the Western countries and therefore both private medical companies and public universities and funding bodies mainly pour money into the research of diseases found predominantly in Western countries, while equally dangerous and prevalent diseases from developing countries has been neglected. However, this is slowly changing with the arrival of medical journals dedicated to this field, such as the open-access PLoS Neglected Tropical Diseases supported by the Bill and Melinda Gates foundation. In the latest Issue, a research group comprising of scientists from the Novartis Institute of Tropical Diseases and from various public institutions in Singapore and Vietnam has published a study on Dengue Fever.

Dengue Fever (DF) is caused by a virus that is transmitted by the mosquito Aedes aegypti. It has a distribution similar to Malaria, but unlike Malaria it is also found in urban areas in the tropics and in Africa. DF gives characteristically bright red rashes and causes diarrhea, vomiting and abdominal pain. In rare cases it can result in the death of the patient. It is estimated that there are around 40 million cases of DF each year.

The diagnosis of DF is often difficult, because the early phases of the disease of often mistaken for more harmless fevers or influenzas. In the published study, the researchers examined 1200 patients of which almost a third had DF. From data such as body temperature and numbers of platelets, lymphocytes and hematocrit value in blood samples they developed a simple algorithm to predict whether the disease was DF or another harmless illness with an accuracy of 85%.

By taking a further later blood sample from the patients suffering from DF, another algorithm developed by the team could from the decrease in the number of platelets predict whether the disease developed into a severe form or not.

Such simple algorithms, where the input data is easy to obtain, have the potential to save lives by giving the correct diagnosis in the early stages of the disease thus ensuring proper care and treatment from the onset.

Source:
Tanner L, Schreiber M, Low JGH, Ong A, Tolfvenstam T, et al. (2008) Decision Tree Algorithms Predict the Diagnosis and Outcome of Dengue Fever in the Early Phase of Illness. PLoS Negl Trop Dis 2(3): e196. doi:10.1371/journal.pntd.0000196.

Tag it:

?

Be first to comment this article

Only registered users can write comments.
Please login or register.

Powered by AkoComment Tweaked Special Edition