Year : 2021 | Volume
: 19 | Issue : 4 | Page : 274--277
Artificial intelligence - Technology for prediction and prevention of third wave of COVID-19 pandemic
Prem Sagar Panda1, Ashish Kumar Sinha2, G Susmita Dora3,
1 Department of Community Medicine, Kalinga Institute of Medical Sciences, Bhubaneswar, Odisha, India
2 Department of Community Medicine, Pt. JNM Medical College, Raipur, Chhattisgarh, India
3 Department of Community Medicine, All India Institute of Medical Sciences, Bhubaneswar, Odisha, India
Dr. Prem Sagar Panda
Department of Community Medicine, Kushabhadra Campus 5, KIIT Square, Kalinga Institute of Medical Sciences, Bhubaneswar - 751 024, Odisha
Pandemics bear unique challenges which require a fast response from health system on many aspects ranging from prevention to management through rapid diagnostic modalities, drug/vaccine discovery, and health resource allocation and planning management. However, in low resource settings, the mismatch between demand & supply of health services and inadequate knowledge about the course of pandemic results in failure in management of pandemic & resulted in loss of human lives. However, due to discovery of the latest technologies like artificial intelligence (AI), the pandemic is often managed from prevention to management level in a predictive manner. AI is increasingly being studied as a useful gizmo to assist in preventing pandemic and managing existing crisis in a timely manner. However, while AI has been proved to be useful in its ability to assist halting the rapid spread or contamination of disease during a pandemic, there exist few ethical and legal issues that have gotten to be taken care of before it is to be utilized in a mass scale.
|How to cite this article:|
Panda PS, Sinha AK, Dora G S. Artificial intelligence - Technology for prediction and prevention of third wave of COVID-19 pandemic.Curr Med Issues 2021;19:274-277
|How to cite this URL:|
Panda PS, Sinha AK, Dora G S. Artificial intelligence - Technology for prediction and prevention of third wave of COVID-19 pandemic. Curr Med Issues [serial online] 2021 [cited 2022 May 21 ];19:274-277
Available from: https://www.cmijournal.org/text.asp?2021/19/4/274/331840
Artificial intelligence (AI) is the nascent branch of computer science that is based on three things; first, it simulates intelligent behavior in computers and then incorporates human-made intelligence into machines, and finally, it thinks like humans. A group of researchers coined the term “;Artificial Intelligence” in 1956. After few decades of its evolution, AI has shown high presence. These changes have increased interest regarding its use in all future endeavors, including public health/preventive health. Kaplan and Haenlein describe AI as “;correct interpretation and learning of data by a system and to use those learning to achieve assigned goals and tasks through flexible adaptation and modification.” Apart from applications of AI among the technology sectors, it has also enrouted to healthcare system, especially public health. In healthcare, apart from public health, AI applications have been spread and proved to be outperforming in various other medical fields such as radiology, dermatology, and pathology. In addition, a few hospitals have started to incorporate AI technology into the electronic medical record and clinical management, as in the Predictive Analytics Unit, New York University Langone Health. In a nutshell, AI is all about taking advantage of the fast development that a computer can process information to draw insights and predictions. It can help detect threats beforehand compared to traditional mechanisms and help us understand what kind of interventions prevent disaster and make society safer and healthier.
Types of Artificial Intelligence
Two broad categories are there in AI, namely, artificial general intelligence (AGI) and artificial narrow intelligence (ANI).
AGI is more of generalized and designs the machine to follow and work like a human mind and perform algorithm-based intellectual task that a human can be able to do.
ANI is more of specialized activity and represents the ability of a machine to perform an individual task in a quite achievable manner. Mostly, nowadays, all AI applications are specialized and act in the principle of ANI.
Few AI technologies include machine learning (ML), deep learning, natural language processing, knowledge-based system, health informatics and digital medical records, cloud computing, signal and image processing, and cross-sectoral data application.
How Is It Useful in COVID-19 So Far?
