ARGONet: the most accurate estimates of influenza activity available to date

AGRONet leverages its  information from electronic health records, flu-related Google searches and historical flu activity in a given location. Improved accuracy has been achieved by adding a second model, which draws on spatial-temporal patterns of flu spread in neighbouring areas [1]. Furthermore, the machine learning system was “trained” by feeding it flu predictions from both models as well as actual flu data, helping to reduce errors in the predictions.

Screen Shot 2019-01-15 at 09.20.36.png

Figure 1: State-level performance of ARGONet benchmarked with ARGO and AR52, as measured by RMSE (top), Pearson correlation (middle), and MAPE (bottom), over the period from September 28, 2014 to May 14, 2017. States are ordered by ARGONet performance relative to the benchmarks to facilitate comparison [1]

The novel methodological framework for this task dynamically combines two distinct flu tracking techniques, using ensemble machine learning approaches, to achieve improved flu activity estimates at the state level in the US. The two predictive techniques behind the proposed ensemble methodology, named ARGONet, utilize (1) a dynamic and self-correcting statistical approach to combine flu-related Google search frequencies, information from electronic health records, and historical trends within a given state, as well as (2) a data-driven network-based approach that leverages spatial and temporal synchronicities observed in historical flu activity across states to improve state-level flu activity estimates.

“It exploits the fact that the presence of flu in nearby locations may increase the risk of experiencing a disease outbreak at a given location”

– Harvard Medical School.


Read more here.



Written by Nefti-Eboni Bempong

What should we learn from Zika?

The 2016 Zika outbreak in the Americas was a public health emergency of international concern. Alongside traditional approaches, several digital technologies were used to tackle this rapidly spreading global health threat. A recent review, identified several domains of digital technologies which were utilised during the Zika outbreak, such as computational modelling , big data , mobile health , and other novel technologies [1].

Continue reading “What should we learn from Zika?”

Spinal implant helps paraplegics walk again

This week’s blogpost focuses on the development of a rather remarkable piece of homegrown innovation. Stories of restoring a paraplegic’s ability to walk was something previously confined to the pages of ancient divine texts, yet scientists from EPFL based at Campus Biotech in Geneva have managed to achieve the seemingly miraculous. Their success has been a combination of brilliant scientific minds, innovative technology and dedication to a common goal, which has led to this breakthrough.

Their cutting-edge spinal implant acts as a kind of electrical bridge, implanted over the damaged tissue of a patient’s spinal cord, receiving stimuli above the injury and transcribing them below it. The procedure has successfully restored lower motor function in a number of patients who had lost the ability to walk. Beyond the considerable improvement in the quality of life and mental wellbeing of individual patients, such curative technological advancements have huge potential for insuring a healthy and mobile population with far-reaching socio-economic benefits.


Written by Danny Sheath

Advocating for an expanded mandate of the Global Fund

Founded in 2002, the Global Fund is partnership organisation designed to accelerate the end of AIDS, tuberculosis and malaria as pandemics.  Through continued work with governments, civil society and the private sector, the Global Fund strengthens local health systems and improves communities, by raising money to invest in prevention, treatment and care services [1].

Continue reading “Advocating for an expanded mandate of the Global Fund”

AccessMod 5

“Supporting Universal Health Coverage by modelling physical accessibility to health care”

AccessMod 5.0 is a World Health Organisation (WHO) tool, a free and open-source standalone software to model how physically accessible existing health services are to the target population, to estimate the part of the target population that would not receive care despite being physically accessible due to shortage of capacity in these services (human or equipment), to measure referral times and distances between health facilities, and to identify where to place new health facilities to increase population coverage through the scaling up analysis [1].

Continue reading “AccessMod 5”

Create a website or blog at

Up ↑