INTRODUCTION:

Artificial Intelligence (AI) the field of science which combines intelligent machine learning specially intelligent computer programs that provides results in the similar way to human attention process.¹ This process generally comprises obtaining data, developing efficient systems for the uses of obtained data, illustrating definite or approximate conclusions and self-corrections/adjustments.² In general, AI is used for analyzing the machine learning to imitate the cognitive tasks of individuals.^2,3 AI technology is exercised to perform more accurate analyses as well as to attain useful interpretation.³ In this perspective, various useful statistical models as well as computational intelligence are combined in the AI technology.⁴ The progress and innovation of AI applications are often associated to the fear of unemployment threat. However, almost all advancements in the applications of AI technology are being celebrated on account of the confidence, which enormously contributes its efficacy to the industry. Recently, AI technology becomes a very fundamental part of industry for the useful applications in many technical and research fields.^3,4 The emergent initiative of accepting the applications of AI technology in pharmacy including drug discovery, drug delivery formulation development and other healthcare applications have already been shifted from hype to hope.^5,6 The uses of AI models also make possible to predict the in vivo responses, pharmacokinetic parameters of the therapeutics, suitable dosing, etc^{. 2,7} According to the importance of pharmacokinetic prediction of drugs, the uses of in silico models facilitate their effectiveness and inexpensiveness in the drug research.⁸

The use of artificial intelligence (AI) has been increasing in various sectors of society, particularly the pharmaceutical industry. In this review, we highlight the use of AI in diverse sectors of the pharmaceutical industry, including drug discovery and development, drug repurposing, improving pharmaceutical productivity, and clinical trials, among others; such use reduces the human workload as well as achieving targets in a short period of time. We also discuss crosstalk between the tools and techniques utilized in AI, ongoing challenges, and ways to overcome them, along with the future of AI in the pharmaceutical industry.

Over the past few years, there has been a drastic increase in data digitalization in the pharmaceutical sector. However, this digitalization comes with the challenge of acquiring, scrutinizing, and applying that knowledge to solve complex clinical problems⁹. This motivates the use of AI, because it can handle large volumes of data with enhanced automation¹⁰. AI is a technology-based system involving various advanced tools and networks that can mimic human intelligence. At the same time, it does not threaten to replace human physical presence^11,12 completely. AI utilizes systems and software that can interpret and learn from the input data to make independent decisions for accomplishing specific objectives. Its applications are continuously being extended in the pharmaceutical field, as described in this review. According to the McKinsey Global Institute, the rapid advances in AI-guided automation will be likely to completely change the work culture of society^13,14

AI: Networks and Tools:

AI involves several method domains, such as reasoning, knowledge representation, solution search, and, among them, a fundamental paradigm of machine learning (ML). ML uses algorithms that can recognize patterns within a set of data that has been further classified. A subfield of the ML is deep learning (DL), which engages artificial neural networks (ANNs). These comprise a set of interconnected sophisticated computing elements involving ‘perceptons’ analogous to human biological neurons, mimicking the transmission of electrical impulses in the human brain¹⁵. ANNs constitute a set of nodes, each receiving a separate input, ultimately converting them to output, either singly or multi-linked using algorithms to solve problems¹⁶. ANNs involve various types, including multilayer perceptron (MLP) networks, recurrent neural networks (RNNs), and convolutional neural networks (CNNs), which utilize either supervised or unsupervised training procedures^17,18

Classification of ai:

AI can be classified into two different ways: according to calibre and their presence

According to their ability, AI can be categorized as:

i) Artificial Narrow Intelligence (ANI) or Weak AI: It performs a narrow range task, i.e., facial identification, steering a car, practicing chess, traffic signalling, etc.

ii) Artificial General Intelligence (AGI) or Strong AI: It performs all the things as humans and also known as human level AI. It can simplify human intellectual abilities and able to do unfamiliar task.

iii) Artificial Super Intelligence (ASI): It is smarter than humans and has much more activity than humans drawing, mathematics, space, etc.

According to their presence and not yet present, AI can be classified as follows:

i) Type 1: It is used for narrow purpose applications, which cannot use past experiences as it has no memory system. It is known as reactive machine. There are some examples of this memory, such as a IBM chess program, which can recognize the checkers on the chess playing board and capable of making predictions.

ii) Type 2: It has limited memory system, which can apply the previous experiences for solving different problems. In automatic vehicles, this system is capable of making decisions there are some recorded observations, which are used to record further actions, but these records are not stored permanently.

iii) Type 3: It is based upon “Theory of Mind”. It means that the decisions that human beings make are impinged by their individual thinking, intentions and desires. This system is non-existing AI.

iv). Type 4: It has self-awareness, i.e., the sense of self and consciousness. This system is also non-existing AI.

