AI4Covid: Effective AI covid-tests using only cough sounds

3

October

2022

No ratings yet.

In the fight against the coronavirus, early and accurate diagnosis is vital. To this day most common tests still rely on antibodies, therefore results are often only conclusive after several days and not reliable enough.

Researchers in the field of automated cough classification have been working on another strategy: They adapted a supervised machine-learning algorithm that detects slight differences in coughs and can diagnose or rule out respiratory infections accordingly. 

This tool is supposed to automatically identify cough sounds and define them pursuant to certain parameters. AI makes it possible to compare patterns with other coughs and diagnose instantaneously. Cough sounds are especially informative because the sounds correlate with tissue structure in the respiratory organs, in addition to providing insight to the behavior of surrounding organs and structures.

The most challenging aspect of the studies is to find the most significant features, on which grounds to train the machine-learning system. The Massachusetts Institute of Technology has based their program on the four attributes: Muscular degradation, vocal cord strength, sentiment as well as respiratory and lung performance (Saplakoglu, 2020). For their program thousands of volunteers uploaded forced coughs and filled out information on their health status, symptoms and covid infection. While a large group of cases were then used to train the machine-learning system, another was used to function as a test group. Although results were very encouraging, transferring this success out of the laboratory provided a challenge, since cough sound not only vary on respiratory function, but many other parameters, such as mother-tongue and gender. Therefore investigation continued and showed that time-frequency representation of a cough successfully aided in achieving higher quality results. So far the best model is Random Forest with an accuracy of 90% (Tena, Clarià and Solsona, 2022).

These cough related covid tests have the potential to contain the pandemic in a more efficient way, as they would – if installed as an app on phones – not need high cost data evaluation in labs and would therefore be more easily accessible and affordable. Also AI can spot covid infections sooner than rapid covid tests can and would therefore be a strong advantage to the prevention of high spreading.

References

Saplakoglu, Y. (2020). Newsela [online] newsela.com. Available at: https://newsela.com/read/ai-detect-covid19-cough/id/2001015957/%C2%A0/https://newsela.com/read/ai-detect-covid19-cough/id/2001015957/%C2%A0/ [Accessed 2 Oct. 2022].
Tena, A., Clarià, F. and Solsona, F. (2022). Automated detection of COVID-19 cough. Biomedical Signal Processing and Control, [online] 71, p.103175. doi:10.1016/j.bspc.2021.103175. Available at: https://www.sciencedirect.com/science/article/pii/S1746809421007722  [Accessed 1 Oct. 2022].
Detecting COVID-19 through cough sounds. (n.d.). www.nature.com. [online] Available at: https://www.nature.com/articles/d42473-022-00294-9 [Accessed 2 Oct. 2022].

Please rate this

Fake News during Covid-19: Who is responsible?

7

October

2021

No ratings yet.

Earlier this year, the EU Commission told tech giants Google, Facebook, Twitter and Microsoft to generate monthly reports on their efforts to tackle fake news (Chee, 2021). The problem of fake news has become more serious ever since the start of the Covid-19 pandemic, or as some like to call it: the Covid-19 infodemic. An infodemic refers to a disease outbreak during which too much information, including false or misleading information is being spread on both digital and physical environments (World Health Organization, 2021). This results in mistrust in health authorities and undermining of public health response. 

Covid-19 has indeed given rise to immense amounts of fake news being spread on social media platforms. A recent study shows that one in five people believe fake news about Covid-19 (De Bruin, 2021). With the alarming amounts of fake news being spread, imagine the alarming number of people misinterpreting fake news for real news. Misinterpretation or believing fake news on its own might not be harmful, but when such beliefs result in actions (e.g. unwillingness to take the vaccine), it can seriously harm the approach to tackling the Covid-19 pandemic.  

Therefore, tech giants must now share the data they have on how misinformation spreads and on the granular impact of their actions in EU countries (Chee, 2021). Companies like Google and Facebook also act on preventing fake news themselves through the use of fact checkers. During Covid-19, Facebook has removed 16 million pieces of content and added warnings to 167 million and Youtube (owned by Google) removed 850.000 videos, all due to ‘dangerous or misleading covid-19 medical information’ (Clarke, 2021). Additionally, Google has released an open fund for projects debunking vaccine misinformation, accepting applications from projects that want to broaden the audience of fact checks (Mantzarlis, 2021). 

