Journal of Research in Medical and Dental Science

2020, Volume 8, Issue 3, Page No: 137-140

Copyright CC BY-NC 4.0
Available Online at: www.jrmds.in
eISSN No. 2347-2367: pISSN No. 2347-2545

Scope of Artificial Intelligence in Medicine

Atul Dwivedi1, Shweta Shukla Dwivedi2*, Muhammad Raheel Tariq3, Xiaoming Qiu4,
Suzhen Hong1, Yu Xin1
1
Department of Clinical and Basic Sciences, Medical College of Hubei Polytechnic University (HBPU) Huangshi,
Hubei, China
2
Department of Dental Surgery, Jabalpur, Madhya Pradesh, India
3
Department of Internal Medicine, North Sichuan Medical college, Affiliated Hospital of North Sichuan Medical
College, Sichuan, China
4
Department of Radiology, Huangshi Central Hospital, Affiliated Hospital of Hubei Polytechnic University
(HBPU), Edong Health Care Group, Huangshi, Hubei, China

ABSTRACT
Artificial Intelligence concept is becoming popular in search engines, voice recognition software’s, biometric recognition
software’s, automatic vehicles, healthcare electronic device. With the assistance of Artificial Intelligence, clinicians can sort out
the relevant information about the management of a disease in order to take right decisions. Moreover, clinicians could consult
e-books, websites, e-journals for collecting updated information. As technology is evolving day by day, Medical researchers also use
this technology in setting up appropriate modalities and algorithm for several diseases.
Artificial Intelligence methods excel at recognizing tumor’s at stages, complex images, exact pathologies behind several disease
and tumors. AI also reserved its importance in robotics, by which several complicated surgeries can be performed easily. Here, we
also explore the emerging potential of Artificial Intelligence in research, in which, AI can extract the relevant information from
huge data towards taking perfect clinical decision in healthcare system. Artificial Intelligence has got its application in several
branches of medicine. In this review, we tried to establish a general understanding and scope of Artificial Intelligence in medicine.
Key words: Artificial intelligence, Machine learning, Algorithm, Deep learning, Computer aided diagnosis, Automated
computer diagnosis

HOW TO CITE THIS ARTICLE: Atul Dwivedi, Shweta Shukla Dwivedi, Muhammad Raheel Tariq, Xiaoming Qiu, Suzhen Hong, Yu Xin, Scope of
Artificial Intelligence in Medicine, J Res Med Dent Sci, 2020, 8 (3):137-140.

Corresponding author: Shweta Shukla Dwivedi

AI concept has become tremendously popular
e-mail: [email protected] in recent years, as this concept has empowered
Received: 22/04/2020 search engines, automatic vehicles, voice
Accepted: 14/05/2020 recognition software’s etc. have mesmerized our
daily lives. Moreover, AI also gets importance
INTRODUCTION and shows great promise in improvement of
research quality, practice efficacy, personalized
Artificial Intelligence (AI), first proposed by patient management, drug effects etc. [4,5].
Professor John McCarthy in 1955, direct to
Artificial Intelligence has revolutionized the
reproduce human intelligence using computers
medical world and can be commonly regarded
and other electronic devices [1]. The concept
as the component of computer sciences, that's is
of Computer Aided Diagnosis (CAD) was able to handle huge data easily with little theory
introduced in 1980. Its primary intention was to [6]. AI-powered medical technologies enable a 4P
provide second opinion to radiologists [2]. CAD model of medicine, that is predictive, preventive,
is strongly related to Artificial Intelligence (AI). personalized, participatory [7]. Smartphones
CAD and automated computer diagnosis (ACD) are filling the gap and distribute the electronic
are two concepts with different meanings [3]. personal health record [8], helping patients for
137
Journal of Research in Medical and Dental Science | Vol. 8 | Issue 3 | May 2020
Atul Dwivedi et al J Res Med Dent Sci, 2020, 8 (3):137-140