Artificial Intelligence and Robotics:

Artificial intelligence and Robotics have a common root and a long history of interaction and scientific discussion.one might argue that not every machine is a Robot and certainly artificial intelligence is concerned also with virtual agents. Artificial intelligence is a theory and robots are manufactured as hardware. The connection between these two is that the control of the robot is a software agent that reads data from these sensors decides what to do next and then directs the efforts to act in the physical world. It has wide application in robotics²⁰. Furthermore, as patients become more engaged in their healthcare decision, they will turn to research possible medication options. Through target audience marketing, pharmaceutical companies can further assure the right information is presented at the right time to facilitate informed patent and provider discussions¹⁹.

“It Is Time for Connected Pharma”

However, progress is far from uniform and progress is likely to be “lumpy “at best .AI technology is well on its way to becoming ubiquitous and has huge scope, enhancing technology at many levels, leading to much better, faster patient outcomes.

Pharmaceutical Automation:

With the help of Artificial Intelligence Automation is the result of industrialization, driven by the need to increase productivity, to achieve consistent quality products and to remove hazardous and heavy work from workers.

Innovations in technology now comprise the essential building blocks of Automation. Most Pharma players understand the benefit of adopting new technologies but there remains a persistent and troubling gap between strategy and organizations ability to adopt and deploy a data analytics working solution²¹

The adoption of AI allows for learning from real - time data.

*Identifying the right candidates for clinical trials.

*Processing real time patient feedback.

*Integrating data exchanges with partners.

*Distributors and caregivers.

There are just few examples on how to improve drug discovery outcomes, while aligning operational efficiencies to deliver better care to the patients, often getting the right medication to the right patient at right time is really about getting right information in front of healthcare provider. Armed with complete real-time drug insights, doctors are able to choose right prescription for the best possible outcome.

Automation applications continue to grow with enabling technologies such as²²:

1. Wireless

2. Nanotechnology

3. Advance storage and memory

4. Sensors and analyzers

5. Advance software algorithms

6. Artificial intelligence.

Ai in Advancing Pharmaceutical Drug Development:

The discovery of a novel drug molecule requires its subsequent incorporation in a suitable dosage form with desired delivery characteristics. In this area, AI can replace the older trial and error approach ²³. Various computational tools can resolve problems encountered in the formulation design area, such as stability issues, dissolution, porosity, and so on, with the help of QSPR ²⁴. Decision-support tools use rule-based systems to select the type, nature, and quantity of the excipients depending on the physicochemical attributes of the drug and operate through a feedback mechanism to monitor the entire process and intermittently modify it²⁵.

The Model Expert System (MES) makes decisions and recommendations for formulation development based on the input parameters. By contrast, ANN uses backpropagation learning to link formulation parameters to the desired response, jointly controlled by the control module, to ensure hassle-free formulation development²⁶.

Various mathematical tools, such as computational fluid dynamics (CFD), discrete element modeling (DEM), and the Finite Element Method have been used to examine the influence of the flow property of the powder on the die-filling and process of tablet compression^27,28. CFD can also be utilized to study the impact of tablet geometry on its dissolution profile²⁹. The combination of these mathematical models with AI could prove to be of immense help in the rapid production of pharmaceutical products.

Ai in Pharmaceutical Marketing:

With the increasing complexities of manufacturing processes along with increasing demand for efficiency and better product quality, modern manufacturing systems are trying to confer human knowledge to machines, continuously changing the manufacturing practice³⁰. The incorporation of AI in manufacturing can prove to be a boost for the pharmaceutical industry. Tools, such as CFD, uses Reynolds-Averaged Navier-Stokes solvers technology that studies the impact of agitation and stress levels in different equipment (e.g., stirred tanks), exploiting the automation of many pharmaceutical operations. Similar systems, such as direct numerical simulations and large eddy simulations, involve advanced approaches to solve complicated flow problems in manufacturing³¹.