It is understandable that governments and state organizations such as the EU Commission require action to tackle fake news from the platforms the fake news is being spread on. However, it is impossible for these platforms to fully stop the spread of fake news, even with the use of fact checkers and the sharing of data with governmental institutions. Therefore, some are saying that doctors must tackle fake news related to Covid-19. They would be able to stop the spread of false information by refuting misleading health information and providing appropriate sources to accompany their refutation (O’Connor, 2020). It is debatable whether this approach would work, therefore I would like to ask what you think. Whose responsibility is it to tackle fake news related to Covid-19? 

References

Chee, F. Y. (2021). EU tells Google, Facebook and Twitter to extend fake news watch, COVID-19 in focus. Retrieved October 7, 2021, from https://www.reuters.com/article/us-eu-tech-fakenews-idUSKBN29X1R2

Clarke, L. (2021). Covid-19: Who fact checks health and science on Facebook? Retrieved October 7, 2021, from https://www.bmj.com/content/373/bmj.n1170

De Bruin, B. (2021). New study shows: one in five people believe fake news about COVID-19. Retrieved October 7, 2021, from https://www.rug.nl/feb/news/current/new-study-shows-one-in-five-people-believe-fake-news-about-covid-19?lang=en

Mantzarlis, A. (2021). An open fund for projects debunking vaccine misinformation. Retrieved October 7, 2021, from https://blog.google/outreach-initiatives/google-news-initiative/open-fund-projects-debunking-vaccine-misinformation/

O’Connor, C. (2020). Going viral: doctors must tackle fake news in the covid-19 pandemic. Retrieved October 7, 2021, from https://www.bmj.com/content/369/bmj.m1587

World Health Organization. (2021). Infodemic. Retrieved October 7, 2021, from https://www.who.int/health-topics/infodemic/the-covid-19-infodemic#tab=tab_1

Please rate this

How Greece used AI to detect asymptomatic travelers infected with COVID-19

29

September

2021

No ratings yet.


A few months after the Covid-19 outbreak, operations researcher Kimon Drakopoulos, who works in data science at the University of Southern California, offered to help the Greek government by developing a system that uses machine learning in order to determine which travelers had the most risk of being infected and thus should get tested. Greece was asked by the European Union to allow non-essential travel again, but of course the option of testing all travelers was not available. Consequently, they chose to implement a more efficient way to test incoming travelers than the usual practices of randomized sample testing or testing based on the visitor’s country of origin, by launching this system called ‘Eva’ and deploying it across all Greek borders.

Drakopoulos and his colleagues discovered that machine learning proved to be more effective at identifying asymptomatic cases than the aforementioned methods, by a factor of two to four times during peak tourist season. This was accomplished because Eva used multiple sources of data, besides just travel history, to assess and estimate the infection risk of an individual. These sources include demographic data like the age and sex of the travelers, which was then paired with the obtained data from previously tested passengers, to calculate who had the highest risk out of a group and needed to be tested. This process was also used to provide information to the border policies about real-time estimates of the prevalence of COVID-19.

When the researchers compared the performance of this model against the methods that only use epidemiological metrics, such as random testing, it was clear that it performed better in all aspects. One main reason for this was the limited predictive value that these metrics possessed in relation to asymptomatic cases. Consequently, the paper raises concern on the effectiveness of internationally proposed border policies that employ such population-level metrics.

All in all, Eva is a successful example of how the use of reinforcement learning and artificial intelligence in combination with real-time data can provide very useful assistance both in crisis situations but also in the public health sector.

References

Bastani, H., Drakopoulos, K., Gupta, V. et al. Efficient and targeted COVID-19 border testing via reinforcement learning. Nature (2021). https://doi.org/10.1038/s41586-021-04014-z

Nature (2021) ‘Greece used AI to curb COVID: what other nations can learn’, 22 September. Available at: https://www.nature.com/articles/d41586-021-02554-y  (Accessed: 29 September 2021).

