5 Page paper

Chaos, Solitons and Fractals 139 (2020) 110059

Contents lists available at ScienceDirect

Chaos, Solitons and Fractals Nonlinear Science, and Nonequilibrium and Complex Phenomena

journal homepage: www.elsevier.com/locate/chaos

Review

Applications of machine learning and artificial intelligence for

Covid-19 (SARS-CoV-2) pandemic: A review

Samuel Lalmuanawma a , ∗, Jamal Hussain a , Lalrinfela Chhakchhuak b

a Department of Mathematics & Computer Science, Mizoram University, Tanhril, Aizawl, Mizoram, 796004, India b Department of Computing, Uiversity of York, Heslington, York, YO10 5DD, UK

a r t i c l e i n f o

Article history:

Received 10 June 2020

Accepted 23 June 2020

Available online 25 June 2020

Keywords:

Covid-19

Machine learning

Artificial intelligence

Pandemic

a b s t r a c t

Background and objective: During the recent global urgency, scientists, clinicians, and healthcare experts

around the globe keep on searching for a new technology to support in tackling the Covid-19 pandemic.

The evidence of Machine Learning (ML) and Artificial Intelligence (AI) application on the previous epi-

demic encourage researchers by giving a new angle to fight against the novel Coronavirus outbreak. This

paper aims to comprehensively review the role of AI and ML as one significant method in the arena of

screening, predicting, forecasting, contact tracing, and drug development for SARS-CoV-2 and its related

epidemic.

Method: A selective assessment of information on the research article was executed on the databases

related to the application of ML and AI technology on Covid-19. Rapid and critical analysis of the three

crucial parameters, i.e., abstract, methodology, and the conclusion was done to relate to the model’s pos-

sibilities for tackling the SARS-CoV-2 epidemic.

Result: This paper addresses on recent studies that apply ML and AI technology towards augmenting the

researchers on multiple angles. It also addresses a few errors and challenges while using such algorithms

in real-world problems. The paper also discusses suggestions conveying researchers on model design,

medical experts, and policymakers in the current situation while tackling the Covid-19 pandemic and

ahead.

Conclusion: The ongoing development in AI and ML has significantly improved treatment, medication,

screening, prediction, forecasting, contact tracing, and drug/vaccine development process for the Covid-

19 pandemic and reduce the human intervention in medical practice. However, most of the models are

not deployed enough to show their real-world operation, but they are still up to the mark to tackle the

SARS-CoV-2 epidemic.

© 2020 Elsevier Ltd. All rights reserved.

1

W

c

a

n

D

o

n

a

f

b

W

f

fi

v

p

t

h

p

h

w

C

h

0

. Introduction

There are several disease outbreaks that invaded humanity in

orld history. World Health Organization (WHO), its co-operating

linicians and various national authorities around the globe fight

gainst these pandemics to date. Since the first Covid-19 (Coro-

avirus) disease case confirmed in China December 2019 Wuhan

istrict, the outbreak continues to spread all across the world, and

n 30th January 2020 WHO declared the pandemic as an inter-

ational concern of public health emergency [1] . The novel Coron-

virus (SARS-CoV-2) disease spread on more than 185 countries in-

ecting more than 7,145,800 individuals and causing 407,067 deaths

∗ Corresponding author. E-mail address: [email protected] (S. Lalmuanawma).

I

t

t

ttps://doi.org/10.1016/j.chaos.2020.110059

960-0779/© 2020 Elsevier Ltd. All rights reserved.

y June 09, 2020 [ 2 , 3 ]. To address this global novel pandemic,

HO, scientists and clinicians in medical industries are searching

or new technology to screen infected patients in various stages,

nd best clinical trials, control the spread of this virus, develop a

accine for curing infected patients, trace contact of the infected

atient. Recent studies identified that Machine Learning and Ar-

ificial Intelligence are promising technology employed by various

ealthcare providers as they result in better scale-up, speed-up

rocessing power, reliable and even outperform human in specific

ealthcare tasks [4] . Therefore, healthcare industries and clinicians

orldwide employed various ML and AI technology to tackle the

ovid-19 pandemic to address the challenges during the outbreak.

n medical industries, AI is not applied to replace the human in-

eractions, but to provide decision support for clinicians on what

hey are modeled for [5] .

2 S. Lalmuanawma, J. Hussain and L. Chhakchhuak / Chaos, Solitons and Fractals 139 (2020) 110059

t

m

g

i

c

t

p

o

t

c

D

l

o

8

c

r

s

o

t

u

fi

p

8

t

a

f

g

p

t

b

e

s

d

s

i

This paper focuses on the novel Covid-19 epidemic and how the

modern AI and ML technology were recently employed to solve the

challenges during the outburst. We present comprehensive reviews

of studies on the model and technology applied to tackle the novel

Covid-19 pandemic. The studies further discuss types of AI and ML

methods recently employed integration and types of the dataset,

the final performance of each proposed model, and present on the

pros and cons of modern techniques.

