BUSINESS INSIGHTS : The latest news, analysis, and trends about protection and care

Jun 2, 2018,  by Allianz Partners Business Insights

Artificial Intelligence: Tool with the potential to detect dengue outbreaks three months in advance

AIME (Artificial Intelligence in Medical Epidemiology) is a system that claims to be able to predict dengue outbreaks by analysing medical data in real time, databases, and variables influencing the spread of the illness. The programme’s designers believe it to be 80% reliable, though opinion in the scientific community is divided. 



Since January 2018, the Malaysian state of Penang has been using an AI programme to predict dengue outbreaks up to three months in advance. Known as AIME (Artificial Intelligence in Medical Epidemiology), the system is also being tested in several cities in Asia and South America, as reported by the website Sci Dev Net


Over 80% accurate 


The Penang authorities have spent USD 120,000 (a little over EUR 100,000) to run the system. Judging by initial results, it seems to be money well spent. In comparing the forecasts generated by their programme with actual events on the ground in Manila (Philippines), Rio de Janeiro (Brazil), Penang and the fellow Malaysian state of Selangor, the engineers behind AIME have found that it is 81% to 84% accurate. 

Those findings were revealed by Dhesi Raja, one of the system’s inventors, at the Geneva Health Forum 2018 in April. A researcher from the Institute for Medical Research Malaysia, he explained that his creation was also capable of determining where future dengue outbreaks would take place to within a 400-metre radius.  


90 databases and 276 variables analysed 


The system analyses data provided by doctors on the ground, with the database thus containing all known cases of the disease. The programme then cross-references the data, searching through some 90 databases and taking into account 276 variables that influence its spread. 

The figures announced by Raja in relation to the programme’s effectiveness have yet to be published officially, while some specialists have questioned the designers’ scientific reasoning. “If your system is really, really good at predicting outbreaks then someone will go out and start fogging, insecticiding in the predicted area – and the transmission dynamics change,” said Oliver Brady of the London School of Hygiene and Tropical Medicine. “So all those important relationships that you’ve been learning over your past years of data might now be completely different.”  


Allianz Partners

Linked Topics
About Allianz Partners Business Insights