Please rate this

Back to the office or does remote working stimulate the quality of life?

26

September

2021

No ratings yet.

There has been clear communication that advocates two opposing views adopting cloud based (remote) working for the quality of life: a firm should stimulate remote working versus a firm should stimulate offline working. According to C. Jalagat and M. Jalagat (2019), remote working can be defined as performing work – from any location where Wi-Fi is present and  Cloud Computing is adopted by the company – other than the location of the employer. I believe that adapting cloud computing is beneficial for our daily life. Even after the Covid-19 pandemic as well (see Figure 1).

The first benefit of remote working is that the sickness rate is 0.5 lower among people who work remotely compared to those who work in the office (PWC, s.a.). PWC hypothesizes that remote workers can give more attention to their children, their stress levels drop significantly, and burnout problems are prevented. The second benefit is that remote working via cloud services – most of that eco-friendly generated – increases air quality and protects our climate; in city of Phoenix it resulted in 1.3 million fewer miles driven, which equates to over 47,000 pounds less air pollutant emissions each day (Irwin, 2004). Higher air quality is correlated with a longer average life span, and therefore, it is important that we ensure our own future and the future of today’s youth. 

There are also two disadvantages. The first disadvantage is that companies that encourage remote working deliberately expect their employees to be available at all times (Bijen, 2021). She argues that remote workers are continuously busy with finishing their notifications after work hours; it disrupts daily routines such as eating or raising children (Manocka , 2020). The second drawback is that remote working contribute to the disappearance of many management positions. Current technology is capable of continuously tracking and assessing employees for productivity, thus, companies are experiencing a lesser need for managers to make decisions on behalf of their employees (Morse, 2020). 

I believe that our health and prevent air pollution is central to the quality of life. Quality of life is  subjective and is complicated to measure. However, what is our life worth if we experience health issues, or if in five years’ time it is determined that we will not meet the Paris Agreement? One could argue against my position that health can be maintained without remote working. While people are indeed capable of taking personal responsibility for maintaining their health, we must remember that people cannot tackle this problem individually. There is also concern that remote working may mean that companies expect us to sacrifice our free time for work. However, the Dutch government is working on a bill that would give homeworkers more rights to remain unreachable after work (Bijen, 2021). As a well-known saying goes, “Most of us spend too much time on what is urgent and not enough time on what is important in life”.

Figure 1: Worldwide Public Cloud Services End-User Spending Forecast (Millions of U.S. Dollars)

References:

Jalagat, C., & Jalagat, M. (2019). RATIONALIZING REMOTE WORKING CONCEPT AND ITS IMPLICATIONS ON EMPLOYEE PRODUCTIVITY. Global Journal of Advanced Research, 95-100.

PWC. (z.j.). The costs and benefits of working from home. PWC.

Irwin, F. (2004, Januari). GAINING THE AIR QUALITY AND CLIMATE BENEFIT FROM TELEWORK. Retrieved from http://pdf.wri.org/teleworkguide.pdf

Bijen, M. (2021). Wetsvoorstel: thuiswerker moet recht krijgen onbereikbaar te zijn buiten werktijd. Retrieved from Het Parool: https://www.parool.nl/nederland/wetsvoorstel-thuiswerker-moet-recht-krijgen-onbereikbaar-te-zijn-buiten-werktijd~b88e4da5/?referrer=https%3A%2F%2Fwww.google.com%2F

Morse, J. (2020, December). Amazon announces new employee tracking tech, and customers are lining up. Retrieved from Mashable: https://mashable.com/article/amazon-aws-panorama-worker-customer-tracking-technology-smart-cameras/?europe=true

Manocka, I. (2020). Covid-19: Teleworking, Surveillance and 24/7 Work. Some Reflexions on the Expected Growth of Remote Work After the Pandemic. Political Anthropological Research on International Social Sciences (PARISS).

Please rate this

How Covid-19 speeded the digital revolution

15

September

2021

No ratings yet.

