A computer-controlled text message service could direct Ebola cases to appropriate medical facilities and track the spread of the disease in the process–provided it can raise the necessary funding.
Back in July, Cedric Moro started a crowdsourced mapping service to keep track of the spread of Ebola in Sierra Leone, Liberia and Guinea. Moro is a risk consultant who has created several crowdsourced maps of this kind using the openStreetMap project Umap.
Anyone can enter information about suspected or confirmed Ebola cases while hospitals and other health facilities can tell people whether they are open and functioning and how many spare beds they have. But it also has an important limitation. Anyone hoping to contribute must have access to a computer or smartphone to upload their information. That means the system is accessible only to a relatively small portion of the population.
Today, Mohamad Trad from Doctors Without Borders in Paris, France, and a couple of pals outline plans to build on Moro’s approach and make this kind of information available purely through ordinary mobile phones. “We propose building a recommendation system based on simple SMS text messaging to help Ebola patients readily find the closest health service with available and appropriate resources,” they say.
The system will be easy for locals to use. The idea is that they can report their symptoms via text to a toll-free number where the messages will be analysed by natural language processing algorithms to determine whether theirs is likely to be a case of Ebola. The system will take into account the spatial distribution of known Ebola cases to classify the disease as accurately as possible.
Next, the system determines the person’s approximate location using the cell tower from which the message was sent or any postcode or village name included in the message. Finally, it will search its database for medical facilities with spare capacity in that area and text back the details accordingly.