The novel Chapter platform helps digital automation for the synthesis and manufacturing of molecules, incorporating various chemical codes and operating by using a scripting language known as Chemical Assembly³². It has been successfully used for the synthesis and manufacture of sildenafil, diphenhydramine hydrochloride, and rufinamide, with the yield and purity significantly similar to manual synthesis³³. The estimated completion of granulation in granulators of capacities ranging from 25 to 600 l can be done efficiently by AI technologies³⁴. The technology and neuro-fuzzy logic correlated critical variables to their responses. They derived a polynomial equation for the prediction of the proportion of the granulation fluid to be added, required speed, and the diameter of the impeller in both geometrically similar and dissimilar granulators³⁵.

Ai in Quality Control and Quality Assurance:

Manufacturing of the desired product from the raw materials includes a balance of various parameters³⁶. Quality control tests on the products, as well as maintenance of batch-to-batch consistency, require manual interference. This might not be the best approach in each case, showcasing the need for AI implementation at this stage³⁷. The FDA amended the Current Good Manufacturing Practices (cGMP) by introducing a ‘Quality by Design’ approach to understand the critical operation and specific criteria that govern the final quality of the pharmaceutical product³⁸.

Ai in Clinical Filed:

Clinical trials are directed toward establishing the safety and efficacy of a drug product in humans for a particular disease condition and require 6–7 years along with a substantial financial investment. However, only one out of ten molecules entering these trials gain successful clearance, which is a massive loss for the industry³⁹. These failures can result from inappropriate patient selection, shortage of technical requirements, and poor infrastructure. However, with the vast digital medical data available, these failures can be reduced with the implementation of AI⁴⁰.

CONCLUSION:

During past few years, a considerable amount of increasing interest towards 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, poly pharmacology, hospital pharmacy, etc., as the AI technological approaches believe like human beings imagining knowledge, cracking problems and decision making. The uses of automated workflows and databases for the effective analyses employing AI approaches have been proved useful. As a result of the uses of AI approaches, the designing of the new hypotheses, strategies, prediction and analyses of various associated factors can easily be done with the facility of less time consumption and inexpensiveness.

Human being is the most sophisticated machine that can ever be created. The human brain, which is working hard to create something that, is much more efficient than a human being in doing any given task and it has great success to extent in doing so. The AI tools like Watson for oncology, tug robot and robotic pharmacy has change the profession considerably. The bigger the healthcare sector gets more sophisticated and more technologically advanced infrastructure it will need.

REFERENCES:

1. Mak KK, Pichika MR. Artificial intelligence in drug development: Present status and future prospects. Drug Discov Today. 2019;24(3):773-80.

2. Hassanzadeh P, Atyabi F, Dinarvand R. The significance of artificial intelligence in drug delivery system design. Adv Drug Deliv Rev. 2019;151:169-90.

3. Russel S, Dewey D, Tegmark M. Research priorities for robust and beneficial artificial intelligence. AI Mag. 2015;36(4):105-14.

4. Duch W, Setiono R, Zurada JM. Computational intelligence methods for rulebased data understanding. Proc IEEE. 2004;92(5):771-805.

5. Dasta JF. Application of artificial intelligence to pharmacy and medicine. Hosp Pharm. 1992;27(4):319-22.

6. Jiang F, Jiang Y, Zhi H. Artificial intelligence in healthcare: Past, present and future. Stroke Vasc Neurol. 2017;2(4):230-43.

7. Gobburu JV, Chen EP. Artificial neural networks as a novel approach to integrated pharmacokinetic-pharmacodynamic analysis. J Pharm Sci. 1996;85(5):505-10.

8. Sakiyama Y. The use of machine learning and nonlinear statistical tools for ADME prediction. Expert Opin Drug Metab Toxicol. 2009;5(2):149-69.

9. Ramesh A. Artificial intelligence in medicine. Ann. R. Coll. Surg. Engl. 2004; 86:334–338.

10. Miles J., Walker A. The potential application of artificial intelligence in transport. IEE Proc.-Intell. Transport Syst. 2006;153:183–198

11. Yang Y., Siau K. MWAIS; 2018. A Qualitative Research on Marketing and Sales in the Artificial Intelligence Age.

12. Wirtz B.W. Artificial intelligence and the public sector—applications and challenges. Int. J. Public Adm. 2019;42:596–615.

13. Smith R.G., Farquhar A. The road ahead for knowledge management: an AI perspective. AI Mag. 2000;21 17–17.

14. Lamberti M.J. A study on the application and use of artificial intelligence to support drug development. Clin. Ther. 2019;41:1414–1426.