The world has been up-side-down since Covid-19 started almost one and a half years ago. To control the pandemic, having almost no personal contact and interaction became the “new normal”. The government demanded a lockdown, events got cancelled, schools were closed and companies introduced remote working.

Because of the “new normal”, companies had to rethink aspects of their business as consumers now mainly had to rely on online channels. And companies had to respond accordingly. This led to an exponential increase in new digital technologies and a digital transformation in many different sectors. Companies that were affected by the lockdown had to think in the digital direction to stay competitive in this new business environment. But also digital companies quickly developed and expanded with new digital services that helped to reduce face-to-face interactions. Examples of these digital technologies are delivery services, video conferencing services and cloud computing.

The pandemic arrived so unexpectedly. Since it affected millions of companies – or should we say almost the whole business world – so quickly and severely, companies also quickly had to respond with digital transformations. Research shows that due to Covid-19, the adoption of digital technologies is increased in speed by several years. According to McKinsey, the digitization of customer and supply-chain interactions and of their internal operations have accelerated by three to four years. In addition, the share of digital-enabled products in their portfolios has increased speed by seven years.

The same research also found that most of these digital transformations are there to last – even when everything goes back to the “old normal”. Changes that happened because of Covid-19, such as remote working and changing customer needs, are believed to stick as the pandemic evolves. And this of course has important implications for businesses. What do you think this means for businesses?

You can read the articles in the sources for more information and the other results of the McKinsey survey.

Sources:

https://www.mckinsey.com/business-functions/strategy-and-corporate-finance/our-insights/how-covid-19-has-pushed-companies-over-the-technology-tipping-point-and-transformed-business-forever

https://www2.deloitte.com/us/en/insights/topics/digital-transformation/digital-transformation-COVID-19.html

Please rate this

‘Energy Shaming’ is the new ‘Fat Shaming’ – Crypto thé solution?

9

September

2021

No ratings yet.

The paradigm of global climate change has been continuously shifting for decades. Currently, it is argued that global warming is the cause of human-induced emissions of greenhouse gasses. If no further measures are taken, it is possible that the Earth will be warmer by 1.5 – 2 degrees Celsius. This could lead to many natural disasters, some even affecting regions in Western countries that are in the present hard to imagine. Think about extreme drought, floods and wildfires in the Netherlands – a very strange concept to grasp. There was even a study published that suggested that more global pandemics will follow due to climate change, marking the COVID-19 pandemic as the start of many more.

It is clear that the current school of taught about the future of climate change is as concerning as hippie inspired water preserving practices in restrooms such as “If it’s yellow, let it mellow. If it’s brown, flush it down”. I would never wish someone to live in such a world, especially when your daily concerns are natural disasters (or that your toilet water is always yellow for that matter). Fortunately, decades of climate change research had not been taken for granted by many world leaders, causing them to sign the Paris Agreement in 2016. It is an agreement, in which a collective goal is stated to reach net-zero emission by the second half of the 21st century.

Unfortunately, many companies do not fully comply to the Paris Agreement. Of course, most companies will admit the existence of climate change and the importance of taking actions. However, it is the extent to which they will work on it that is questionable. At the end of the day, they want to continue making profits under conditions of certainty, which in this case is extending their current practices for as long as possible. Shell is a great example of a company being reluctant about implementing green policies as fast as possible. H&M, another ‘committed’ company with bold green statements.

To prevent cancel culture, that is banning a certain entity from their life, companies like Shell and H&M would market themselves as green. Just as how some people do not like to be fat shamed, companies do not want to be ‘energy shamed’, otherwise they could lose customers and thus revenue. Unlike fat shaming that is extremely unhealthy to be practiced on, the practice of energy shaming could actually be a great starting point for a greener tomorrow. Here is a hint how: blockchain technology.

Energy Web (EW) is a non-profit organization that uses open-source blockchain technology to keep track of which companies are using green energy for their daily operations. The idea is that individuals and companies receive incentives to join EW’s network of validators on the blockchain. Doing so, all the involved stakeholders could check upon each other if they are using clean energy or not. Since it uses blockchain technology, it is therefore impossible for companies to lie about their energy sources. Thus, if a stakeholder does not believe that Shell is using green energy, one could easily check that on EW’s network. This is quite plausible given how many established companies are already part of this network (like Shell). It is also the nature of EW being open-source that makes it more reliable.