monitoring vital functions with biosensors and lumpectomy by 30% in patients whose breast
to reach optimal therapeutic compliance [9,10]. needle biopsies are considered high risk lesions
AI techniques can help the clinicians to sort out but finally found to be benign after surgical
clinically relevant information from massive excision [22].
amount of data, so that clinicians can take
Recently, Bhandari et al. reported that the
decisions easily and appropriately. Additionally,
progress in cloud computing, big data analytics
AI can assist the researchers to analyses huge
and AI have led to evolution of more intelligent
clinical data within a short time, in order to make
robots and subsequently with the application of
the healthcare facility successful [11-13].
deep learning, several surgical companies are
In other words, Artificial Intelligence also assist collaborating with tech Companies for developing
physicians by giving them updated information intelligent robots. There is huge development in
from journals, websites, e-books about clinical the field of autonomous robotics. However, the
practice. Simultaneously, Artificial Intelligence role of robotics in operation theatre remains
System can minimize the diagnostic and hazy. It is time, when surgeons actively take part
therapeutic errors, which are inevitable to in development of next generation smart and
avoid. With real time reference, as technology intelligent robots [23].
moving ahead, Artificial Intelligence filters key
The primary aim behind the emergence of
information from gigantic population data to
Artificial Intelligence in radiodiagnosis is
make prior health risk alert and therapeutic
because of greater efficacy and efficiency in
outcome predictions [13-17].
clinical outcome & clinical settings. Patrick et al.
CURRENT APPLICATIONS OF ARTIFICIAL INTELLIGENCE also reported that Magnetic Resonance Imaging
(AI) IN MEDICINE (MRI) is an effective modality in the selecting the
patients suitable for arthroscopy from a general
AI is becoming the main constituent of health
population [24]. Google launched its Deep mind
care, including drug discovery, remote patient
Health project, which is used to collect the data
monitoring, medical diagnostics, medical imaging,
of medical records for efficient health services.
virtual assistance, hospital management and risk
In 2016, they also launched a cooperative project
assessment and management. Many branches of
with Moorefield’s Eye Hospital NHS Foundation
medicine dealing with huge data such as analysis
Trust to improve eye treatment [25]. Some other
of DNA and RNA sequencing, imaging data
companies also there, who are using artificial
including radiology, pathology, dermatology and
intelligence to improve health care outcome
ophthalmology, have already benefitted from
mentioned in Table 1.
Artificial Intelligence implementations [18-20].
Pathologists have utilized Artificial Intelligence Study reported that AI and ML can be used in
to decrease their error rate in the recognition the diagnosis of interstitial lung disease and few
of cancer- positive lymph nodes from 3.4% to studies also reported about interpretation of
0.5% [21]. Additionally, Artificial Intelligence images on chest X-ray and diagnosis of bronchial
improved the outcomes in the field of surgery asthma. Despite, ML may be helpful in making
and radio-diagnosis for improved identification clinical decisions, can't replace the expertise
of high risk patients, also reduced the rate of completely [26]. Importantly, Nick identified

Table 1: Shows List of companies using AI to improve outcome in health services.

Name of Company Description
IBM Watson Health Explore data and analytics
Cerner Can discover hidden trends in healthcare data
Health Catalyst Its products can withstand with any IT environment present, and applicable to meet future needs in data analytics
This company process over 40 million claims annually, also providing services to more than 425,000 patients covered under value- based
Health EC
reimbursement models.
Epic It currently has data 0f 190 million patients in order to run health care more efficiently.
The company can proceed through a comprehensive strategy in order to monitor outcomes, reduce cost, and provide better patient
Amitech
experience.
Conifer health Can access clinical and administrative data from several sources, which provides clients simple access To hospital admission data,
solutions predictive analytics, population on risk and referral data.
Prognos uses both diagnostic expertise and AI. This company improves quality and uniformity in data and realise the import EC of clients
Prognos
in health industry.

138
Journal of Research in Medical and Dental Science | Vol. 8 | Issue 3 | May 2020
Atul Dwivedi et al J Res Med Dent Sci, 2020, 8 (3):137-140