2. ML and AI recently employed to tackle health care

SARS-CoV-2 outbreak

AI and ML technology are used to improve the accuracy of pre-

diction for screening both infectious and non-infectious diseases

[6] . The relation with health care begins with the evolution of the

first expert system called MYCIN developed in 1976 [7] . MYCIN

was designed to use 450 rules collected from a medical expert

to treat bacterial infection by suggesting antibiotics to the pa-

tients. Such an expert system serves as clinical decision support for

clinicians and medical experts [8] . Recent studies evident on the

prospect of ML and AI technology for the various pandemic out-

break, it supports healthcare experts in various communicable dis-

eases (SARS, EBOLA, HIV, COVID_19) [9-17] and non-communicable

diseases (Cancer, Diabetic, Heart disease, and Stroke) [18-25] out-

break.

2.1. ML and AI technology in SARS-CoV-2 screening and treatment

Early detection of any disease, be it infectious and non-

infectious, is critically an important task for early treatment to

save more lives [ 26 , 27 ]. Fast diagnosis and screening process helps

prevent the spread of pandemic diseases like SARS-CoV-2, cost-

effective, and speed up the related diagnosis. The development of

an expert system for health care assists in the new order of identi-

fication screening and management of SARS-CoV-2 carrier by more

cost-effective com pared to the traditional method. ML and AI are

used to augment the diagnosis and screening process of the iden-

Table 1

ML and AL technology in SARS-CoV-2 Screening.

Publication ML/AI method Types of data No of patients

Ardakani, A. A et al .,

[28]

Deep

Convolutional

Neural Network

ResNet-101

Clinical,

Mamographic

1020, 86

Ozturk, T. et al ., [29] Convolutional

Neural Network

DarkCovidNet

Architecture

Clinical,

Mamographic

127, 43 f, 82 m

500, 500

Sun, L et al ., [30] Support Vector

Machine

Clinical, laboratory

features,

Demographics

336, 220

Wu, J. et al ., [31] Random forest

Algorithm

Clinical,

Demographics

253, 169, 49,24

ified patient with radio imaging technology akin to Computed To-

ography (CT), X-Ray, and Clinical blood sample data. In this re-

ard, Table 1 shows selective information on diagnosis and screen-

ng proposed for the Coronavirus disease. The healthcare expert

an use radiology images like X-ray and CT scans as routine tools

o augment traditional diagnosis and screening. Unfortunately, the

erformance of such devices is moderate during the high outburst

f the SARS-CoV-2 pandemic. In this regard, studies [28] show

he potential of AI and ML tools by suggesting a new model that

omes with rapid and valid method SARS-CoV-2 diagnosis using

eep Convolutional Network. The study shows that diagnosis uti-

izing an expert system employing AI and ML on 1020 CT images

f 108 Covid-19 infected patients along with viral pneumonia of

6 patients, the remarkable performance suggests the use of the

onvolutional neural network (Resnet-101) as an adjuvant tool for

adiologist resulting 86.27%, 83.33% of accuracy and specificity re-

pectively.

Recent studies design an auxiliary tool to increase the accuracy

f Covid-19 diagnosis with new model Automatic COVID-19 detec-

ion based on deep learning algorithm [ 29 ]. The developed model

ses raw chest X-ray images of 127 infected patients with 500 no-

ndings and pneumonia cases of 500 records. With remarkable

erformance accuracy, binary class of 98.08%, and multi-class with

7.02%. Multi-classes proved the applicability of the expert system

o assist radiology in validating in screening process rapidly and

ccurately.

Furthermore, researchers have found four important medical

eatures combinations of clinical, laboratory features, and demo-

raphic information using GHS, CD3 percentage, total protein, and

atient age employing Support Vector Machine as the primary fea-

ure classification model [30] . The new model is effective and ro-

ust in predicting patients in critical/severe conditions, and the

mpirical results show that a combination of the four-feature re-

ults an AUROC of 0.9996 and 0.9757 in training and testing

atasets respectively. The survival and the cox-multivariant regres-

ion analysis revealed the model’s significance towards and auxil-

ary tools for the healthcare expert.