Then the question arises: what does the validator actually check to confirm the use of green energy? Simply said, being part of EW’s network, means that you have to buy green energy from grid operators that are EW and European Union (or any other regulatory body) approved as for being a green energy supplier. The idea is that companies receive a number of certificates per volume kWh energy that they order from these grid operators. These certificates are called Energy Web Tokens (EWT), that could be validated on EW’s network. EWTs also state where the energy comes from and when it was generated. Thus, in other words, if H&M wants to check if Shell is using clean energy, it would check if Shell possesses the right amount of EWTs through EW’s network. If it appears that Shell is lying about their energy sources, Shell could be energy shamed, likely by its direct competitors like BP.

Is energy shaming going to solve climate change entirely? Probably not. However, it is a great steppingstone to encourage companies to use clean energy. Hopefully, if the world gets greener, I can retire without any stress about the environment or any peculiar hippie practices.

:

References

https://www.energyweb.org/about/what-we-do/

https://www.medium.com/energy-web-insights/issuing-certificates-with-the-ew-origin-sdk-part-ii-e18fa907c57

https://www.shell.com/media/news-and-media-releases/2021/shell-confirms-decision-to-appeal-court-ruling-in-netherlands-climate-case.html

https://www.shell.com/energy-and-innovation/digitalisation/news-room/blockchain-building-trust-to-enable-the-energy-transition.html

https://www.pressroom.ifc.org/all/pages/PressDetail.aspx?ID=18195

https://www.green.blogs.nytimes.com/2009/05/22/hippies-hollywood-and-the-flush-factor/

https://www.propublica.org/article/climate-infectious-diseases

https//www.yaleclimateconnections.org/2021/08/1-5-or-2-degrees-celsius-of-additional-global-warming-does-it-make-a-difference

Please rate this

Criminals working from home

9

October

2020

No ratings yet. During the COVID-19 pandemic, the time we spent on our screens has increased drastically. Everything became remote and most of our human interaction consisted of our online contact. Instead of being able to speak with our colleagues, most of our face-to-face conversations turned to emails and Zoom calls. People who started a position while working from home may not even be able to recognize their colleagues if their cameras were not on during the virtual meetings. Working from home became the new normal, but is this transition safe? Will the threat to our cybersecurity be greater as we spend more time and share more online?

The need for keeping our data safe online has become increasingly important during the pandemic, as we spend more time interacting online, sharing more information, and working from home. Remote working has had an impact on the average cost of a data breach already, increasing it by $137,000. Employees working on private home networks rather than secure company ones are left more vulnerable. The pandemic has also limited the number of activities we can enjoy outside of our houses and provided us with more spare time. For hackers, this time was not wasted as pandemic related fraud reports, in the US, have cost around $114.4 million by mid-August 2020. Even when it comes to Zoom, our data has not been safe. In April, more than 500,000 users have been victims of a breach and the accounts were sold on the dark web. It is increasingly important for people to be aware of online threats, and for companies to ensure their cybersecurity strategies sufficiently protect our data, both as consumers and employees.

It has become increasingly attractive for cyber-criminals to attack as the value of data increases and we become more vulnerable. Individuals are not the only ones at risk, companies and other institutions have also felt the increase in cyber-crime. The laboratory at the University of California had their system frozen and ended up having to pay 116.4 bitcoins ($1.14m) to the hackers. The system was worth the money to the laboratory, since it had contained research relating to the search for a Covid-19 cure.

As more companies find ways to monetize data, there will be more money and value for cybercriminals to extort. There are many ways to protect ourselves such as checking our emails for phishing, using an anti-virus, using a VPN, strong passwords, two-factor verification, etc. However, even if we take the necessary steps to protect ourselves, we may still become victims. Facebook is constantly involved in data breaches and third-party misusage of users’ information. In 2019, 267 million Facebook user accounts were compromised with phone numbers and names obtained, then offered for sale on the dark web. Do you trust companies with protecting our data? I believe cybercrime will become an increasingly important issue as we transition to hybrid ways of working in the post-pandemic life (hopefully). Are you concerned about cybercrime and the safety of your data?