16 review studies related with AI applications disease, novel modalities of treatment, where
in acute stroke diagnosis and added that stroke there is no prior information for therapeutics,
onset timing, core and penumbral volume, diagnosis, prognosis and outcomes. Obviously,
clinical examination may be combined for exact in the lack of information, AI may not replace
detection of LVO (Large vessel occlusion) in human knowledge and human brain reasoning
order to enhance the patient selection for a rapid power [44]. Telemedicine filling the gap between
thrombectomy [27]. Multispecialty hospital and Primary health care
units, where Surgeons and super specialist can
Applications of Artificial Intelligence have
give relevant suggestions and diagnosis online,
also shown importance in prediction of
but they can't provide surgical treatment online.
development of Alzheimer's disease from
positron emission tomography [28], detecting CONCLUSION
cancers in mammograms [29], analyzing CT
scans [30,31], identifying brain tumor lesions Artificial Intelligence is expanding its roots in
Magnetic resonance imaging [32], detecting several branches of medicine, such as radiology,
Arrhythmias [33], identification of cancerous pathology, oncology, surgery, etc. As technology
skin lesions [34,35], assessment of embryo evolves, Artificial Intelligence also able to
quality for maximizing the success chances change the decision of Surgeons and Physicians.
of in vitro fertilization [36], interpretation of Additionally, healthcare professional able to
retinal imaging [37], improvement in genomics keep themselves safe in the era of pandemic
expression [38] etc. (COVID -19), with well programmed robots,
which can scan the patient's vital sign without
Commonly, Outcomes of most of the orthopedic
coming into direct contact with them. Last but
surgeries are uncertain, because even after
not the least, huge clinical evaluation is essential
success full surgeries, surgeons can't avoid
for ensuring the efficiency, accuracy and safety
inevitable complications such as malunion,
of Artificial Intelligence.
implant failure, surgical wound infections,
Heterotopic ossification, spinal trauma & REFERENCES
hematoma in Artificial Cervical Disc Replacement
(ACDR), etc. Another study concluded that in 1. Deo RC. Machine learning in medicine. Circulation 2015;
132:1920-1930.
case of pilon fracture management, no single
method or approach can be regarded as ideal for 2. Huang HK. Medical imaging, PACS, and imaging
the treatment of pilon fracture, even surgeon's informatics: Retrospective. Radiological Phy Technol
2014; 7:5-24.
skills and choice also matter a lot in the outcome
of surgery. Therefore, we need to implement 3. Mokli Y, Pfaff J, dos Santos DP, et al. Computer-aided
imaging analysis in acute ischemic stroke-background
stem cell regenerative medicine (SCRM) in
and clinical applications. Neurol Res Practice 2019; 1:2.
place of surgeries. We can regenerate several
damaged tissues, tendons, cartilages, muscles, 4. Panchmatia JR, Visenio MR, Panch T. The role of artificial
intelligence in orthopaedics surgery. Br J Hosp Med
etc. [39-42]. In this scenario, AI techniques could
2018; 79:676-681.
be used for optimization of stem cell therapy and
gene therapy in Pediatric patients by predicting 5. Track C. Artificial intelligence and machine learning:
Applications in musculoskeletal physiotherapy.
clinical outcomes, simplifying cost and treatment Musculoskelet Sci Pract 2019; 39:164-169.
[43]. In near future, hopefully researchers can
6. Peng Y, Zhang Y, Wang L. Artificial intelligence in
implement the same in all branches of medicine.
biomedical engineering and informatics: an introduction
Limitation of artificial intelligence and review. Artif Intell Med 2010; 48:71-73.

Artificial Intelligence also has its own limitations, 7. Orth M, Averine M, Chatzipanagiotou S, etal. Opinion:
Redefining the role of the physician in laboratory
as forecasting and predictions about outcomes of
medicine in the context of emerging technology,
therapeutics may be wrong in novel cases of viral personalised medicine and patient autonomy ('4P
infections ( e.g. Novel corona virus infection or medicine'). J Clin Pathol 2019; 72:191-197.
COVID -19, recently we have limited information
8. Abdulnabi M, Al- Haiqi A, Kiah MLM, et al. A distributed
about behavior of this virus and definitive framework for health information exchange using
treatment modalities ), novel side effects or smartphone technologies. J Biomed informat 2017;
resistant cases, newly reported side effects, rare 69:230-250.

139
Journal of Research in Medical and Dental Science | Vol. 8 | Issue 3 | May 2020
Atul Dwivedi et al J Res Med Dent Sci, 2020, 8 (3):137-140

9. Topol EJ. A decade of digital medicine innovation. Sci 28. Ding Y, Sohn JH, Kawczynski MG, et al. A deep learning
Trans Med 2019; 11:7610. model to predict a diagnosis of alzheimer disease
by using 18F-FDG PET of the Brain. Radiology 2019;
10. Morawski K, Ghazinouri R, Krumme A, et al. Association of 290:456-464.
a smartphone application with medication adherence and
blood pressure control: The MedISAFE-BP Randomized 29. https://arxiv.org/abs/1703.07047
clinical trial. JAMA Int Med 2018; 178:802-809. 30. Hua KL, Hsu CH, Hidayati SC, et al. Computer aided
11. Murdoch TB, Detsky AS. The inevitable application of classification of lung nodules on computed tomography
big data to health care. JAMA 2013; 309:1351-1352. images via deep learning technique. Onco Targets Ther
2015; 8:2015-2022.
12. Kolker E, Özdemir V, Kolker E. How Healthcare can refocus
on its super customers (Patient, n=1) and customers 31. https://ieeexplore.ieee.org/document/8363515
(Doctors and Nurses) by leveraging lessons from amazon, 32. Kamnitsas K, Ferrante E, Parisot S, et al. Deep medic for
uber, and Watson. OMICS 2016; 20:329-33. brain tumor segmentation In: international workshop
13. Dilsizian SE, Siegel EL. Artificial intelligence in medicine on brainlesion: Glioma, Mutiple sclerosis, stroke, and
and cardiac imaging: Harnessing big data and advanced traumatic brain injuries 2016; 138-149.
computing to provide personalised medical diagnosis 33. Hannun AY, Rajpurkar P, Haghpanahi M, et al.
and treatment. Curr Cardiol Resp 2014; 16:441. Cardiologist: Level arrhythmia detection and
14. Neil DB. Using artificial intelligence to improve hospital classification in ambulatory electrocardiograph using a
inpatient care. Intell Syst 2013; 28:92-95. deep neural network. Nat Med 2019; 25:65-69.

