We are IntechOpen,

the world’s leading publisher of

Open Access books
Built by scientists, for scientists

7,200
Open access books available
192,000
International authors and editors
210M Downloads

Our authors are among the

154
Countries delivered to
TOP 1%
most cited scientists
14%
Contributors from top 500 universities

Selection of our books indexed in the Book Citation Index

in Web of Science™ Core Collection (BKCI)

Interested in publishing with us?

Contact [email protected]
Numbers displayed above are based on latest data collected.
For more information visit www.intechopen.com
Chapter

Artificial Intelligence in
Healthcare: An Overview
Syed Shahwar Anwar, Usama Ahmad, Mohd Muazzam Khan,
Md. Faheem Haider and Juber Akhtar

Abstract

The healthcare industry is advancing ahead swiftly. For many healthcare

organizations, being able to forecast which treatment techniques are likely to be
successful with patients based on their makeup and treatment framework is a big
step forward. Artificial intelligence has the potential to help healthcare providers in
a variety of ways, including patient care and administrative tasks. The technology
aims to mimic human cognitive functions, as it offers numerous advantages over
traditional analytics and other clinical decision-making tools. Data becomes more
precise and accurate, allowing the healthcare industry to have more insights into the
theranostic processes and patient outcomes. This chapter is an overview of the use
of artificial intelligence in radiology, cardiology, ophthalmology, and drug discov-
ery process.

Keywords: artificial intelligence, algorithms, healthcare, radiology, cardiology,

drug discovery

1. Introduction

In the field of healthcare, Artificial Intelligence (AI) is the privilege to breathe.

It’s a maneuver of the algorithm for the purpose of diagnosis, prognosis, or treat-
ment of certain diseases. AI is the convergence of human and machine learning.
John McCarthy, one of the founding fathers of AI, defined it as “the science and
engineering of making intelligent machines” [1]. In this current era, intelligent
machines pertain in various domains like financial, automatic driving, smart
home, etc. In healthcare, machine learning is widely used to build automated
clinical decision systems and in the treatment of different diseases [2]. AI utilizes
advanced algorithms to learn from healthcare data and assist healthcare profes-
sionals in clinical practice. It has self-correcting and learning capabilities to cope
with its exactness based on analysis [3]. AI can detect the spread of endemics by
tracking animals and plant diseases and by accessing global airline ticketing data
that are when and where the infected residents are moving and detect when an
endemic can become a pandemic. The advancement in AI and its caliber to imitate
human intelligence is heading towards the passing of Turing test [4] and AI will
have a major impact on the forthcoming industrial revolution [5].

1
Smart Drug Delivery

1.1 History/evolution

AI is the ray of computer science that deals with counterfeit intelligent human
behavior. Using an electric circuit, Dr. Warren Mculloch and Dr. Walter Pitts [6]
described neuronal activity and their modeling and explained the notion of neural
networks. AI was first coined at Dartmouth college conference in 1956 [7] and the
primitive work of AI was recorded in the 1970s after 15 years of existence of AI.
The dendral experiment was the early employment of AI in life science [8]. The
interpretation of electrocardiogram (ECG) stepped from 1970 to 1990 is considered
as a major development in the field of AI [9]. A clinical decision support system
was developed during the 20th century [10, 11]. However, the eagerness about AI
was at its peak during the 1980s, but the phenomena of “AI winter” occurred due
to groundless forecasting by the observers led to a lack of funding and interest
[12]. There was continuous progress in building artificial intelligence in mid-20s
by improving the algorithm and feeding the huge data of healthcare and its intel-
ligence makes it cognizance of assisting the clinical cases of patients with the
support of healthcare professionals. The renaissance of AI happened in 2012 after
the evolution of image classifiers [13] and incorporation of AI in patients treatment
needs to be trained on the basis of large data of clinical case studies so that it can
examine the patient condition on the basis of history and the data which it has and
results in diagnosis and in treatment methodology. The devices which favors in the
department of healthcare are trained through machine learning. Basically, machine
learning makes computer learn by the provided data i.e. algorithm in great measure
[14, 15]. Supervised and unsupervised machine learning are two paradigms of
machine learning [16]. Supervised machine learning classified the large data result
and separate it into different categories and also predicts the result i.e. regression.
In unsupervised machine learning there is no result prediction and it conglomerates
the results [17].
The proof of AI and its concept has been demonstrated since older times. The
history has been recorded with such minds related to the AI and executed their
intellections and till today there are a new development, researches, and inventions
going on in the field of AI and its application in different branches of healthcare.

