See discussions, stats, and author profiles for this publication at: [Link]

net/publication/362275639

Artificial Intelligence (AI) in Pharmacy: An Overview of Innovations

Article in INNOVATIONS in pharmacy · July 2022

DOI: 10.24926/iip.v13i2.4839

CITATIONS READS
140 6,397

7 authors, including:

Muhammad Ahmer Raza Shireen Aziz

17 PUBLICATIONS 234 CITATIONS 15 PUBLICATIONS 230 CITATIONS

SEE PROFILE SEE PROFILE

Misbah Noreen Amna Saeed

National University of Sciences and Technology Xi'an Jiaotong University
13 PUBLICATIONS 203 CITATIONS 37 PUBLICATIONS 911 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Amna Saeed on 19 May 2023.

The user has requested enhancement of the downloaded file.

Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

Artificial Intelligence (AI) in Pharmacy: An Overview of Innovations

Muhammad Ahmer Raza1,2; Shireen Aziz3,4; Misbah Noreen2,5; Amna Saeed6,7; Irfan Anjum8,9; Mudassar Ahmed2,5;
Shahid Masood Raza2,4,10
1
Department of Pharmacy Practice, The University of Lahore, Punjab, Pakistan
2
Faculty of Pharmacy, The University of Faisalabad, Punjab, Pakistan
3
School of Pharmacy, Zhengzhou University, Henan, China
4
Faculty of Pharmacy, University of Sargodha, Punjab, Pakistan
5
School of Pharmacy, University of Agriculture, Faisalabad, Punjab, Pakistan
6
Department of Pharmacy Administration and Clinical Pharmacy, School of Pharmacy, Xi’an Jiaotong University, Xi’an, China
7
Center for Drug Safety and Policy Research, Xi’an Jiaotong University, Xi’an, China
8
Faculty of Pharmacy, The University of Lahore, Pakistan
9
Faculty of Pharmacy, Hacettepe University, Ankara, Turkey
10
School of Pharmacy, Tongji Medical College, Huazhong University of Science and Technology, Hubei, China

Abstract
Artificial Intelligence (AI) emerged as an intervention for data and number-related problems. This breakthrough has led to several
technological advancements in virtually all fields from engineering to architecture, education, accounting, business, health, and so on.
AI has come a long way in healthcare, having played significant roles in data and information storage and management – such as
patient medical histories, medicine stocks, sale records, and so on; automated machines; software and computer applications like
diagnostic tools such as MRI radiation technology, CT diagnosis and many more have all been created to aid and simplify healthcare
measures. Inarguably, AI has revolutionized healthcare to be more effective and efficient and the pharmacy sector is not left out. During
the past few years, a considerable amount of increasing interest in the uses of AI technology has been identified for analyzing as well
as interpreting some important fields of pharmacy like drug discovery, dosage form designing, polypharmacology, and hospital
pharmacy. Given the growing importance of AI, we wanted to create a comprehensive report which helps every practicing pharmacist
understand the biggest breakthroughs which are assisted by the deployment of this field.

Keywords: Artificial intelligence, pharmacy, pharmacist

Introduction growing operating costs, and lower reimbursements. Pharmacy

AI is a stream of science related to intelligent machine learning, has also done a great job of leveraging enabling technology
mainly intelligent computer programs, which provides results in automation to improve workflow efficiency and lower
a similar way to the human attention process[1]. This process operating costs while promoting safety, accuracy, and
generally comprises obtaining data, developing efficient efficiency in every pharmacy setting. Automated dispensing
systems for the uses of obtained data, illustrating definite or gives pharmacists more time to engage with a greater volume
approximate conclusions, self-corrections, and adjustments[2]. of patients while also enhancing their health outcomes[4].
In general, AI is used for analyzing machine learning to imitate
the cognitive tasks of individuals[2, 3]. AI technology is exercised The first application of a computer in a pharmacy presumably
to perform more accurate analyses as well as to attain useful dates back to the 1980s and since then, computers have been
interpretation[3]. In this perspective, various useful statistical utilized in everything from data collection, retail pharmacy
models, as well as computational intelligence, are combined in management, clinical research, drug storage, pharmacy
AI technology. education, clinical pharmacy, and lots more, and with the
emergence of artificial intelligence, there is no telling just how
Recently, AI technology becomes a very fundamental part of much the Pharmacy sector will evolve in the long run. There
the industry for useful applications in many technical and have been several expert systems developed in medicine to
research fields. Reflecting on the past 25 years, pharmacy has assist physicians with medical diagnosis[5]. Recently, several
done a great job of addressing the growing demand for programs focusing on drug therapy have been described[6].
prescriptions, even when faced with pharmacist shortages, They guide drug interactions, drug therapy monitoring, and
drug formulary selection. There are many aspects of pharmacy
that AI can have an impact on and the pharmacists to consider
Corresponding author: Shahid Masood Raza these possibilities because they may someday become a reality
School of Pharmacy, Tongji Medical College, Huazhong in pharmacy practice.
University of Science and Technology, Hubei, China
Email: shahipharmacist@[Link]