Validation

method Sample size Accuracy

Holdout 1020 CT images of 108

volume of patients with

laboratory confirmed

Covid-19, 86 CT images of

viral and atypical pneumonia

patients,

Accuracy: 99.51%

Specificity: 99.02%

Cross-validation 127 X-ray images with 43

female and 82 male positive

cases 500 no-findings and

pneumonia cases of 500

Accuracy: 98.08% on

Binary classes

Accuracy: 87.02% on

Multi-classes

Holdout 336 infected patients with

PCR kit, 26 severe/critical

cases and 310 non-serious

cases and with another

related disease79

hypertension, 29diabetes, 17

coronary disease and 7 having

history of tuberculosis

Accuracy: 77.5%

Specificity: 78.4%

AUROC reaches 0.99

training and 0.98

testing dataset

Cross-validataion Total of 253 samples from 169

patients suspected with

Covid-19 collected from

multiple sources. Clinical

blood test of 49 patients

derived from commercial

clinic center. 24 samples

infected patient with Covid-19

Accuracy: 95.95%

Specificity: 96.95%

S. Lalmuanawma, J. Hussain and L. Chhakchhuak / Chaos, Solitons and Fractals 139 (2020) 110059 3

s

G

w

e

1

i

t

a

l

s

c

e

a

r

h

l

o

i

a

o

m

n

p

2

i

t

t

n

s

t

c

r

s

f

t

c

o

r

u

c

t

A

i

a

A

d

w

c

c

t

d

h

a

p

After evaluating 253 clinical blood samples from Wuhan, re-

earchers found eleven (bilirubin total, creatine kinase isoenzyme,

LU, creatinine, kalium, lactate dehydrogenase, platelet distribution

idth, calcium, basophil, total protein, and magnesium) key rel-

vant indices which can assist as a discrimination tool of Covid-

9 for healthcare expert toward rapid diagnosis [31] . The stud-

es show that 11 relevant indices are extracted after employing

he Random Forest algorithm with an overall accuracy of 95.95%

nd 96.97% specificity respectively. Furthermore, the authors pub-

ished that the tools were deployed and are available on web-

erver at http://lishuyan.lzu.edu.cn/COVID2019 _ 2/ to assist health-

are experts.

The above studies give the evidence of an application of the

xpert system; designing rapid diagnosis was the main objective

long with augmentation of accuracy. Prompt and early detection

educe the spread of the disease and reserve more time to the

ealthcare expert to correspond to the next diagnosis to save more

ives, resulting in low-cost medical expenditure. However, majority

f the studied paper employed a single classification algorithm on

ndividual data or more. Therefore it is suggested to come up with

hybrid classification method applying more potential algorithm

n multi-database or hybrid-database consisting of clinical, mam-

ographic, and demographic data, as each type of data has a sig-

ificant factor that could represent the true identity of the infected

atients and deployment of the application in the real world.

.2. ML and AI technology in SARS-Cov-2 contact tracing

If a person diagnoses and is confirmed with Covid-19, the next

mportant step is contact tracing prevention of the wider spread of

Table 2

Contact tracing application used by Countries.

Sl. No Country Contact tracing App Location tr

1 Australia COVIDSafe BlueTrace

2 Austria Stopp Corona Bluetooth,

3 Bahrain BeAware Bahrain Bluetooth

4 Bulgaria ViruSafe GSM

5 China conjunction with Alipay GPS, GSM,

6 Cyprus CovTracer GPS, GSM

7 Colombia CoronApp GPS

8 Czech Republic eRouška (eFacemask) BlueTrace

9 Estonia Estonia’s App Google/Ap

10 Finland Ketju DP-3T, Blu

11 France StopCovid Bluetooth

12 Germany CoronaApp Bluetooth,

13 Ghana GH Covid-19 Tracker App GPS

14 Hungary VírusRadar Bluetooth

15 Iceland Rakning C-19 GPS

16 India Aarogya Setu Bluetooth

17 Iran Mask.ir GSM

18 Ireland HSE Covid-19 App Bluetooth,

19 Israel HaMagen Standard l

20 Italy Immuni Bluetooth,

21 Jordan AMAN App - Jordan GPS

22 Latvia Apturi Covid Bluetooth

23 Malaysia MyTrace Bluetooth,

24 Mexico CovidRadar Bluetooth

25 New Zealand NZ COVID Tracer Contact de

26 North Macedonia StopKorona Bluetooth

27 Norway Smittestopp Bluetooth

28 Poland ProteGO Bluetooth

29 Qatar Ehteraz Bluetooth

30 Saudi Arabia Corona Map Bluetooth

31 Singapore TraceTogether BlueTrace

32 South Korea Non-app-based Mobile de

33 Switzerland SwissCovid DP-3T pro

34 Turkey Hayat Eve Sigar Bluetooth,

35 UAE TraceCovid Bluetooth

36 UK NHS Covid-19 App Bluetooth

he disease. According to WHO, the infection spreads from person-

o-person primarily through saliva, droplets, or discharges from the

ose through contact transmission [32] . To take control on the

pread of SARS-Cov-2, contact tracing is an essential public health

ool used to break the chain of virus transmission [33] . The pro-

ess of contact tracing is to identify and manage people who are

ecently exposed to an infected Covid-19 patient to avoid further

pread. Generally, the process identifies the infected person with a

ollow-up for 14 days since the exposure. If employed thoroughly,

his process can break the transmission chain of the current novel

oronavirus and suppress the outbreak by giving a higher chance

f adequate controls and helping reduce the magnitude of the

ecent pandemic. In this regard, various infected countries come

p with a digital contact tracing process with the mobile appli-

ation, utilizing different technologies like Bluetooth, Global Posi-

ioning System (GPS), Social graph, contact details, network-based

PI, mobile tracking data, card transaction data, and system phys-

cal address. The digital contact tracing process can perform virtu-

lly real-time and much faster compared to the non-digital system.

ll these digital apps are designed to collect individual personal

ata, which will be analyzed by ML and AI tools to trace a person

ho is vulnerable to the novel virus due to their recent contacted

hain.