2. Applications in healthcare industry

AI has proliferated its roots in the noble profession of healthcare. There is a

boom in the use of AI, from detection of pulse rate to cancer detection and therapy
consultation, from complete medical history to health monitoring to maintain
and analyze the healthcare system. It is a helping hand in drug discovery and drug
creation database and all this is implemented by the use of the algorithm and deep
neural network.
Currently, AI is being used in various healthcare departments like radiology,
cardiology, hematology, ophthalmology, and also in the management of various
diseases.

2.1 AI in cardiology

AI in cardiology assists healthcare professionals in detecting the changes in

normal heart functioning and helping in making a clinical decision. ECG is also
a contribution of AI. There are various devices that are used in the monitoring
of heart rate, blood pressure, tachycardia, bradycardia, stroke, and atrial fibril-
lation which works on the algorithm and deep neural network. These devices are

2
Artificial Intelligence in Healthcare: An Overview
DOI: http://dx.doi.org/10.5772/intechopen.102768

Figure 1.
Use of artificial intelligence in cardiology.

user-friendly and alarm the individual who is using them. Wearables that detect
biological activity also work on the same principle [18]. A schematic representation
of the use of AI in cardiology is given in Figure 1.

2.2 AI in radiology

AI and radiology together have brought a drastic change in the field of healthcare.
The dawn of the application of AI in radiology was since 1960s [19]. Medical imaging
in the detection and diagnosis of diseases is the widest use of machine learning in the
field of healthcare [20]. CT scans, MRI, tomography, X-Ray are used algorithms in
radiodiagnosis. The machines detect and pinpoint the changes on the basis of large
data by which the neural network has been trained. The AI in radiology is applied for
the detection of breast cancer at an early stage by mammography scans [21, 22] and
tumors, tuberculosis, or diseases related to lungs with chest radiography [23–27]. A
schematic representation of clinical radiology workflow is given in Figure 2.

2.3 AI in ophthalmology

In ophthalmology AI is tremendously used in detection and monitoring of

diabetic retinopathy [28–33], glaucoma [29, 34, 35], age-related macular degeneration
(AMD) [29, 36, 37], retinopathy of prematurity (ROP) [38] with the help of retinal
cameras of fundus photography [16]. The diagnosis of ocular diseases is based on the
deep learning system that is trained on the numerous images of each disease. A study
of the population with diabetes from US, Australia, Europe, and Asia in the years
between 1980 to 2008 shows the frequency of diabetic retinopathy of 34.6% and 7%
vision-threatening diabetic retinopathy [39]. Thus, continuous monitoring along

3
Smart Drug Delivery

Figure 2.
Clinical radiology workflow.

Figure 3.
Use of AI in diabetic retinopathy diagnosis and treatment.

with the treatment can prevent vision loss. A schematic representation of the use of
AI in ophthalmology is depicted in Figure 3 [40].
Machine learning models such as visual fields, optical coherence tomography
(OCT), and optic disc characters are used for the diagnosis of glaucoma [41].
Glaucoma is a medical condition in which the intraocular pressure inside the eye
rises up. Age-related macular degeneration (AMD) is a condition in which there is
degeneration in the center of the retina and is responsible for vision loss. Spectral
OCT is used in the diagnosis of AMD [42]. Retinopathy of Prematurity (ROP) is
a disease that occurs in premature born babies and the leading cause of childhood
blindness due to abnormal growth of blood vessels towards the edge of retina.
Wide-angle retinal images with machine learning [43] and i-ROP DL system which
works on the basis of convolutional neural network (CNN) was trained on the
images more than 5000 in number with a single standard reference diagnosis (RSD)
[44] for the diagnosis of ROP.

4
Artificial Intelligence in Healthcare: An Overview
DOI: http://dx.doi.org/10.5772/intechopen.102768

Figure 4.
Biopharmaceutical companies using AI technology in drug discovery.

