This article is more than 5 years old. Information may no longer be current.
Hotline call analysis forecasts dengue fever outbreaks
Click Here to Manage Email Alerts
A system that analyzes people’s telephone calling behavior to a public health hotline may be able to forecast the outbreak of dengue fever weeks in advance, according to research published in Science Advances.
“Thousands of lives are lost every year in developing countries for failing to detect epidemics early because of the lack of real-time data on reported cases,” Lakshminarayanan Subramanian, PhD, professor at New York University’s Courant Institute for Mathematical Sciences, said in a press release. “We think our technique can be of use to public health officials in their fight against the spread of crippling diseases.”
Subramanian and colleagues used a telephone triage service to locate patients and measure the severity of a dengue outbreak to develop an early epidemic warning system in Pakistan. The researchers collaborated with the Punjab government in response to the 2011 dengue outbreak in Lahore. More than 350 people died, and 21,000 were infected with dengue during that outbreak. The investigators used more than 300,000 calls made to the public health hotline during a 3-year period to predict suspected cases of dengue at a subcity, block-by-block level.
The forecasting system’s efficacy results were predicted with a random forest learning algorithm that matched well with reported public hospitalizations of suspected cases. The researchers said the results showed the service predicted accurate forecasts for dengue outbreak 2 to 3 weeks early for both the number of patients infected and their location. They also said since the introduction of the system in Lahore, the incidence of confirmed dengue cases dropped from 21,000 in 2011 to 1,600 in 2013.
The system’s main limitation, the investigators said, is that hotline calls must be monitored carefully because not all callers are affected by dengue. Nevertheless, they recommended the system for developing countries such as Pakistan to maintain disease incidence control.
“On the basis of the results, we conclude that call volume data from a simple hotline facility combined with widely available city-level weather data can serve as a good predictor of future suspected dengue cases at a fine-grained subcity level,” Subramanian and colleagues wrote. “We believe that this system can also be used for a broad array of diseases beyond dengue and can easily be replicated in other developing countries at low costs.” – by Kate Sherrer
Disclosure: The researchers report no relevant financial disclosures.
Click Here to Manage Email Alerts