[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 1

DOI: [Link]
Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

The purpose of this article was to review topics related to AI. Machine perception is another aspect of AI and it involves
The topics include AI general overview and classification, AI designing and building machines with the ability to use sensory
uses in hospitals, the pharmaceutical industry, and retail inputs to deduce information about the different aspects of the
pharmacies and to create awareness for AI as a component of world. Computer vision is the ability of machines to process
pharmacy practice in the future, to encourage pharmacists to visual inputs such as facial information, objects, and
embrace this advancement, and as much as possible put in the gestures[14].
effort to acquire the relevant skills, which will enable
pharmacists to contribute towards the much-envisaged There have been various skepticism, criticism, and myths
development. towards AI mostly concerning safety and the dangers that may
be potentiated by the creation of machines that could match
AI general overview human cognitive capabilities. One of the five predictions made
The term AI (also known as machine intelligence) is very by Forbes for AI in 2019[15] is that it may become an issue of
commonly confused and used interchangeably with robotics national politics. Aside from concerns that AIs may be used as
and automation. While robotics is simply the creation of weapons for war and mass destruction, certain people have
machines that can carry out difficult repetitive tasks, AI refers expressed concerns that the creation of AI systems that are
to the exhibition of human-like behaviors or intelligence by any smarter than humans, through general AI could be more fatal
computer or machine[7]. Traditionally, robots were not built to and be the end of the human race itself. They believe we may
possess these “intelligent capabilities” even though they may not be able to predict how AI systems that are more intelligent
be able to move or carry objects independently using a than us will behave and that humans may end up being
designed program and surface sensors in a process known as controlled by these super-intelligent machines. Scientists
automation. AI, in essence, is the field of computer science that believe most of the safety concerns about future super-
specializes in the creation of intelligent machines, developed intelligent AI systems may be resolved if the “goals” of these
with the ability to perform tasks that will ordinarily be machines can be made to align with our own goals[15].
associated with a human being[8].
AI classification
AI is frequently applied to the development of digital computers AI can be classified in two different ways [16, 17]
or computer-controlled robots with the capacity to
autonomously execute intellectual and cognitive human-like a) according to caliber
processes. Such intellectual and cognitive processes include b) according to the presence (See table 1)
learning, reasoning, problem-solving, perception, and language.
The form of AI currently in use today is referred to as narrow AI Table 1: Classification of AI
or weak AI because it is only designed to perform narrow tasks Weak intelligence
like internet search, facial and voice recognition, controlling and Based on the caliber Artificial narrow intelligence
driving cars, and so on. However, the long-term goal of the AI Artificial general intelligence
community is to have machines that can autonomously Artificial super intelligence
outperform humans’ at all cognitive tasks. The AI that involves Type 1 reactive machine
creating machines that can perform all human cognitive tasks Based on presence Type 2 limited memory system
will be the general AI or Strong AI (ADI)[9]. Type 3 is based on the theory of mind
Type 4 self-awareness
In simple terms, AI refers to the ability of machines and
computers to think, act, behave and function as human beings. Based on their caliber, AI system is classified as follows:
Familiar examples of AI-controlled systems include Apple’s SIRI
(in iPhone)[10], Amazon’s Alexa[11], and the self-driving cars of 1. Weak intelligence or Artificial narrow intelligence (ANI):
Google, Mercedes, BMW, and Tesla to name a few[12]. The core This system is designed and trained to perform a narrow task,
of AI can be Knowledge Engineering, in which machines are such as facial recognition, driving a car, playing chess, and
assembled with access to abundant data and information traffic signaling. E.g.: Apple SIRI virtual personal assistance,
relating to the human world, which enables them to be able to tagging in social media.
mimic human behavior. Machine Learning is another type of AI,
which involves the use of algorithms and statistical models to 2. Artificial General Intelligence (AGI) or Strong AI: It is also
improve the accuracy of software applications in predicting called Human-Level AI. It can simplify human intellectual
outcomes without being distinctly programmed. It was abilities. Due to this, when it is exposed to an unfamiliar task, it
established based on the idea that machines can learn from can find the solution. AGI can perform all the things as humans.
data, identify problems and make decisions with minimum
human help or intervention. Applications of machine learning 3. Artificial Super Intelligence (ASI): It is brainpower, which is
include self-driven Google cars, fraud detection, and online more active than smart humans in drawing, mathematics,
recommendation offers like those on Amazon and Netflix[13]. space, etc; in every field from science to art. It ranges from the