2.4 AI in drug discovery

In this modern era, AI is used for drug discovery and drug design on the basis of
artificial neural network (ANN), algorithm, and deep learning. In drug discovery,
inaugural employment of ANN was in 1970 to detect whether the 1,3-dioxane is physi-
ologically active or not [45]. The application of ANN in Quantity Structure Activity
Relationship (QSAR) is the next stage in the field of drug discovery [46]. QSAR studies
were involved in drug design since 1960 by involving the simple structures to know the
activity of the combination of compounds [47]. Currently the biological and physico-
chemical activity i.e. ADMET (Absorption, distribution, metabolism, excretion, and
toxicity), binding constants according to their binding sites are also vaticinated using
ANN which is trained on various sets of compounds in the field of drug discovery [48].
The application of AI is at every step of the drug discovery process, from identification
of drug targets to new drug molecule research following its volunteer election for clini-
cal trials [49–51] also its pharmacological property [52], its binding effect with protein,
potency and synergistic effect with other drugs [53, 54]. Docking software which is
used to find the perfect binding molecule for the particular receptor and its activity
also works on the algorithm. AI has simplified the process of drug discovery by saving
time and money expenditure of US$2.5 billion on R&D [55]. Thus, AI has routed the
drug discovery process into simpler, quicker, and cost-effective, an example of drug
discovery is by BenevolentBio which has its own AI platform and was asked to sug-
gest the treatment of amyotrophic lateral sclerosis (ALS) also called as motor neuron
diseases (MND) and has displayed nearly 100 of drugs, five drugs were selected out of
which four of them were effective and one was showing delayed neurological symp-
toms on mice [56]. The top multinational biopharmaceutical companies have started
using AI technology in their drug discovery (Figure 4) [57].

3. Conclusion

Artificial intelligence is an important and valuable technology that offers prom-

ising solutions to healthcare industry needs. It opens up gateways to individualized

5
Smart Drug Delivery

treatment approaches tailored to the needs of individual patients. It offers multiple

advantages over traditional analytics and other clinical decision-making tools.
Data becomes more precise and accurate allowing the healthcare industry to have
more insights into the diagnosis and treatment processes thereby improving patient
outcomes.

Author details

Syed Shahwar Anwar, Usama Ahmad*, Mohd Muazzam Khan, Md. Faheem Haider
and Juber Akhtar
Faculty of Pharmacy, Integral University, Lucknow, India

*Address all correspondence to: [email protected]

© 2022 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms
of the Creative Commons Attribution License (http://creativecommons.org/licenses/
by/3.0), which permits unrestricted use, distribution, and reproduction in any medium,
provided the original work is properly cited.

6
Artificial Intelligence in Healthcare: An Overview
DOI: http://dx.doi.org/10.5772/intechopen.102768

References

[1] Reddy S, Fox J, Purohit MP. Artificial [11] Musen MA, Middleton B,
intelligence-enabled healthcare delivery. Greenes RA. Clinical decision-support
Journal of the Royal Society of systems. In: Biomedical Informatics.
Medicine. 2019;112(1):22-28 London: Springer; 2014. pp. 643-674

[2] Koprowski R and Foster KR. Machine [12] Shortliffe EH. Artificial intelligence
Learning and Medicine: Book Review in medicine: Weighing the
and Commentary. 2018 accomplishments, hype, and promise.
Yearbook of Medical Informatics.
[3] Pearson T. How to Replicate Watson 2019;28(01):257-262
Hardware and Systems Design for your
Own Use in your Basement. Watson, [13] Krizhevsky A, Sutskever I,
MN, USA: IBM; 2011 Hinton GE. Imagenet classification with
deep convolutional neural networks. In:
[4] Alan M. Turing. Computing Advances in Neural Information
machinery and intelligence. Mind. Processing Systems. 2012. pp. 1097-1105
1950;59(236):433-460
[14] Hastie T, Tibshirani R, Friedman J.
[5] Monostori L. Cyber-physical The Elements of Statistical Learning:
production systems: Roots, expectations Data Mining, Inference, and Prediction.
and R&D challenges. Procedia CIRP. Springer Science & Business Media; 2009
2014;17:9-13
[15] Abu-Mostafa YS, Magdon-Ismail M
[6] Palm G. Warren mcculloch and and Lin HT. Learning from Data. 2012.
walter Pitts: A logical calculus of the AMLbook. Com. 2008
ideas immanent in nervous activity. In:
Brain Theory. Berlin, Heidelberg: [16] Yu KH, Beam AL, Kohane IS.
Springer; 1986. pp. 229-230 Artificial intelligence in healthcare.
Nature Biomedical Engineering.
[7] History of Artificial Intelligence. 2018;2(10):719-731
Available from: http://en.wikipedia.org/
wiki/History_of_artificial_intelligence [17] Deo RC. Machine learning in
[Accessed: June 1, 2020] medicine. Circulation. 2015;132(20):
1920-1930
[8] Lindsay R, Buchanan B, Feigenbaum
E and Lederberg J. Applications of [18] Krittanawong C, Johnson KW,
Artificial Intelligence for Organic Hershman SG, Tang WW. Big data,
Chemistry. 1980 artificial intelligence, and
cardiovascular precision medicine.
[9] Kundu M, Nasipuri M, Basu DK. Expert Review of Precision Medicine
Knowledge-based ECG interpretation: A and Drug Development. 2018;3(5):
critical review. Pattern Recognition. 305-317
2000;33(3):351-373
[19] Lodwick GS, Haun CL, Smith WE,
[10] Miller RA. Medical diagnostic Keller RF, Robertson ED. Computer
decision support systems—Past, diagnosis of primary bone tumors: A
present, and future: A threaded preliminary report. Radiology.
bibliography and brief commentary. 1963;80(2):273-275
Journal of the American Medical
Informatics Association. 1994;1(1): [20] Yu KH, Beam AL, Kohane IS.
8-27 Artificial intelligence in healthcare.