As shown in Table 2 , articles [ 34 , 35 ] listed various countries

ompetent with such ML and AL-based contact tracing applica-

ions. Studies show that over 36 Countries successfully employed

igital contact tracing use following centralized, decentralized, or

ybrid of both techniques were proposed to lessen the effort and

ugment the effectiveness of the traditional healthcare diagnosis

rocesses.

acking Launch on

protocol: Bluetooth April 14, 2020

Google/Apple March, 2020

& GSM March 31, 2020

May, 2020

credit-card-transaction-history Very little Info

May, 2020

April 12, 2020

protocol: Bluetooth April 15, 2020

ple, DP-3T, Bluetooth April, 2020

etooth May, 2020

May, 2020

Google/Apple May, 2020

April 12, 2020

May 13, 2020

April 2020

& location-generated social graph April 2, 2020

May, 2020

Google/Apple May, 2020

ocation APIs March, 2020

Google/Apple May, 2020

May, 2020

May, 29, 2020

Google/Apple May 3, 2020

May, 2020

tails and physical address May 20, 2020

April 13, 2020

and GSM April 16, 2020

May, 2020

and GSM May, 2020

April 3, 2020

protocol, Bluetooth March 20, 2020

vice tracking data and card transaction data May, 2020

tocol, Bluetooth, Google/Apple May 20, 2020

GSM April, 2020

May, 2020

May, 2020

4 S. Lalmuanawma, J. Hussain and L. Chhakchhuak / Chaos, Solitons and Fractals 139 (2020) 110059

t

d

T

p

t

s

w

s

i

t

t

S

o

t

r

d

v

w

c

t

a

(

h

m

2

e

b

S

e

f

k

i

m

M

t

i

e

o

g

c

v

F

Concerning contact tracing, studies have proven the use of ML

and AI in augmentation of contact tracing process against infec-

tious Chronic Wasting disease [36] . After applying Graph theory

on infectious animal disease epidemics data, mainly shipment data

between each farm, the resultant graph properties generated by

the proposed model can be used to exploit to augment contact

tracing more efficiently. Moreover, the generated graphs have a po-

tential prediction impact on the number of infections that can take

place. However, there are still limitations in addressing the sce-

nario, privacy, control over the data, and even data security breach.

Countries are working to overcome the challenges; some countries

like Israel “passed an emergency law to use mobile phone data” to

tackle the current pandemic [37] . Among the world contact trac-

ing apps, some countries app violated privacy law and reported

unsafe [35] so far they do the job acceptably by supplement the

manual tracing process. However, virtually every country has their

contact tracing application individually, as the outbreak continues

to spread across the world, it becomes a global health emergency.

To fight against the Covid-19 as one, one should provide a stan-

dard de-facto centralized contact tracing application to trace every

human being all around the world. Also, it is reported that some

specific query needs to address: “Is it mandatory or voluntary?” “Is

the attempt clear or translucent?” “Is information gathering less-

ened?” “Will collected information be demolished as declared?”,

“Is the data safe with the host” and “Are there any restrictions or

control on utilizing the information?”.

2.3. ML and AI technology in SARS-CoV-2 prediction and forecasting

Selective information shown in Table 3 indicates the applica-

tions of ML and AI in forecasting and predicting the novel pan-

demic. A new novel model, that forecast and predicting 1-3 to 6

days ahead of total Covid-19 patient of 10 Brazilian states, using

stacking-ensemble with support vector regression algorithm on the

cumulative positive Covid-19 cases of Brazilian data was proposed,

thus augmenting the short-term forecasting process to alert the

healthcare expert and the government to tackle the pandemic [38] .

Recent studies suggested a novel model using a supervised multi-

layered recursive classifier called XGBoost on clinical and mam-

mographic factor datasets. After applying the model, researchers

found out those three significant key features (high-sensitivity C-

reactive protein, lymphocyte and lactic dehydrogenase (LDH)) of

the 75 features clinical and blood test samples result to be the

highest rank of 90% accuracy in predicting and assessing Covid-19

patient into general, severe and mortality rate [39] . Furthermore,

comparatively higher value in single lactic dehydrogenase appears

to be a significant factor in classifying most patients in need of in-

Table 3

ML and AI applications: prediction and forecasting SARS-CoV-2.

Publication ML/AI method Types of data No of pat

Ribeiro, M. H. D. M.,

et al ., [37]

Support Vector Regression and

stacking-ensemble

Clinical 40.581

Yan, L. et al ., [38] XGBoost classifier Clinical, Blood

samples of 75

features

485

Chimmula, V.K.R.,

et al ., [39]

Deep Learning using LSTM

network

Demographic John Hop

Canadian

containin

March 31

Chakraborty, T. and

Ghosh, I. [40]

Hybrid Wavelet- autoregressive

integrated moving average model

and regression tree

Demographic India: 64

France: 7

ensive medical care, as LDH degree related to various respiratory

isorder diseases, namely asthma and bronchitis, and pneumonia.