[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 2

DOI: [Link]
Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

computer just little than the human to a trillion times smarter cases and insights gleaned from working thousands of
than humans. hours with Memorial Sloan Kettering Cancer Center
physicians and provides treatment options to help
Arend Hintze[18], an AI scientist classified the AI technology oncology clinicians make informed decisions. These
based on its presence and not yet present. They are as follows: treatment options are supported by literature curated by
Memorial Sloan Kettering, and over 300 medical journals
Type 1: This type of AI system is called a Reactive machine. E.g. and 200 textbooks, resulting in almost 15 million pages
Deep Blue, the IBM chess program which hit the chess of text [22].
champion, Garry Kasparov, in the 1990s. It can identify checkers • Assisting in repetitive tasks: AI technology also assists in
on the chessboard and can make predictions; it does not have some repetitive tasks, such as examining the X-ray
the memory to use past experiences. It was designed for imaging, radiology, ECHO, ECG, etc., for the detection
narrow purposes use and is not useful in other situations.
and identification of diseases or disorders. Medical
Another example is Google's AlphaGo. Sieve[23] (an algorithm launched by IBM) is a “cognitive
Type 2: This type of AI system is called a Limited memory assistant” having good analytical and reasoning abilities.
system. This system can use past experiences for present and
A medical start-up is necessary for the improvement of
future problems. In autonomous vehicles, some of the decision- the patient's condition by combining deep learning with
making functions are designed by this method only. The medical data. A specialized computer program is
recorded observations are used to record the actions available for each body part and used in specific disease
happening in the future, such as changing the lanes by car. The
conditions. Deep learning can be employed for almost all
observations are not in the memory permanently. types of imaging analyses, such as X-ray, CT scan, ECHO,
Type 3: This type of AI system is called as “theory of mind”. It ECG, etc.
means that all humans have their thinking, intentions, and
• Health support and medication assistance: In recent
desires which impact the decisions they make. This is a non-
years, the uses of AI technology are recognized as
exist AI.
efficient in health support services and also, for
Type 4: These are called self-awareness. The AI systems have a
medication assistance. Molly[24] (a start-up-designed
sense of self and consciousness. If the machine has self-
virtual nurse) receives a pleasant voice along with a
awareness, it understands the condition and uses the ideas
cordial face. Its aim of it is for helping patients to guide
present in others' brains. This is a non-existing AI.
the treatment of patients as well as support them with
their chronic conditions during doctor’s visits. Ai Cure[25]
Applications of AI
is an app existing in a Smartphone webcam, which
AI in diagnosis and targeted genomic treatments monitors patients and assists them to control their
There are several applications of AI in hospital-based health conditions. This app is useful to patients with severe
care systems[19, 20] in organizing dosage forms for individualized medication situations and for patients who participate in
patients and selecting suitable or available administration clinical trials.
routes or treatment policies. • Accuracy of medicine: AI shows a good impact on
genomics and genetic development. Deep Genomics[26],
• Maintaining of medical records: Maintenance of the an AI system is useful for observing patterns in the
medical records of patients is a complicated task. The genetic information and medical records to identify the
collection, storage normalizing, and tracing of data are mutations and linkages to diseases. This system informs
made easy by implementing the AI system. Google Deep doctors about the events happening within a cell when
Mind health project[21] (developed by Google) assists to DNA is altered by genetic variation. An algorithm is
excavate the medical records in a short period. Hence, designed by the father of the human genome project,
this project is a useful one for better and faster health Craig Venter[27] that gives information on patients’
care. The Moor fields Eye hospital NHS is assisted by this physical characteristics based on their DNA. “Human
project for the improvement of eye treatment. Longevity” AI technology is useful to identify the exact
• Treatment plan designing: The designing of effective location of cancer and vascular diseases in their early
treatment plans is possible with the help of AI stage.
technology. When any critical condition of a patient • Drug creation: The development or creation of
arises and the selection of a suitable treatment plan pharmaceuticals takes more than a decade and
becomes difficult, then the AI system is necessary to consumes billions of rupees. “Atomwise”[28], an AI
control the situation. All the previous data and reports, technology that uses supercomputers, is useful to find
clinical expertise, etc., are considered in the designing of out the therapies from the database of molecular
the treatment plan as suggested by this technology. IBM structure. It hurled a virtual search program for safe and
Watson for Oncology[22], the software as a service, is a effective therapy for the Ebola virus with the existing
cognitive computing decision support system that drugs. The technology identified two drugs that caused
analyzes patient data against thousands of historical Ebola infection. This analysis was completed within one