7
Smart Drug Delivery

Nature Biomedical Engineering. [28] Varma R. How AI Benefits Patients

2018;2(10):719-731 and Physicians. 2018

[21] Samala RK, Chan HP, Hadjiiski L, [29] Ting DSW, Cheung CYL, Lim G,
Helvie MA, Wei J, Cha K. Mass Tan GSW, Quang ND, Gan A, et al.
detection in digital breast Development and validation of a deep
tomosynthesis: Deep convolutional learning system for diabetic retinopathy
neural network with transfer learning and related eye diseases using retinal
from mammography. Medical Physics. images from multiethnic populations
2016;43(12):6654-6666 with diabetes. JAMA. 2017;318(22):
2211-2223
[22] Arevalo J, González FA,
Ramos-Pollán R, Oliveira JL, Lopez MAG. [30] Gulshan V, Peng L, Coram M,
Convolutional neural networks for Stumpe MC, Wu D, Narayanaswamy A,
mammography mass lesion classification. et al. Development and validation of a
In: 2015 37th Annual International deep learning algorithm for detection of
Conference of the IEEE Engineering in diabetic retinopathy in retinal fundus
Medicine and Biology Society (EMBC). photographs. JAMA. 2016;316(22):
IEEE; 2015. pp. 797-800 2402-2410

[23] Lakhani P, Sundaram B. Deep [31] Lee CS, Tyring AJ, Deruyter NP,
learning at chest radiography: Wu Y, Rokem A, Lee AY. Deep-learning
Automated classification of pulmonary based, automated segmentation of
tuberculosis by using convolutional macular edema in optical coherence
neural networks. Radiology. tomography. Biomedical Optics Express.
2017;284(2):574-582 2017;8(7):3440-3448

[24] Wang X, Peng Y, Lu L, Lu Z, [32] Abràmoff MD, Lou Y, Erginay A,

Bagheri M, Summers RM. Chestx-ray8: Clarida W, Amelon R, Folk JC, et al.
Hospital-scale chest x-ray database and Improved automated detection of
benchmarks on weakly-supervised diabetic retinopathy on a publicly
classification and localization of available dataset through integration of
common thorax diseases. In: deep learning. Investigative
Proceedings of the IEEE Conference on Ophthalmology & Visual Science.
Computer Vision and Pattern 2016;57(13):5200-5206
Recognition. 2017. pp. 2097-2106
[33] Gargeya R, Leng T. Automated
[25] Yao L, Poblenz E, Dagunts D, identification of diabetic retinopathy
Covington B, Bernard D, Lyman K. using deep learning. Ophthalmology.
Learning to diagnose from scratch by 2017;124(7):962-969
exploiting dependencies among labels.
arXiv preprint arXiv:1710.10501. 2017 [34] Li Z, He Y, Keel S, Meng W,
Chang RT, He M. Efficacy of a deep
[26] Rajpurkar P, Irvin J, Zhu K, Yang B, learning system for detecting
Mehta H, Duan T, et al. Chexnet: glaucomatous optic neuropathy based
Radiologist-level pneumonia detection on color fundus photographs.
on chest x-rays with deep learning. Ophthalmology. 2018;125(8):
arXiv preprint arXiv:1711.05225. 2017 1199-1206

[27] Hosny A, Parmar C, Quackenbush J, [35] Zheng C, Johnson TV, Garg A,

Schwartz LH, Aerts HJ. Artificial Boland MV. Artificial intelligence in
intelligence in radiology. Nature glaucoma. Current Opinion in
Reviews Cancer. 2018;18(8):500-510 Ophthalmology. 2019;30(2):97-103

8
Artificial Intelligence in Healthcare: An Overview
DOI: http://dx.doi.org/10.5772/intechopen.102768

[36] Burlina PM, Joshi N, Pekala M, Computer-based image analysis for plus
Pacheco KD, Freund DE, Bressler NM. disease diagnosis in retinopathy of
Automated grading of age-related prematurity: Performance of the
macular degeneration from color fundus “i-ROP” system and image features
images using deep convolutional neural associated with expert diagnosis.
networks. JAMA Ophthalmology. Translational Vision Science &
2017;135(11):1170-1176 Technology. 2015;4(6):5-5