15. Beneke F., Mackenrodt M.-O. Artificial intelligence and collusion. IIC Int. Rev. Intellectual Property Competition Law. 2019;50:109–134.

16. Steels L., Brooks R. Routledge; 2018. The Artificial Life Route to Artificial Intelligence: Building Embodied, Situated Agents.

17. Bielecki A., Bielecki A. Foundations of artificial neural networks. In: Kacprzyk Janusz., editor. Models of Neurons and Perceptrons: Selected Problems and Challenges. Springer International Publishing; 2019. pp. 15–28. Polish academy of sciences, Warsaw, Poland.

18. Kalyane D. Artificial intelligence in the pharmaceutical sector: current scene and future prospect. In: Tekade Rakesh K., editor. The Future of Pharmaceutical Product Development and Research. Elsevier; 2020. pp. 73–107.

19. Russell S, Dewey D, Tegmark M. Research priorities for robust and beneficial artificial intelligence. Ai Magazine. 2015 Dec 31;36(4):105-14.

20. Lakshmi Teja T, Keerthi P, Debarshi Datta NB. Recent trends in the usage of robotics in pharmacy.

21. Yussupova N, Kovács G, Boyko M, Bogdanova D. Models and methods for quality management based on artificial intelligence applications. Acta Polytechnica Hungarica. 2016 Mar; 13(3):45-60

22. 22.Brady M. Artificial intelligence and robotics. In Robotics and Artificial Intelligence 1984 (pp. 47-63). Springer, Berlin, Heidelberg.

23. Guo M. A prototype intelligent hybrid system for hard gelatin capsule formulation development. Pharm. Technol. 2002;6:44–52.

24. Mehta C.H. Computational modeling for formulation design. Drug Discovery Today. 2019;24:781–788.

25. Zhao C. Toward intelligent decision support for pharmaceutical product development. J. Pharm. Innovation. 2006;1:23–35.

26. Rantanen J., Khinast J. The future of pharmaceutical manufacturing sciences. J. Pharm. Sci. 2015;104:3612–3638.

27. Ketterhagen W.R. Process modeling in the pharmaceutical industry using the discrete element method. J. Pharm. Sci. 2009;98:442–470.

28. Chen W. Mathematical model-based accelerated development of extended-release metformin hydrochloride tablet formulation. AAPS PharmSciTech. 2016;17:1007–1013.

29. Meziane F. Intelligent systems in manufacturing: current developments and future prospects. Integr. Manuf. Syst. 2000;11:218–238.

30. Steiner S. Organic synthesis in a modular robotic system driven by a chemical programming language. Science. 2019;363:eaav2211.

31. Faure A. Process control and scale-up of pharmaceutical wet granulation processes: a review. Eur. J. Pharm. Biopharm. 2001;52:269–277.

32. Landin M. Artificial intelligence tools for scaling up of high shear wet granulation process. J. Pharm. Sci. 2017;106:273–277.

33. Das M.K., Chakraborty T. ANN in pharmaceutical product and process development. In: Puri Munish., editor. Artificial Neural Network for Drug Design, Delivery and Disposition. Elsevier; 2016. pp. 277–293.

34. Gams M. Integrating artificial and human intelligence into tablet production process. AAPS PharmSciTech. 2014;15:1447–1453. 35. Kraft, D.L. System and methods for the production of personalized drug products. US20120041778A1.

35. Aksu B. A quality by design approach using artificial intelligence techniques to control the critical quality attributes of ramipril tablets manufactured by wet granulation. Pharm. Dev. Technol. 2013;18:236–245.

36. 96. Goh W.Y. Application of a recurrent neural network to prediction of drug dissolution profiles. Neural Comput. Appl. 2002;10:311–317.

37. Drăgoi E.N. On the use of artificial neural networks to monitor a pharmaceutical freeze-drying process. Drying Technol. 2013;31:72–81. 38. Reklaitis R. PharmaHub; 2008. Towards Intelligent Decision Support for Pharmaceutical Product Development.

38. Wang X. 2009 International Conference on Computational Intelligence and Software Engineering. IEEE; 2009. Intelligent quality management using knowledge discovery in databases; pp. 1–4.

39. Hay M. Clinical development success rates for investigational drugs. Nat. Biotechnol. 2014;32:40–51.

Received on 31.05.2022 Modified on 15.06.2022

Research J. Science and Tech. 2022; 14(3):183-187.

DOI: 10.52711/2349-2988.2022.00030