[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 3

DOI: [Link]
Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

day compared to months to years with manual analysis. Research works are carried out daily to find new active
A Biopharma company in Boston developed big data for principles for the currently incurable diseases and conditions;
the management of patients. It reserves data to find the increase the safety profile of already existing drugs; combat
reasons why some patients survive diseases. They used drug resistance and minimize therapeutic failure. Hence, there
patients’ biological data and AI technology to find out the is an increase in the size and variety of biomedical data sets
difference between healthy and disease-friendly involved in drug design and discovery. This factor and many
atmospheric conditions. It helps in the discovery and more contributed to the advancement of AI in the
design of drugs, healthcare, and problem-solving pharmaceutical industry. Today, some companies offer
applications. software with much relevance in drug design and data
• AI helps people in the health care system: The “open processing, as well as in predicting treatment outcomes.
AI ecosystem”[29] was one of the top 10 promising
technologies in 2016. It is useful to collect and compare GNS healthcare[39] uses AI machine software known as Reverse
the data from social awareness algorithms. In the Engineering and Forward Simulation (REFS). REFS determines
healthcare system, vast information is recorded which the cause and effect relationships between various types of
includes patient medical history and treatment data data, that are unforeseen ordinarily by direct data evaluation.
from childhood to that age. This enormous data can be GNS claims that REFS can transfer millions of data points
analyzed by the ecosystems and gives suggestions about ranging from clinical to genetics, laboratory, imaging, drug,
the lifestyle and habits of the patient. consumer, geographic, pharmacy, mobile, proteomic, and so
• Healthcare system analysis: In the healthcare system, on. In drug design, a company known as Atomwise developed
if all the data is computerized then retrieval of data is the first deep learning neural network for structure-based drug
easy. Netherland maintains 97% of invoices in digital design and discovery that they called AtomNet[40]. AtomNet
format[30], which contain treatment data, physician makes use of a statistical approach to extract information from
names, and hospital names. Hence, these can be millions of experimental affinity measurements and thousands
retrieved easily. Zorgprisma Publiek, a local company of protein structures to predict the binding properties of small
analyses the invoices with the help of IBM Watson cloud molecules with proteins. By presenting 3-dimensional images
technology. If any mishap occurs, it recognizes it of the protein and ligand pair showing channels for carbon,
immediately and takes the correct action. Because of oxygen, nitrogen, and other types of atoms, AtomNet
this, it improves and avoids patient hospitalization. technology enables the pharmaceutical chemists to perform
core processes of drug discovery and design like hit discovery,
AI and development of pharmaceuticals [31-37] lead optimization, and prediction of toxicity with high precision
Top pharmaceutical companies are collaborating with AI and accuracy in weeks as against years.
vendors and leveraging AI technology in their manufacturing
processes for research and development and overall drug Insilico Medicine[41, 42] announced an AI project by the company
discovery. Reports show nearly 62 percent of healthcare called Pharm AI. Insilico Medicine claims they applied
organizations are thinking of investing in AI shortly, and 72 Generative Adversarial Networks (GAN) and reinforcement
percent of companies believe AI will be crucial to how they do learning algorithms. The GAN is a type of generative model that
business in the future. To get a better sense of the future of can generate samples and also learn from training samples.
AI in the sector, Pharma News Intelligence[38] dives into current They are made up of two neural networks, the generator, and
AI use cases, the best uses for the technology, and the future the discriminator. The relationship between the generator and
of AI and machine learning. The McKinsey Global Institute the discriminator is referred to as “adversarial”. The generator
estimates that AI and machine learning in the pharmaceutical tries to create and learns to create new samples and sends
industry could generate nearly $100B annually across the US them to the discriminator, which classifies the sample as real or
healthcare system. According to researchers, the use of these fake where real denotes the examples that belong to the data
technologies improves decision-making, optimizes innovation, set, and the examples generated by the generator are denoted
improves the efficiency of research/clinical trials, and creates “fake”. Through continuous training, the generator begins to
beneficial new tools for physicians, consumers, insurers, and create samples that are similar to the real ones while the
regulators. Top pharmaceutical companies, including Roche, discriminator gets better at the identification process. With
Pfizer, Merck, AstraZeneca, GSK, Sanofi, AbbVie, Bristol-Myers Pharm AI, through GAN and reinforcement learning, Insilico
Squibb, and Johnson & Johnson have already collaborated with Medicine claims that it can generate new molecular structures
or acquired AI technologies. In 2018, the Massachusetts and ideate the biological origin of a disease.
Institute of Technology (MIT) partnered with Novartis and
Pfizer to transform the process of drug design and AI in pharmacy practice in hospital and community
manufacturing with its Machine Learning for Pharmaceutical pharmacies
Discovery and Synthesis Consortium[38]. Machine learning models allow e-mails to be personalized at a
speed and accuracy greater than that of any human being.
Chatbots[43] can be used to increase the efficiency of service
[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 4
DOI: [Link]
Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