[37] Grassmann F, Mengelkamp J, [44] Brown JM, Campbell JP, Beers A,

Brandl C, Harsch S, Zimmermann ME, Chang K, Ostmo S, Chan RP, et al.
Linkohr B, et al. A deep learning Automated diagnosis of plus disease in
algorithm for prediction of age-related retinopathy of prematurity using deep
eye disease study severity scale for convolutional neural networks. JAMA
age-related macular degeneration from Ophthalmology. 2018;136(7):803-810
color fundus photography.
Ophthalmology. 2018;125(9):1410-1420 [45] Hiller SA, Golender VE,
Rosenblit AB, Rastrigin LA, Glaz AB.
[38] Brown JM, Campbell JP, Beers A, Cybernetic methods of drug design. I.
Chang K, Ostmo S, Chan RP, et al. Statement of the problem—The
Automated diagnosis of plus disease in perceptron approach. Computers and
retinopathy of prematurity using deep Biomedical Research. 1973;6(5):411-421
convolutional neural networks.
JAMA Ophthalmology. 2018;136(7): [46] Aoyama T, Suzuki Y, Ichikawa H.
803-810 Neural networks applied to structure-
activity relationships. Journal of
[39] Yau JW, Rogers SL, Kawasaki R, Medicinal Chemistry. 1990;33(3):
Lamoureux EL, Kowalski JW, Bek T, 905-908
et al. Global prevalence and major risk
factors of diabetic retinopathy. Diabetes [47] Duch W, Swaminathan K, Meller J.
Care. 2012;35(3):556-564 Artificial intelligence approaches for
rational drug design and discovery.
[40] Du XL, Li WB, Hu BJ. Application Current Pharmaceutical Design.
of artificial intelligence in 2007;13(14):1497-1508
ophthalmology. International Journal of
Ophthalmology. 2018;11(9):1555 [48] Baskin II, Winkler D, Tetko IV. A
renaissance of neural networks in drug
[41] Kapoor R, Walters SP, Al-Aswad LA. discovery. Expert Opinion on Drug
The current state of artificial Discovery. 2016;11(8):785-795
intelligence in ophthalmology. Survey of
Ophthalmology. 2019;64(2):233-240 [49] Huang Z, Juarez JM, Li X. Data
mining for biomedicine and healthcare.
[42] Treder M, Lauermann JL, Eter N. Journal of Healthcare Engineering.
Automated detection of exudative 2017;2017
age-related macular degeneration in
spectral domain optical coherence [50] Zhang Y, Zhang G, Shang Q.
tomography using deep learning. Computer-aided clinical trial
Graefe’s Archive for Clinical and recruitment based on domain-specific
Experimental Ophthalmology. language translation: A case study of
2018;256(2):259-265 retinopathy of prematurity. Journal of
Healthcare Engineering. 2017;2017
[43] Ataer-Cansizoglu E, Bolon-
Canedo V, Campbell JP, Bozkurt A, [51] Mamoshina P, Vieira A, Putin E,
Erdogmus D, Kalpathy-Cramer J, et al. Zhavoronkov A. Applications of deep

9
Smart Drug Delivery

learning in biomedicine. Molecular

Pharmaceutics. 2016;13(5):1445-1454

[52] Klopman G, Chakravarti SK, Zhu H,

Ivanov JM, Saiakhov RD. ESP: A
method to predict toxicity and
pharmacological properties of chemicals
using multiple MCASE databases.
Journal of Chemical Information and
Computer Sciences. 2004;44(2):704-715

[53] Menden MP, Iorio F, Garnett M,

McDermott U, Benes CH, Ballester PJ,
et al. Machine learning prediction of
cancer cell sensitivity to drugs based on
genomic and chemical properties. PLoS
One. 2013;8(4)

[54] Nascimento AC, Prudêncio RB,

Costa IG. A multiple kernel learning
algorithm for drug-target interaction
prediction. BMC Bioinformatics.
2016;17(1):46

[55] Mohs RC, Greig NH. Drug discovery

and development: Role of basic
biological research. Alzheimer’s &
Dementia: Translational Research &
Clinical Interventions. 2017;3(4):
651-657

[56] Fleming N. How artificial

intelligence is changing drug discovery.
Nature. 2018;557(7706):S55-S55

[57] Mak KK, Pichika MR. Artificial

intelligence in drug development:
Present status and future prospects.
Drug Discovery Today. 2019;24(3):
773-780

10