From the initiation of pandemic, AI has helped basically starting from prevention, contact tracing, detection to management of COVID-19 cases. The AI uses large amount of existing dataset to get acquainted with recognition of pattern and thereby potentially suggesting future prospect.
Artificial intelligence for prediction of COVID-19
AI is often used for forecasting the spread of virus and developing early warning systems by extracting information from different sources such as social media platforms, calls and news sites, and supply reliable and practicable data about the vulnerable regions and for prediction of morbidity and mortality. With the invention Blue-Dot (software developed by Canadian AI company), it works by fusion of AI and knowledge of epidemiologists for evidence generation of emerging diseases. Blue-Dot technology gives information to healthcare providers (HCPs), government sectors, private sectors, and public health clients. This briefly alerts abnormality in morbidity and mortality patterns, indicating toward disease outbreaks.
Artificial intelligence for prevention of spread of COVID-19
China-based companies are using AI technology with the assistance of drones, and robots are helpful in maintaining the social distancing and sanitization as they perform contactless delivery and spray disinfectants publicly areas to attenuate the danger of contamination during this COVID-19 pandemic. Further, robots are checking people for rise in blood heat and other key COVID-19 symptoms and dispensing/spraying hand sanitizer at every check points. Robots are getting used to require care of patients in COVID wards in serving food, measuring vital parameters, dispensing drugs, and disinfecting rooms to attenuate cross-contamination with other staffs.
Artificial intelligence for contact tracing of COVID-19
Mobile phone apps for contact tracing were utilized in Wuhan city, China, to contain virus; AI together with other technologies was wont to trace the probable carriers of the virus. Using AI-powered smart glasses, persons with increased blood heat could even be detected. Security guards without contacting the human will check at the safety checkposts using an equivalent. Variations of these kinds of surveillance technology were utilized publicly and in crowded places of China. This technology made it possible to need body temperature in a contactless way without changing people's behavior. With this technology, those whose-body temperatures exceeded a particular limit could quickly be located. It has been very helpful over the manual measurement because the latter one is time-consuming and carries the danger of cross-contamination.
Artificial intelligence for diagnosis of COVID-19
Various AI programs are now available for chest screening which can be helpful in detecting lung abnormalities during a chest X-ray scan, as a result of which COVID-19 risk evaluation has become much faster than human radiologists. ATMAN AI developed by DRDO (CAIR division) can detect COVID-19 infection by using X-ray technique, and it replaced CT scan. Google Deep Mind Health Technology integrates ML into a neuroscience system to form a person's brain model using AI and helpful in decision-making support to healthcare professionals. Thus, AI algorithms can determine the danger of cross contamination in an institution then alert human staffs of such risks.
Artificial intelligence in the management of COVID-19 patients
The mismatch between demand and supply of healthcare services has caused the highest mortality during the COVID-19 pandemic. Hospitalized patients, and particularly medical care unit patients, necessitate very resource-intensive and timely treatment. Pertaining to saturation of healthcare system, the HCPs must make fast and informed decisions regarding the treatment protocol of incoming patients.
Artificial intelligence in drug/vaccine discovery
AI can be helpful in predicting the structure of important proteins crucial for virus entry and replication, which will pave the way for drug development during a shorter span of time. AlphaFold algorithm of Google Deep mind incorporates deep residual networks called as ResNets, and it has been useful for predicting various protein structures such as membrane protein of SARS CoV2, which can give huge breakthrough to drug discovery programs. BenevolentAI used ML methods to accelerate its drug discovery program and identified a drug named baricitinib against COVID-19. In silico medicine has identified several small molecules against COVID-19 using AI. Another study combined virtual screening and supervised learning to identify potential drugs against COVID-19. Zhou et al. used an integrative network-based systems pharmacological methodology for finding effective drugs for SARS-CoV-2 from the already existing repertoire of drug molecules and drug combinations. Several other AI-based endeavors including INCL Project named as Identifying Infectious Disease combination therapy with AI and PolypharmDB have been successful in identifying suitable drugs against COVID-19., Ong et al. focused on vaccine candidates for COVID-19 using the reverse vaccinology-ML platform namely VAXIGN that relied on supervised classification models.