delivery. Chatbots are capable of mimicking interactions Discussion

between customers and customer care of sale staffs. Chatbots The primary aim of health-related AI applications is to analyze
are capable of automatically resolving customer complaints and relationships between prevention or treatment techniques and
queries and the difficult questions are transferred to human patient outcomes. AI programs have been developed and
staff. In retail pharmacy, this principle can be applied. The applied to practices such as diagnosis processes, treatment
chatbots can be programmed to mimic pharmacist-patient protocol development[47], drug development[1], personalized
interaction. medicine[48], and patient monitoring and care[49], among others.
As the quality of care offered for patients continues to grow in
Walgreen[44] made a partnership with Medline, a telehealth prominence, here are some ways pharmacies can leverage the
firm to create an avenue to help patients interact with continued technology explosion to impact value-based
healthcare professionals through video chat. AI can also be outcomes. As the most accessible and affordable healthcare
useful in inventory management. As a retail pharmacist, stakeholder, pharmacies can become health management
imagine being able to predict what your patients will need in centers instead of only medication fulfillment locations.
the nearest future, stocking them, and using personalized Technology can help provide more personalized healthcare
software to deliver e-mails to remind the patient of drug needs. offerings including advice, guidance, and an expanded suite of
With the use of AI-powered data analytics, a patient’s future services (e.g., immunizations, screenings, MTM, disease state
drug purchase can be predicted. Predicting the patient’s drug management). Health trackers and wearable will be able to
purchase through AI will help the pharmacist to make proper provide real-time capture of data that can enable pharmacy to
stock procurement decisions. follow up with at-risk patients on their conditions and monitor
their quality of improvement[50].
Although, there are existing inventory management software
and application that are used in retail pharmacy stock AI can be of real help in analyzing data and presenting results
management like Mckessons; Liberty; Winpharm; PrimeRx; and that would support decision making, saving human effort, time,
WinRx, not all of them utilize AI or machine learning. For and money, and thus helps save lives. Medical and
example, an AI company, Blue Yonder developed software for technological advancements that have helped the healthcare-
Otto group[45], a German online and catalog retailer. This related development of AI include the overall evolution of
software can predict with 90% accuracy what will be sold by computers, resulting in faster data collection and more
Otto in 30 days. This reduced the delivery schedule for powerful data processing, Growth in the availability of health-
purchased products from one week or more to one of two days related data from personal and healthcare-related devices and
by enabling direct delivery of the product from the supplier to records, and the development of pharmacogenomics and gene
the consumer without having to pass through the warehouse. databases, Expansion and industry adoption of electronic
health records and natural language processing and other
Intending to improve the safety of patients, the University of advancements in computing that have enabled machines to
California San Francisco (UCSF) Medical Center uses robotic replicate human certain processes[51].
technology for the preparation and tracking of medications.
According to them, the technology has prepared 3, 50, 000 In the physician space, AI from technology companies like
medication doses without any error. The robot has proved to Microsoft is breaking into the healthcare industry by assisting
be far better than humans both in size as well as its ability to doctors in finding the right treatments among the many options
deliver accurate medications. The abilities of the robotic for cancer. Capturing data from various databases relating to
technology include the preparation of oral as well as injectable the condition, AI is helping physicians identify and choose the
medicines which include toxic chemotherapy drugs. This has right drugs for the right patients[52, 53]. In the pharma space, AI
given the freedom to the pharmacists and nurses of UCSF so is working with researchers to support the decision-making
that they can utilize their expertise by focusing on direct patient processes for existing drugs and expanded treatments for other
care and working with the physicians. Within the automated conditions, as well as expediting the clinical trials process by
system of the pharmacy, the computers first receive medication finding the right patients from several data sources [1, 54, 55].
orders electronically from the physicians and pharmacists of Pharma is even working to predict with certain accuracy when
UCSF. After this, individual doses of pills are picked, packaged, and where epidemic outbreaks might occur, using AI learning
and dispensed by the robotics. This is followed by machines based on a history of previous outbreaks and other media
assembling the doses onto a bar-coded plastic ring. The thin sources.
plastic ring contains all medications that have to take by a
patient within a period of 12h. Adding to the capabilities of the In the hospital space, AI is being used to prevent medical errors
automated system is their ability to prepare sterile and reduce hospital readmissions. By analyzing patient data
preparations that are meant for chemotherapy along with from medical and medication errors, readmission root causes,
filling intravascular syringes with the right medications[46]. and other internal and external databases, AI will one day
identify and prevent high-risk patients from developing
complications, and provide prospective care guidance, and
diagnostic support, among many other clinical applications.
[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 5
DOI: [Link]
Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

Additionally, AI will be useful in workflow optimization and The opinions expressed in this paper are those of the authors.
efficiency, helping eliminate redundancy in cost from duplicate
or unnecessary procedures[56, 57]. Ethics approval and consent to participate: Not applicable.

