IEEE Computational Intelligence Magazine - November 2020 - 54

Irish cross-filter tool, shown in Figure 3, allows the monitoring
of diabetes cohorts and their Around the Clock prescription
use by individual counties. With the MIDAS cross-filter tool it
is possible to repurpose it to closely follow the COVID-19
codes and obtain a more accurate epidemiological overview
over the regional county map.
Using the exploratory data analytics dashboards in the
MIDAS platform, we have evidenced the known link [18]
between diabetes and pneumonia outcomes. This insight from
the available data is also highly useful in the response to
COVID-19, considering that diabetes is a risk factor for the
progression and poorer prognosis for COVID-19 patients [13],
[16]. Using the MIDAS platform to understand the cohort of
the population with diabetes in Ireland enables more targeted
responses to the COVID-19 pandemic, for example, targeting
local areas, which have high prevalence or higher historical
hospitalizations with comorbidities, with specific messaging.
This permits a more effective and rapid service delivery and
may allow the identification of potential COVID-19 hot spots
in advance.
The MIDAS pilot in the Basque Region, focusing on the
topic of childhood obesity, is useful and important given the
known associations of obesity in children with the emergence
of comorbidities (e.g. diabetes and hypertension). Moreover,
the Basque public health authorities are interested in monitoring the effect of the COVID-19 pandemic on childhood obesity using the MIDAS tools. Behavioral changes during
lockdown in children and adolescents with obesity participating in a longitudinal observational study in Italy have been
published recently [24]. No changes in vegetable intake were
reported during lockdown, whilst in contrast, potato chip, red
meat, and sugary drink intake increased significantly. Time
spent in sports activities decreased, sleep-time increased and

screen time increased. Taking into account the severity of the
COVID-19 cases identified in people diagnosed with obesity,
the MIDAS platform could be utilized to enhance our understanding of the adverse collateral effects and lasting impact of
the COVID‐19 pandemic lockdown on the adiposity level of
adolescents. This includes the evolution of childhood obesity
during the pandemic, and the evolution and adoption of policies based on the monitoring and visualization of a rapidly
changing context.
The topic of mental health was studied in the context of
the MIDAS pilot in Finland. This pilot ran a social media
campaign in 2019 through the Twitter chatbot capabilities
within the MIDAS platform (described in a later section of
this paper). The existing data, ingested into the MIDAS platform previously and located within the policy sites, can be
useful in this new COVID-19 framework, helping public
health authorities to gain a better understanding of the health
scenario over this difficult to assess topic, complemented by
the news published around it. The additional ingestion of
online participatory surveillance systems can contribute to a
better understanding of the impact of the pandemic on mental health.
The COVID-19 situation has increased global concerns in
relation to the mental wellbeing of children and young people.
In Finland, the MIDAS pilot focused on the prevention of
mental health problems in young people. As an example,
within this context, the MIDAS platform could be used as a
tool to support decision-making related to the organization
of mental healthcare services and resources for young people.
The COVID-19 pandemic has created a situation whereby
long isolation periods at home and difficult economic situations are commonplace. This has raised concern amongst
decision-makers in relation to child abuse and domestic

FIGURE 3 The cross-filtering at the MIDAS platform and its usage by the public health authorities in Ireland.

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE | NOVEMBER 2020

IEEE Computational Intelligence Magazine - November 2020

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - November 2020