 

Sources:

https://www.pandasecurity.com/mediacenter/news/covid-cybersecurity-statistics/

https://www.ibm.com/security/data-breach

https://mitsloan.mit.edu/ideas-made-to-matter/how-to-think-about-cybersecurity-era-covid-19

https://www.forbes.com/sites/zakdoffman/2020/04/20/facebook-users-beware-hackers-just-sold-267-million-of-your-profiles-for-540/

https://www.ft.com/content/935a9004-0aa5-47a2-897a-2fe173116cc9

https://www.telegraph.co.uk/news/2019/12/20/facebook-personal-details-267-million-users-exposed-online/

Please rate this

AI as a weapon against Covid-19: How far can we go?

8

October

2020

No ratings yet. After almost one year since the outbreak of COVID-19, the world is still in a race to find a vaccine or remedy against it. Since the Spanish flu, the Corona-virus is the latest pandemic to hold it’s grip on the world as we know it. It affected the way we are living and how we humans interact overall. Therefore, more and more creative solutions have been up for the test against this virus. In order to win the race, lots of research now also calls in the aid of Artificial Intelligence. However, even if well-intended, how far should we take AI in taking on COVID-19? How much of our personal data should we allow AI to process? 

 

Potential uses of AI

First of all, Artificial Intelligence could be used to improve the diagnosing process. As it turns out AI can not replace an entire process, especially in a sector as sensitive as health care where human intervention is vital. Baidu, a Chinese technology company announced last march that it could use infrared sensor systems in order to single out infected persons in crowds (Johnson, 2020).

Another application of AI for COVID-19 diagnosis is the use of AI-driven CT-scan interpreters in order to take time of radiologists’ hands in diagnosing and analyzing the virus. Some hospitals are already using this application, especially in regions where the virus is spreading at a faster rate than hospitals can manage (Wittbold et al., 2020) .

However, finding a quick, efficient and effective way to diagnose people who got infected by the virus, is only a solution to a part of the problem. Luckily, there is also a potential use of AI in research for a vaccine on COVID-19. This can be done by using AI through machine learning into the research of drug discovery for treating diseases. Traditionally drug discovery is a slow process, even without having to adhere to the strict drug-regulations like we have in the European Union. However, through the use of AI one can quickly sift through the large amount of data available on the virus,  study the structure and how it affects human beings and consider the suitability of various drugs (Wakefield, 2020).

 

“Now more than ever, there is a need to unify these disparate drug discovery data sources to allow AI researchers to apply their novel machine-learning techniques to generate new treatments for Covid-19 as soon as possible.” – Prof Ara Darzi, director of the Institute of Global Health Innovation, at Imperial College

 

AI and personal data 

As outlined above, AI has great potential uses for diagnosing and even treating our pandemic, so that we might soon get a glimpse of our social lives as humans before the virus. Now governments and large research institutions are stepping up to introduce apps for the public to download in order to monitor the spread of the virus. With AI and machine learning, lots of data is often required for the system to function at a sufficient level of accuracy (Brynjolfsson and McAfee, 2017). So with the Corona-app launching in the Netherlands, lots of personal data, like health records and how long you had contact with who, is required from the public.

I am really interested in how you think about this development. Would you download the app? Why or why not? Do you think such application is useful for fighting the pandemic? Please let me know what you think in the comments below.

 

References

– Brynjolfsson, E., & McAfee, A. (2017). The Business of Artificial Intelligence: What It Can — and Cannot — Do for Your Organization. Harvard Business Review Digital Articles, 3–11.