In pharmacy today, we already have an early form of AI in place. Consent for publication: All authors approved the manuscript.
It’s called our pharmacy management system, housing patient Availability of data and materials: Not applicable
utilization, and drug data, as well as potentially identifying
drug-related problems through clinical decision support Competing interests: All authors declare no competing
screening. The next generation in pharmacy technology is the interests
introduction of a technology-based information expert system
to identify timely drug-related problems based on patient data Funding: None
captured from the pharmacy system and other external data Author contributions: All authors listed have made a
systems. Consistent with workflow robotics, this would leave substantial and intellectual contribution to the work and
less of the work on the pharmacist to shoulder the approved it for publication.
responsibility of identifying serious drug-related problems[58, 59].
Authors’ information:
Implications for pharmacists and their practice Muhammad Ahmer Raza, PharmD (The University of
AI can strongly influence and shift pharmacists’ focus from the Faisalabad, Pakistan), MS Clinical Pharmacy (Shandong
dispensing of medications toward providing a broader range of University, Jinan, China) is a registered pharmacist (RPh) in
patient-care services. The pharmacist can leverage AI to help Pakistan and an academic pharmacist and pharmacy practice
people get the most from their medicines and keep them researcher. Shireen Aziz, PharmD (Pakistan) MS (Zhengzhou
healthier. Most importantly, AI provides pharmacy an University, China), is a registered pharmacist (RPh) in Pakistan
opportunity for more collaboration across many different and completed her MS in Pharmacology from Zhengzhou
entities serving the same patient. For the patient, in addition to University, China. Misbah Noreen, PharmD, MPhil (Pakistan) is
potentially better healthcare services offered by their a community pharmacist in the chain pharmacy setup of
professionals, AI may be a useful tool for providing guidance on Pakistan (Care Pharmacy). Irfan Anjum, PharmD (Pakistan), MS,
how and where to obtain the most cost-effective healthcare PhD (Turkey) is an Assistant Professor at The University of
and how best to communicate with healthcare professionals; Lahore (UOL) Pakistan. Shahid Masood Raza, BPharm (Hons),
optimizing the value of data from wearable; providing everyday [Link] is a lecturer at The University of Faisalabad, Pakistan.
lifestyle guidance; integrating diet and exercise; and supporting He is currently pursuing a PhD from Huazhong University of
treatment compliance and adherence. Science and Technology, Wuhan, Hubei, China. Both are
experienced in qualitative and quantitative research methods
Concluding comments
and content analysis.
AI involves the combination of human knowledge and
resources with Artificial Intelligence. As research into AI
List of abbreviations:
continues, with many interesting applications of it in progress,
MRI Magnetic resonance imaging
one may consider it a necessary evil even for those that see it
CT Computerized tomography
as an enemy. Therefore, it is strongly recommended that
ECHO Echocardiogram
pharmacists should acquire the relevant hard skills that
ECG Electrocardiogram
promote AI augmentation. Education about and exposure to AI
DNA Deoxyribonucleic acid
is necessary throughout all domains of pharmacy practice.
NHS National health services
Pharmacy students should be introduced to the essentials of
GSK GlaxoSmithKline
data science and fundamentals of AI through a health
GNS Gene network sciences
informatics curriculum during their PharmD education.
MTM Medication therapy management
Pharmacists must also be allowed to develop an understanding
of AI through continuing education. Data science courses or
pharmacy residencies with a focus on AI topics should be made
available for pharmacists seeking more hands-on involvement
in AI development, governance, and use. As these technologies
rapidly evolve, the pharmacy education system must remain
agile to ensure our profession is equipped to steward these
transformations of care.