he forecast model employed decision rule to forecast rapidly and

redict infected individuals at the highest risk, authorized patients

o be manageable for intensive care, and possibly lessen the tran-

ience rate. A Canadian based forecasting model using time-series

as developed employing Deep learning algorithm for the long-

hort-term-memory network, the studies found out a key factor

ntended for predicting the course with an ending point estima-

ion of the current SARS-CoV-2 epidemic in Canada and all over

he globe [40] . The suggested model forecast ending point of this

ARS-CoV-2 outbreak in Canada will be around June 2020. Based

n the data collected from John Hopkins University [3] , the predic-

ion was likely to be accurate as newly infected cases have dropped

apidly and proven the applicability of the expert system in pre-

icting and forecasting for the current pandemic outbreak by re-

ealing key significant features. The real-time forecasting model

as proposed combining the goodness of the wavelet-based fore-

asting model and autoregressive integrated moving average based

ime-series model [41] . The model solves the problem by gener-

ting short-term forecasts of the SARS-CoV-2 for various countries

India, United Kingdom, Canada, South Korea, and France) to assist

ealthcare experts and policymakers as a preliminary cautioning

odule for each target country.

.4. ML and AI technology in SARS-CoV-2 drugs and vaccination

Since the coronavirus epidemic fury, researchers and healthcare

xperts around the globe ubiquitously urged to develop a possi-

le choice to tackle the development of drug and vaccine for the

ARS-CoV-2 pandemic, and ML/AI technology constitutes to be an

nthralling road. Concerning the possibility of drug choice for in-

ected patient’s treatment, instant testing on the existing old mar-

etable medicines for novel SARS-CoV-2 carrier in a human being

s essential.

Researchers from Taiwan are building a new model to aug-

ent the development of a novel drug [42] . After applying the

L and AI technology-based model on two datasets (one using

he 3C-like protease constraint and other data-holding records of

nfected SARS-CoV, SARS-Cov-2, influenza, and human immunod-

ficiency virus (HIV)) using Deep Neural Network on the eighty

ld drugs with potential for Covid-19 treatment, the study sug-

ested eight drugs, i.e., vismodegib, gemcitabine, clofazimine, cele-

oxib, brequinar, conivaptan, bedaquiline and tolcapone are found

irtually effective against feline infectious peritonitis coronavirus.

urthermore, other five drugs like homoharringtonine, salinomycin,

ients Validation method Results

Holdout Accuracy: Error in range of

0.87%-3.51% one, 1 .02%–5.63%

three and 0.95% -6.90% six day

ahead

Cross-validation Accuracy: 90%

kins University &

Health authority, data

g infected cases upto

, 2020

Cross-validation Ending point of the pandemic

outbreak in Canada was

predicted on June 2020

UK: 65 Canada:70

1 South Korea: 76

Cross-validation Real-time forecast and 10 days

ahead, Observed seven key

features associated with dead

rate.

S. Lalmuanawma, J. Hussain and L. Chhakchhuak / Chaos, Solitons and Fractals 139 (2020) 110059 5

b

d

w

t

v

m

p

t

a

d

b

1

l

r

l

p

d

i

c

f

a

m

v

t

l

S

f

b

d

t

o

o

f

o

l

e

a

o

c

a

c

h

3

m

a

s

d

r

a

p

a

g

g

p

b

r

p

w

c

e

a

v

u

a

f

g

p

p

c

p

H

t

t

D

R

oceprevir, tilorone and chloroquine are also found operational

uring AI experimental environment.

A novel molecule transformer-drug target interaction model

as proposed jointly by researchers from the US and Korea to

ackle the need for an antiviral drug that can treat the Covid-19

irus [43] . The study compares the accessible virtual screening and

olecular docking application called AutoDock Vina with the pro-

osed model employing a deep learning algorithm on 3C-like pro-

einase of Covid-19 and FDA approved 3,410 existing drugs avail-

ble in the market. The result revealed that a popular antiretroviral

rug used to treat HIV called Antazanavir (Kd of 94.94 nM) is the

est drug for Covid-19 medication, followed by Remdisivir (Kd of

13.13 nM). Furthermore, results revealed that some medications

ike darunavir, ritonavir, and lopinavir were outlined to tackle vi-

al proteinases. It was also found that various antiviral compounds

ike Kaletra might be utilized for the medicine of Covid-19 human

atients.

A group of researchers from the USA discovered an antiviral

rug for treating the Ebola virus. The discovery was first active

n the year 2014 [44] , starting with ML and AI-based pharma-

ophore computational analyzing on a limited size of in vitro in-

ected carriers of the Ebola virus. The study proposed an amodi-

quine and chloroquine compound popularly used to treat the

alaria virus. Furthermore, after uncovering a decade of drug de-

elopment based on ML and AI technology, a fusion of compu-

ational screening method with docking application and machine

earning for choosing supplementary medication to investigate on

ARS-CoV-2 was proposed [45] . Researchers refer to the success-

ul discovery of Ebola [44] , and the Zika virus [46] experience gain

elief that the same model could be repeatedly utilized for drug

iscovery on Covid-19 and future virus pandemic ahead.