15. Patel VL, Shortliffe EH, Stefanelli M, et al. The coming of 34. Han SS, Kim MS, Lim W, et al. Classification of the clinical
images for benign and malignant cutaneous tumors
age of artificial intelligence in medicine. Artif Intell Med
using a deep learning algorithm. J Invest Dermatol
2009; 46:5-17.
2018; 138:1529-1538.
16. https://www.ibm.com/developerworks/community/
35. Brinker TJ, Hekler A, Enk AH, et al. Deep learning
blogs/InsideSystemStorage/entry/ibm_watson_
outperformed 136 of 157 dermatologists in a head-to-
how_to_build_your_own_watson_jr_in_your_
head dermoscopic melanoma image classification task.
basement7?lang=en
Eur J Cancer 2019; 113:47-54.
17. Lee CS, Nagy PG, Weaver SJ, et al. Cognitive and system
36. Khosravi P, Kazemi E, Zhan Q, et al. Deep learning enables
factors contributing to diagnostic errors in radiology. robust assessment and selection of human blastocysts
Am J Roentgenology 2013; 201:611-617. after in vitro fertilisation. Digit Med 2019; 2:21.
18. Gulshan V, Peng L, Coram M, et al. Development and 37. De Fauw J, Ledsam JR, Romera-Paredes B, et al. Clinically
validation of a deep learning algorithm for detection applicable deep learning for diagnosis and referral in
of diabetic retinopathy in retinal fund us photographs. retinal disease. Nat Med 2018; 24:1342-1350.
JAMA 2016; 316: 2402-2410.
38. Xu J, Yang P, Xue S, et al. Translating cancer genomics
19. Rusk N. Deep learning. Nature Methods 2015; 13:35. in to precision medicine with artificial intelligence:
20. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist: Level Applications, challenges and future perspective. Hum
classification of skin cancer with deep neural networks. Genet 2019; 138:109-124.
Nature 2017; 542:115-118. 39. Dwivedi A, Dwivedi SS, Su Zhenhong, et al. Open
21. https://arxiv.org/abs/1606.05718 reduction and Internal Fixation of posterior pilon variant
fractures with buttress plate through posterolateral
22. Bahl M, Barzilay R, Yedida AB, et al. High-risk breast approach. IJCMR 2019; 5:1-5.
lesions: A machine learning model to predict pathologic
upgrade and reduce unnecessary surgical excision. 40. Dwivedi A, Dwivedi SS, Tariq MR, et al. Stem cell
Radiology 2018; 286:810-818. regenerative medicine (SCRM)-A new hope in
orthopedics-Review article. J Stem Cell Biol Transplant
23. Bhandari M, Zeffiro T, Reddiboina M. Artificial 2019; 3:1-4.
intelligence and robotics surgery: Current perspective
and future directions. Curr Opin Urol 2020; 30:48-54. 41. Dwivedi A, Jian WX, Dwivedi SS, et al. Pilon fracture: An
unsolved riddle: An updates review. IJCMR 2017; 4:718-
24. Vincken PW, Braak BP, van Erkell AR, et al. Effectiveness 725.
of MR imaging in selection of patients for arthroscopy of
the knee. Radiology 2002; 223:739-746. 42. Dwivedi A, Jian WX, Dwivedi SS. Artificial cervical disc
replacement: A double edged sword-A clinical review.
25. https://www.moorfields.nhs.uk/news/moorfields- IJCMR 2017; 4:1163-1168.
announces-research-partnership
43. Sniecinski I, Seghatchian J. Artificial intelligence: A
26. Mekov E, Miravitlles M, Petkov R. Artificial intelligence joint narrative on potential use in Pediatric stem and
and machine learning in respiratory medicine: Expert immune cell therapies and regenerative medicine.
Rev Respir Med 2020; 17:1-6. Transfus Apher Sci 2018; 57:422-424.
27. Murray N. Artificial intelligence in acute stroke 44. Mesko B. The role artificial intelligence in precision
diagnostics: Application in large vessel occlusions. medicine. Expert Review Precision Med Drug Develop
Neurology 2019; 92:6. 2017; 2:239-241.

140
Journal of Research in Medical and Dental Science | Vol. 8 | Issue 3 | May 2020