[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 6

DOI: [Link]
Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

References 20. Manikiran, S. and N. Prasanthi, Artificial Intelligence:

1. Mak, K.-K. and M.R. Pichika, Artificial intelligence in drug Milestones and Role in Pharma and Healthcare Sector.
development: present status and future prospects. Drug Pharma times, 2019. 51: p. 9-56.
discovery today, 2019. 24(3): p. 773-780. 21. Deep Mind’s health team. [cited 2022 13 June]; Available
2. Das, S., R. Dey, and A.K. Nayak, Artificial Intelligence in from: [Link]
Pharmacy. INDIAN JOURNAL OF PHARMACEUTICAL team-joins-google-health.
EDUCATION AND RESEARCH, 2021. 55(2): p. 304-318. 22. IBM Watson for Oncology.; Available from:
3. Russell, S., D. Dewey, and M. Tegmark, Research priorities [Link]
for robust and beneficial artificial intelligence: an open bin/ssialias?appname=skmwww&htmlfid=897%2FENUS572
letter. AI Magazine, 2015. 36(4). 5-
4. Dasta, J., Application of artificial intelligence to pharmacy W51&infotype=DD&subtype=SM&mhsrc=ibmsearch_a&mh
and medicine. Hospital pharmacy, 1992. 27(4): p. 312-5, q=IBM%20WATSON%20ONcology#:~:text=IBM%20Watson
319. %20for%20Oncology%2C%20software,Center%20physician
5. Deopujari, S., et al., Algoman: Gearing up for the “Net s%20and%20other%20analysts.
Generation” and Era of Artificial Intelligence, One Step at a 23. IBM. Medical Sieve. . [cited 2022 13 June]; Available from:
Time. The Indian Journal of Pediatrics, 2019. 86(12): p. [Link]
1079-1080. [Link]?id=4384.
6. Dasta, J.F., Application of artificial intelligence to pharmacy 24. MOLLY, THE VIRTUAL NURSE. [cited 2022 13 June];
and medicine. Hosp Pharm, 1992. 27(4): p. 312-5, 319-22. Available from: [Link]
7. Honavar, V., Artificial intelligence: An overview. Artificial molly-the-virtual-nurse/.
Intelligence Research Laboratory, 2006: p. 1-14. 25. AiCure. THE RIGHT DOSE FOR THE RIGHT PATIENT. [cited
8. Lopes, V. and L.A. Alexandre, An overview of blockchain 2022 13 June]; Available from: [Link]
integration with robotics and artificial intelligence. arXiv 26. Deep Genomics. Programming RNA Therapies Any Gene,
preprint arXiv:1810.00329, 2018. Any Genetic Condition. [cited 2022 13 June]; Available
9. Kawal, F., A Tour to the World of Artificial Intelligence. from: [Link]
CYBERNOMICS, 2020. 2(5): p. 33-35. 27. Shampo, M.A. and R.A. Kyle, J. Craig Venter--The Human
10. SIRI. [cited 2022 20 May]; Available from: Genome Project. Mayo Clinic proceedings, 2011. 86(4): p.
[Link] e26-e27.
nition/Siri. 28. Atomwise. Artificial Intelligence for Drug Discovery.;
11. What Is Alexa? [cited 2022 20 May]; Available from: Available from: [Link]
[Link] 29. Open AI Ecosystem.; Available from:
ai/#:~:text=What%20Is%20Alexa%3F,Echo%20and%20Dot% [Link]
20smart%20speakers. ecosystem-portends-a-personal-assistant-for-everyone/.
12. How Google's Self-Driving Car Will Change Everything. 30. eInvoicing in The Netherlands.; Available from:
[cited 2022 20 May]; Available from: [Link]
[Link] blocks/wikis/display/DIGITAL/eInvoicing+in+The+Netherlan
ai/. ds.
13. Das, S., et al., Applications of artificial intelligence in 31. Fleming, N., How artificial intelligence is changing drug
machine learning: review and prospect. International discovery. Nature, 2018. 557(7706): p. S55-S55.
Journal of Computer Applications, 2015. 115(9). 32. Okafo, G., Adapting drug discovery to artificial intelligence.
14. Heudin, J.-C. Artificial life and evolutionary computing in Drug Target Rev, 2018: p. 50-52.
machine perception. in Proceedings of Conference on 33. Ferrero, E., I. Dunham, and P. Sanseau, In silico prediction of
Computer Architectures for Machine Perception. 1995. IEEE. novel therapeutic targets using gene–disease association
15. State Of AI And Machine Learning In 2019.; Available from: data. Journal of translational medicine, 2017. 15(1): p. 1-16.
[Link] 34. Katsila, T., et al., Computational approaches in target
state-of-ai-and-machine-learning-in- identification and drug discovery. Computational and
2019/?sh=133dd64c1a8d. structural biotechnology journal, 2016. 14: p. 177-184.
16. Mulholland, M., et al., A comparison of classification in 35. Yildirim, O., et al., Opportunities and challenges for drug
artificial intelligence, induction versus a self-organising development: public–private partnerships, adaptive designs
neural networks. Chemometrics and Intelligent Laboratory and big data. Frontiers in pharmacology, 2016. 7: p. 461.
Systems, 1995. 30(1): p. 117-128. 36. Medarević, D.P., et al., Combined application of mixture
17. Shakya, S., Analysis of artificial intelligence based image experimental design and artificial neural networks in the
classification techniques. Journal of Innovative Image solid dispersion development. Drug development and
Processing (JIIP), 2020. 2(01): p. 44-54. industrial pharmacy, 2016. 42(3): p. 389-402.
18. Arend Hintze. Understanding the four types of AI. [cited 37. Barmpalexis, P., et al., Development of PVP/PEG mixtures as
2022 13 June]; Available from: appropriate carriers for the preparation of drug solid
[Link] dispersions by melt mixing technique and optimization of
types-of-ai-from-reactive-robots-to-self-aware-beings- dissolution using artificial neural networks. European
67616. Journal of Pharmaceutics and Biopharmaceutics, 2013.
19. Ganapathy, K., S.S. Abdul, and A.A. Nursetyo, Artificial 85(3): p. 1219-1231.
intelligence in neurosciences: A clinician's perspective.
Neurology India, 2018. 66(4): p. 934.