The selected review paper adopted various methodologies and

echnologies addressing the classical method of classification based

n statistics to an advanced modern AI and ML algorithm. The use

f computational tools, combined with docking application, was

ound to be more active in predicting the reusability of an existing

ld drug on Covid-19 medication and dramatically minimize the

evel of a risk factor in the development of medicine more cost-

ffective process. During this urgency, the use of ML and AI can

ugment the drug development process by lessening the time slot

n discovering a supplementary treatment and medication for the

arrier by drawing a vast probability over security, manageability,

nd clinical information on the existing drug compound. Issues and

hallenges found in this area were the limited resource of compre-

ensive hybrid data and real-life deployment of the application.

. Conclusion and discussion

Since the outbreak of the novel SARS-CoV-2, scientists and

edical industries around the globe ubiquitously urged to fight

gainst the pandemic, searching alternative method of rapid

creening and prediction process, contact tracing, forecasting, and

evelopment of vaccine or drugs with the more accurate and

eliable operation. Machine Learning and Artificial Intelligence

re such promising methods employed by various healthcare

roviders. This paper addresses on recent studies that apply such

dvance technology in augmenting the researchers in multiple an-

les, addressing the troubles and challenges while using such al-

orithm in assisting medical expert in real-world problems. This

aper also discusses suggestions conveying researchers on AI/ML-

ased model design, medical experts, and policymakers on few er-

ors encountered in the current situation while tackling the current

andemic. This review shows that the use of modern technology

ith AI and ML dramatically improves the screening, prediction,

ontact tracing, forecasting, and drug/vaccine development with

xtreme reliability. Majority of the paper employed deep learning

lgorithms and is found to have more potential, robust, and ad-

ance among the other learning algorithms. However, the current

rgency requires an improved model with high-end performance

ccuracy in screening and predicting the SARS-CoV-2 with a dif-

erent kind of related disease by analyzing the clinical, mammo-

raphic, and demographic information of the suspects and infected

atients. Finally, it is evident that AI and ML can significantly im-

rove treatment, medication, screening & prediction, forecasting,

ontact tracing, and drug/vaccine development for the Covid-19

andemic and reduce the human intervention in medical practice.

owever, most of the models are not deployed enough to show

heir real-world operation, but they are still up to the mark to

ackle the pandemic.

eclaration of Competing Interest

None.

eferences

[1] Sohrabi C, Alsafi Z, O’Neill N, Khan M, Kerwan A, Al-Jabir A, Losifidis C, Agha R.

World health organization declares global emergency: a review of the 2019

novel coronavirus (COVID-19). Int J Surg 2020. doi: 10.1016/j.ijsu.2020.02.034 . [2] WHO: World Health Organization, 2020. Coronavirus disease (COVID-

2019) situation Reports. https://www.who.int/emergencies/diseases/novel- coronavirus- 2019/situation- reports/ (accessed 09 June 2020).

[3] JHU: John Hopkins University, 2020. COVID-19 Dashboard by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University (JHU).

https://www.coronavirus.jhu.edu/map.html (accessed 09 June 2020). [4] Davenport T, Kalakota R. The potential for artificial intelligence in healthcare.

Fut Healthc J 2019;6(2):94–8. doi: 10.7861/futurehosp.6- 2- 94 .

[5] Phillips-Wren, G., Ichalkaranje, N., & Jain, L.C. (Eds.). (2008). Intelligent decision making: an AI-based approach. Studies in computational intelligence. doi: 10.

1007/978- 3- 540- 76829- 6 . [6] Agrebi, S., & Larbi, A. (2020). Use of artificial intelligence in infectious

diseases. Artificial intelligence in precision health, 415–438. doi: 10.1016/ b978- 0- 12- 817133- 2.0 0 018- 5 .

[7] Shortliffe EH. Computer-based medical consultations. Mycin. Elsevier; 1976.

doi: 10.1016/B978- 0- 4 4 4- 00179- 5.50 0 08- 1 . [8] Peiffer-Smadja N, Rawson TM, Ahmad R, Buchard A, Pantelis G, Lescure F-X,

Birgand G, Holmes AH. Machine learning for clinical decision support in infec- tious diseases: a narrative review of current applications. Clin Microbiol Infect

2019. doi: 10.1016/j.cmi.2019.09.009 . [9] Barbat MM, Wesche C, Werhli AV, Mata MM. An adaptive machine learning ap-

proach to improve automatic iceberg detection from SAR images. ISPRS J Pho-

togramm Remote Sens 2019;156:247–59. doi: 10.1016/j.isprsjprs.2019.08.015 . [10] Li H-C, Yang G, Yang W, Du Q, Emery WJ. Deep nonsmooth nonnegative matrix

factorization network factorization network with semi-supervised learning for SAR image change detection. ISPRS J Photogramm Remote Sens 2020;160:167–

79. doi: 10.1016/j.isprsjprs.2019.12.002 . [11] Shang R, Qi L, Jiao L, Stolkin R, Li Y. Change detection in SAR images by arti-

ficial immune multi-objective clustering. Eng Appl Artif Intell 2014;31:53–67.

doi: 10.1016/j.engappai.2014.02.004 . [12] Gao F, You J, Wang J, Sun J, Yang E, Zhou H. A novel target detection method

for SAR images based on shadow proposal and saliency analysis. Neurocom- puting 2017;267:220–31. doi: 10.1016/j.neucom.2017.06.004 .