What is Third Wave of COVID-19 Pandemic?
The term wave is used to describe up and down trends of infections over a prolonged period. The growth curve during an epidemic or pandemic resembles the shape of a wave. After failure of management of second wave of COVID-19 pandemic in India, probably due to inadequate preparation of health system, officials and health authorities are now routinely warning people of the possibility of a third wave. Based on past experiences, pandemics have several waves (3 waves in Spanish flu in 1918) and mutation of COVID-19 virus, if the COVID appropriate behavior is not followed, then third wave can be presumed. When it arrives, the fear is we will be facing fresh challenges, including lack of enough pediatric COVID care facilities, inadequate health infrastructure in the suburbs and rural areas, and shortage of specific medicines. The national curve seems to have entered a downtrend now, after having peaked on May 6, 2021. If there is further rise in cases after that and continues for certain duration, it would get classified as resurgence or the onset of the third wave/peak. Though the distinct possible third wave is likely to come, the scale or timing is not something that can be predicted. However, it is not inevitable.
Recently, during the fourth wave in Hong Kong, multiple public health policies have been formulated and implemented to reduce the spread of COVID-19. These public health policies proved to be exceptional in its implementation, and nearly, all children and youths with COVID-19 in Hong Kong have had no serious illness.,
How Can Artificial Intelligence Technology be Used for Third Wave?
AI technology has been proven to be useful for the detection of onset of new wave, mutation to new variants, diagnosis and management of cases, drug and vaccine delivery, as well as prevention of further spread.
AI can be used in all the intervals of pandemics formulated by CDC such as investigation, recognition, initiation, acceleration and deceleration, and preparation. Different level of approaches is adopted at different interval of a pandemic.
Investigation: Focus on targeted monitoring and investigationRecognition: Identification of emerging biological threatsInitiation: Mitigation of spread of biological diseasesAcceleration: Used for medical management and resource allocationDeceleration: Accelerating the development of medical therapies and treatment protocolPreparation: Sustenance of the situation and prevention of further recurrence or onset of new waves.
Challenges in Using this Technology
AI has been proved to be one of the useful discoveries and likely to hit the digital health industry along with other industries in the coming years. Although it has enormous growth potential, it still does possess a few limitations/challenges.
The challenges include bias (inherent bias), challenges in computing power, AI integration issues, collection and utilization of relevant data, skilled workforce, implementation issues, and legal issues (due to data security, ethics, and sharing).
If risk reward ratio is calculated, then the rewards will outweigh over risks. AI can be considered as a boon for the society. Much more benefit can be done to the society using the previous experiences with this naïve technology. Workforce must be trained and updated regarding the use of this worth technology. Using this technology in a full-fledged manner can help detect threats beforehand compared to traditional mechanisms and help us understand what kind of interventions prevent disaster, advance prediction of epidemics and pandemics so that preparedness can be done and finally save the society from the deadly consequences of pandemics.
Financial support and sponsorship
Conflicts of interest
There are no conflicts of interest.