– Johnson, K. (2020). How people are using AI to detect and fight the coronavirus. VentureBeat. https://venturebeat.com/2020/03/03/how-people-are-using-ai-to-detect-and-fight-the-coronavirus/

– NOS. (2020, October 6). Kan de corona-app helpen? Deze deskundigen denken van wel. https://nos.nl/artikel/2351218-kan-de-corona-app-helpen-deze-deskundigen-denken-van-wel.html

– Wakefield, B. J. (2020, April 17). Coronavirus: AI steps up in battle against Covid-19. BBC News. https://www.bbc.com/news/technology-52120747

– Wittbold, K. A., Carroll, C., Iansiti, M., Zhang, H. M., & Landma, A. B. (2020). How Hospitals Are Using AI to Battle Covid-19. Harvard Business Review. https://hbr.org/2020/04/how-hospitals-are-using-ai-to-battle-covid-19

Please rate this

Artificial Intelligence against COVID-19

7

October

2020

No ratings yet. New research by the VUB (Vrije Universiteit Brussels) proofs that Artificial Intelligence (AI) can successfully support policymakers against epidemics such as COVID-19. AI can potentially combine epidemiologic models with complex decision-making models that are capable to take into account factors such as human behavior. However, predicting this human behavior is incredibly difficult (Subrahmanian and Kumar, 2017). Therefore, the question arises: How can AI combine epidemiologic models with complex decision-making models to assist policymakers?

Reinforcement learning

Reinforcement learning is an AI technique that became famous after the world champion of the GO-game was defeated by the AlphaGo-program from Google Deepmind in 2017. Pieter Libin examines the epidemiological applications of this AI technique in his research (press.vub.ac.be, 2020). Reinforcement learning is particularly suitable to track complicated interactions. It includes cultural, behavioral, and societal factors to successfully determine prevention strategies to reach specified objectives in an epidemic.

The battle against pandemics with AI efficiency

AI allows proposing a targeted approach to actively combat an epidemic such as COVID-19 (press.vub.ac.be, 2020). The models can learn an optimal strategy that can for example consist of the mandatory wearing of mouth masks, and the vaccination of specific target audiences (given that there is a vaccination) (www.bruzz.be, 2020). Besides reinforcement learning, there are other machine learning (ML) techniques that can be useful against the battle of epidemics. ML techniques in combination with epidemiological and statistical models can predict how fast an epidemic can spread. Therefore, intensive care units can be determined that are extremely vital in hospitals. This way medical institutions are more prepared to make the necessary adaptions in their infrastructure in the eye of an epidemiologic storm. Additionally, Artificial Intelligence can assist in developing new medicines. Specifically, pattern recognizing techniques can make active connections out of bio-Informatica databases to contribute to the design of a new medicine against the virus.

COVID19

Current AI initiatives against COVID-19

The VUB has already come up with AI initiatives on both the university and international level.  Together with the medical experts of the Universitair Ziekenhuis Brussel (UZ Brussel), the VUB set up two different AI-driven projects. On the one hand, an analysis was made about how AI can contribute to more accurate long scans. On the other hand, there is the development of an AI application that doctors in intensive care can use to assist them in their decision making (press.vub.ac.be, 2020).

To conclude, AI techniques such as reinforcement learning and ML techniques in combination with epidemiological and statistical models can propose a targeted approach to combat epidemics. This gives policymakers grounded evidence to construct better policies against epidemics.

 

This topic is clearly of high interest to me. However, I was wondering what do you think about the ethical implications of the use of AI in the battle against COVID-19? Do you know other AI initiatives against pandemics such as COVID-19?

—

[References]

press.vub.ac.be. (2020). VUB zet AI in tegen COVID-19. [online] Available at: https://press.vub.ac.be/vub-zet-ai-in-tegen-covid-19 [Accessed 7 Oct. 2020].

Subrahmanian, V.S. and Kumar, S. (2017). Predicting human behavior: The next frontiers. Science, 355(6324), pp.489–489.

www.bruzz.be. (2020). VUB onderzoekt het gebruik van AI om epidemieën in te dijken. [online] Available at: https://www.bruzz.be/wetenschap/vub-onderzoekt-het-gebruik-van-ai-om-epidemieen-te-dijken-2020-05-29 [Accessed 7 Oct. 2020].

 

Please rate this