[13] Colubri A, Hartley M-A, Siakor M, Wolfman V, Felix A, Sesay T, Shaffer JG, Garry RF, Grant DS, Levine AC, Sabeti PC. Machine-learning prognostic mod-

els from the 2014–16 Ebola Outbreak: data-harmonization challenges, valida-

tion strategies, and mHealth applications. EClinicalMedicine. 2019. doi: 10.1016/ j.eclinm.2019.06.003 .

[14] Choi S, Lee J, Kang M-G, Min H, Chang Y-S, Yoon S. Large-scale machine learn- ing of media outlets for understanding public reactions to nation-wide viral

infection outbreaks. Methods 2017;129:50–9. doi: 10.1016/j.ymeth.2017.07.027 . [15] Nápoles G, Grau I, Bello R, Grau R. Two-steps learning of Fuzzy Cognitive Maps

for prediction and knowledge discovery on the HIV-1 drug resistance. Expert

Syst Appl 2014;41(3):821–30. doi: 10.1016/j.eswa.2013.08.012 . [16] Chockanathan U, DSouza AM, Abidin AZ, Schifitto G, Wismüller A. Auto-

mated diagnosis of HIV-associated neurocognitive disorders using large-scale Granger causality analysis of resting-state functional MRI. Comput Biol Med

2019;106:24–30. doi: 10.1016/j.compbiomed.2019.01.006 . [17] To ̆gaçar M, Ergen B, Cömert Z. COVID-19 detection using deep learning models

to exploit social mimic optimization and structured chest X-ray images us- ing fuzzy color and stacking approaches. Comput Biol Med 2020;121:103805.

doi: 10.1016/j.compbiomed.2020.103805 .

[18] Vaka AR, Soni B. Breast cancer detection by leveraging Machine Learning. ICT Express. 2020. doi: 10.1016/j.icte.2020.04.009 .

[19] Saxena S, Gyanchandani M. Machine learning methods for computer-aided breast cancer diagnosis using histopathology: a narrative review. J Med Imag-

ing Radiat Sci 2019. doi: 10.1016/j.jmir.2019.11.001 .

6 S. Lalmuanawma, J. Hussain and L. Chhakchhuak / Chaos, Solitons and Fractals 139 (2020) 110059

[

[20] Nazir T, Irtaza A, Shabbir Z, Javed A, Akram U, Mahmood MT. Diabetic retinopathy detection through novel tetragonal local octa patterns and extreme

learning machines.. Artif Intell Med 2019. doi: 10.1016/j.artmed.2019.07.003 . [21] Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I. Ma-

chine learning and data mining methods in diabetes research. Comput Struct Biotechnol J 2017;15:104–16. doi: 10.1016/j.csbj.2016.12.005 .

[22] Sharma P, Choudhary K, Gupta K, Chawla R, Gupta D, Sharma A. Artificial plant optimization algorithm to detect heart rate & presence of heart disease us-

ing machine learning.. Artif Intell Med 2019:101752. doi: 10.1016/j.artmed.2019.

101752 . [23] Karen Garate-Escamilla, A., Hassani, A. H. E., & Andres, E. (2020). Classification

models for heart disease prediction using feature selection and PCA. Informat- ics in medicine unlocked, 100330. doi: 10.1016/j.imu.2020.100330 .

[24] Liu T, Fan W, Wu C. A hybrid machine learning approach to cerebral stroke prediction based on imbalanced medical dataset.. Artif Intell Med 2019:101723.

doi: 10.1016/j.artmed.2019.101723 .

[25] Dourado Jr CMJM, da Silva, SPP, da Nóbrega RVM, da S, Barros AC, Filho PPR, de Albuquerque VHC. Deep learning IoT system for online stroke detection in

skull computed tomography images. Comput Net 2019;152:25–39. doi: 10.1016/ j.comnet.2019.01.019 .

[26] Vaishya R, Javaid M, Khan IH, Haleem A. Artificial Intelligence (AI) applications for COVID-19 pandemic. Diabetes Metab Syndr 2020;14(4):337–9. doi: 10.1016/

j.dsx.2020.04.012 .

[27] Ai T, Yang Z, Hou H, Zhan C, Chen C, Lv W, Tao Q, Sun Z, Xia L. Correla- tion of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in

China: a report of 1014 cases.. Radiology 2020. https://doi.org/10.1148/radiol. 2020200642 .

[28] Ardakani AA, Kanafi AR, Acharya UR, Khadem N, Mohammadi A. Application of deep learning technique to manage COVID-19 in routine clinical practice us-

ing CT images: results of 10 convolutional neural networks. Comput Biol Med

2020;121:103795. 2020 https://doi.org/10.1016/j.compbiomed.2020.103795 . [29] Ozturk T, Talo M, Yildirim EA, Baloglu UB, Yildirim O, Rajendra Acharya U.

Automated detection of COVID-19 cases using deep neural networks with X- ray images. Comput Biol Med 2020:103792. doi: 10.1016/j.compbiomed.2020.