|1||Malley CS, Kuylenstierna JC, Vallack HW, Henze DK, Blencowe H, Ashmore MR. Preterm birth associated with maternal fine particulate matter exposure: A global, regional and national assessment. Environ Int 2017;101:173-82.|
|2||Knapp S. Artificial Intelligence: Past, Present, and Future; 2006. Available from: http://www.dartmouth.edu/~vox/0607/0724/ai50.html. [Last accessed on 2021 Jun 25]. |
|3||Morgenstern JD, Rosella LC, Daley MJ, Goel V, Schünemann HJ, Piggott T. “;AI's gonna have an impact on everything in society, so it has to have an impact on public health”: A fundamental qualitative descriptive study of the implications of artificial intelligence for public health. BMC Public Health 2021;21:1-4.|
|4||Kaplan A, Haenlein M. Siri, Siri, in my hand: Who's the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Bus Horiz 2019;62:15-25.|
|5||Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJ. Artificial intelligence in radiology. Nat Rev Cancer 2018;18:500-10.|
|6||Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;542:115-8.|
|7||Wang D, Khosla A, Gargeya R, Irshad H, Beck AH. Deep Learning for Identifying Metastatic Breast Cancer. ArXiv160605718 Cs Q-Bio [Internet]. 2016 Jun 18 [cited 2021 Nov 19]; Available from: http://arxiv.org/abs/1606.05718.|
|8||Realizing AI [Internet]. Modern Healthcare. [cited 2021 Nov 19]. Available from: http://www.modernhealthcare.com/indepth/artificial-intelligence-in-healthcare-makes-slow-impact.|
|9||Panda PS, Bhatia V. Role of artificial intelligence (AI) in public health. Indian J Community Fam Med 2018;4:60.|
|10||Goertzel B. Artificial general intelligence. Pennachin C, editor. New York: Springer; 2007.|
|11||Pennachin C, Goertzel B. Contemporary approaches to artificial general intelligence. InArtificial general intelligence. Springer, Berlin, Heidelberg. 2007;pp:1-30.|
|12||Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J 2019;6:94-8.|
|13||Darlington K. How Artificial Intelligence is helping prevent the spread of the COVID-19 pandemic. IQ: The RIM Quarterly 2020;36:19-21.|
|14||AI Based Intelligent COVID-19 Detector Technology for Medical Assistance (ATMAN). Available from: https://www.drdo.gov.in/ai-based-intelligent-covid-19-detector-technology-medical-assistance- atman. [Last accessed in 2021 Jun 23].|
|15||Knebel AR, Sharpe VA, Danis M, Toomey LM, Knickerbocker DK. Informing the gestalt: An ethical framework for allocating scarce federal public health and medical resources to states during disasters. Disaster Med Public Health Prep 2014;8:79-88.|
|16||Senior AW, Evans R, Jumper J, Kirkpatrick J, Sifre L, Green T, et al. Improved protein structure prediction using potentials from deep learning. Nature 2020;577:706-10.|
|17||Randhawa GS, Soltysiak MP, El Roz H, de Souza CP, Hill KA, Kari L. Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study. PLoS One 2020;15:e0232391.|
|18||Zhou Y, Hou Y, Shen J, Huang Y, Martin W, Cheng F. Network-based drug repurposing for novel coronavirus 2019-nCoV/SARS-CoV-2. Cell Discov 2020;6:1-18.|
|19||Stebbing J, Phelan A, Griffin I, Tucker C, Oechsle O, Smith D, et al. COVID-19: Combining antiviral and anti-inflammatory treatments. Lancet Infect Dis 2020;20:400-2.|
|20||Abdulla A, Wang B, Qian F, Kee T, Blasiak A, Ong YH, et al. Project IDentif. AI: harnessing artificial intelligence to rapidly optimize combination therapy development for infectious disease intervention. Advanced therapeutics 2020;3:2000034.|
|21||Dar'ya SR, MacKinnon SS, Landon M, Windemuth A, Kurji N, Shahani V. PolypharmDB, a deep learning-based resource, quickly identifies repurposed drug candidates for COVID-19.|
|22||Ong E, Wong MU, Huffman A, He Y. COVID-19 coronavirus vaccine design using reverse vaccinology and machine learning. Front Immunol 2020;11:1581.|
|23||Cheng HY, Cohen T, Lin HH. Test, trace, and isolate in the UK. BMJ 2021;372:n822.|
|24||Soto-Calle V, Llacsahuanga L, Rodriguez H, Llanos-Cuentas A, Vinetz J, Gamboa D, Alava F, Torres K. Malaria Situation in the Peruvian Amazon during the COVID-19 Pandemic.|
|25||Chua GT, Xiong X, Choi EH, Han MS, Chang SH, Jin BL, et al. COVID-19 in children across three Asian cosmopolitan regions. Emerg Microbes Infect 2020;9:2588-96.|
|26||Pandemic Intervals Framework (PIF). Available from: https://www.cdc.gov/flu/pandemic-resources/national-strategy/intervals-framework.html. [Last accessed in 2021 Jun 24].|