[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 7

DOI: [Link]
Review Article PHARMACY PRACTICE & PRACTICE-BASED RESEARCH

38. Pharma News Inteligence. . Available from: 49. Davoudi, A., et al., The intelligent ICU pilot study: using
[Link] artificial intelligence technology for autonomous patient
39. GNS Healthcare.; Available from: monitoring. arXiv preprint arXiv:1804.10201, 2018.
[Link] 50. Yu, K.-H., A.L. Beam, and I.S. Kohane, Artificial intelligence
40. AtomNet. How we do it.; Available from: in healthcare. Nature biomedical engineering, 2018. 2(10):
[Link] p. 719-731.
41. Insilico Medicine. ARTIFICIAL INTELLIGENCE FOR EVERY STEP 51. Musib, M., et al., Artificial intelligence in research. science,
OF PHARMACEUTICAL RESEARCH AND DEVELOPMENT.; 2017. 357(6346): p. 28-30.
Available from: [Link] 52. Ahuja, A.S., The impact of artificial intelligence in medicine
42. Insilico Medicine. Insilico Medicine launches trial for AI- on the future role of the physician. PeerJ, 2019. 7: p. e7702.
discovered drug.; Available from: [Link] 53. Han, E.-R., et al., Medical education trends for future
[Link]/Article/2021/12/15/Insilico-Medicine- physicians in the era of advanced technology and artificial
launches-trial-for-AI-discovered-drug. intelligence: an integrative review. BMC medical education,
43. Chatbots. Medicine Delivery.; Available from: 2019. 19(1): p. 1-15.
[Link] 54. Henstock, P.V., Artificial intelligence for pharma: time for
templates/healthcare/Hk8N4h/medicine-ordering-chatbot. internal investment. Trends in pharmacological sciences,
44. Walgreen. Convenient virtual care. . Available from: 2019. 40(8): p. 543-546.
[Link] 55. Mitchell, J.B., Artificial intelligence in pharmaceutical
telehealth. research and development. 2018, Future Science. p. 1529-
45. Otto Group. . Available from: 1531.
[Link] 56. Neill, D.B., Using artificial intelligence to improve hospital
us/konzernfirmen/[Link]. inpatient care. IEEE Intelligent Systems, 2013. 28(2): p. 92-
46. UCSF Robotic Pharmacy Aims to Improve Patient Safety. . 95.
[cited 2022 10 Janaury ]; Available from: 57. Klumpp, M., et al. Artificial intelligence for hospital health
[Link] care: Application cases and answers to challenges in
robotic-pharmacy-aims-improve-patient-safety. european hospitals. in Healthcare. 2021. Multidisciplinary
47. Dilsizian, S.E. and E.L. Siegel, Artificial intelligence in Digital Publishing Institute.
medicine and cardiac imaging: harnessing big data and 58. Nelson, S.D., et al., Demystifying artificial intelligence in
advanced computing to provide personalized medical pharmacy. American Journal of Health-System Pharmacy,
diagnosis and treatment. Current cardiology reports, 2014. 2020. 77(19): p. 1556-1570.
16(1): p. 441. 59. Kostić, E.J., D.A. Pavlović, and M.D. Živković, Applications of
48. Li, L.-R., et al., Artificial Intelligence for Personalized artificial intelligence in medicine and pharmacy: Ethical
Medicine in Thyroid Cancer: Current Status and Future aspects. Acta Medica Medianae, 2019. 58(3): p. 128-137.
Perspectives. Frontiers in Oncology, 2021. 10: p. 3360.

[Link] 2022, Vol. 13, No. 2, Article 13 INNOVATIONS in pharmacy 8

DOI: [Link]
View publication stats