103792 . [30] Sun L, Liu G, Song F, Shi N, Liu F, Li S, Li P, Zhang W, Jiang X, Zhang Y,

Sun L, Chen X, Shi Y. Combination of four clinical indicators predicts the se-

vere/critical symptom of patients infected COVID-19.. J Clin Virol 2020:104431. doi: 10.1016/j.jcv.2020.104431 .

[31] Wu, J., Zhang, P., Zhang, L., Meng, W., Li, J., Tong, C., Li, Y., Cai, J., Yang, Z., JZhu, J., Zhao, M., Huang, H., Xie, X. and Li, S. (2020). Rapid and accurate identifica-

tion of COVID-19 infection through machine learning based on clinical avail- able blood test results. medRxiv Preprint doi: https://doi.org/10.1101/2020.04.

02.20051136 .

[32] WHO: World Health Organization, 2020. Health Topic, Coronavirus disease overview. https://www.who.int/health- topics/coronavirus#tab=tab _ 1 (accessed

29 May 2020).

[33] WHO: World Health Organization, 2020. Contact tracing in the con- text of COVID-19. https://www.who.int/publications- detail/contact- tracing-

in- the- context- of- covid- 19 (accessed 29 May 2020). [34] Wikipedia: Covid-19 apps, 2020. https://en.wikipedia.org/wiki/COVID- 19 _

apps#Centralized _ contact _ tracing (Accessed 2 June 2020). [35] MIT: Covid Tracing Tracker - a flood of coronavirus apps are tracking us. Now

it’s time to keep track of them. https://www.technologyreview.com/2020/05/ 07/10 0 0961/launching- mittr- covid- tracing- tracker/ (accessed 5 June, 2020).

[36] Rorres C, Romano M, Miller JA, Mossey JM, Grubesic TH, Zellner DE, Smith G.

Contact tracing for the control of infectious disease epidemics: chronic wasting disease in deer farms. Epidemics 2018;23:71–5. doi: 10.1016/j.epidem.2017.12.

006 . [37] BBC: Coronavirus: Israel enables emergency spy powers. https://www.bbc.com/

news/technology- 51930681 (Accessed 3 June 2020). [38] Ribeiro MHDM, da Silva RG, Mariani VC, Coelho LDS. Short-term forecasting

COVID-19 cumulative confirmed cases: perspectives for Brazil.. Chaos, Solitons

Fractals 2020:109853. doi: 10.1016/j.chaos.2020.109853 . [39] Yan L, Zhang H-T, Goncalves J, Xiao Y, Wang M, Guo Y, Sun C, Tang X, Jing L,

Zhang M, Huang X, Xiao Y, Cao H, Chen Y, Ren T, Wang F, Xiao Y, Huang S, Tan X, Huang N, Jiao B, Cheng C, Zhang Y, Luo A, Mombaerts L, Jin J, Cao Z,

Li S, Xu H, Yuan Y. An interpretable mortality prediction model for COVID-19 patients. Nat Mach Intell 2020. doi: 10.1038/s42256- 020- 0180- 7 .

[40] Chimmula VKR, Zhang L. Time series forecasting of COVID-19 transmission in

Canada using LSTM Networks. Chaos, Solitons Fractals 2020:109864. doi: 10. 1016/j.chaos.2020.109864 .

[41] Chakraborty T, Ghosh I. Real-time forecasts and risk assessment of novel coronavirus (COVID-19) cases: a data-driven analysis.. Chaos, Solitons Fractals

2020:109850. doi: 10.1016/j.chaos.2020.109850 . [42] Ke Y-Y, Peng T-T, Yeh T-K, Huang W-Z, Chang S-E, Wu S-H, Hung H-C, Hsu T-A,

Lee S-J, Song J-S, Lin W-H, Chiang T-J, Lin J-H, Sytwu H-K, Chen C-T. Artifi-

cial intelligence approach fighting COVID-19 with repurposing drugs. Biomed J 2020. doi: 10.1016/j.bj.2020.05.001 .

[42] Beck BR, Shin B, Choi Y, Park S, Kang K. Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through

a drug-target interaction deep learning model. Comput Struct Biotechnol J 2020;18:784–90. doi: 10.1016/j.csbj.2020.03.025 .

44] Ekins S , Freundlich J , Coffee M . A common feature pharmacophore for FDA-ap-

proved drugs inhibiting the Ebola virus. F10 0 0Research 2014;3:277 . [45] Ekins S, Mottin M, Ramos PRPS, Sousa BKP, Neves BJ, Foil DH, Zorn KM,

Braga RC, Coffee M, Southan C, Puhl CA, Andrade CH. Déjà vu: stimulating open drug discovery for SARS-CoV-2. Drug Discov Today 2020. doi: 10.1016/j.

drudis.2020.03.019 . [46] Ekins, S., Mietchen, D., Coffee, M., Stratton, T.P., Freundlich, J.S., Freitas-Junior,

L., Muratov, E., Siqueira-Neto, J., Williams, A. J. and Andrade, C. (2016). Open

drug discovery for the Zika virus. F10 0 0 Research. http://dx.doi.org/10.12688/ f10 0 0research.8013.1 .