A Review on Artificial Intelligence

Abstract

AI is a stream of science related to intelligent machine learning, mainly intelligent computer programs, which provides results in a similar way to the human attention process[1]. This process generally comprises obtaining data, developing efficient systems for the uses of obtained data, illustrating definite or approximate conclusions, self-corrections, and adjustments[2]. In general, AI is used for analyzing 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 AI technology. Pharm AI traces its roots back to early 2000s research at TU Dresden, where foundational work in structural bioinformatics and computational drug discovery laid the groundwork for its core technology. Building on nearly two decades of academic innovation, Pharm AI was officially founded in 2019 to bring these breakthroughs into industrial application. Since then, Pharm AI has successfully completed over 40 projects, establishing a strong track record in AI-driven drug discovery. The company’s Discovery Engine platform has been validated in in vivo settings, including both small-molecule targets and protein–protein interaction disruptors. Pharmaceutical AI (pharma AI) uses artificial intelligence (AI) to speed up and simplify drug development. Agentic AI for pharma, generative AI, machine learning, natural language processing, and deep neural networks — which can process and analyze complex sets of data — work together to predict how drugs will behave. These technologies can recognize patterns faster than human analysts and deliver more precise results than traditional methods Key innovations have been supported through strategic public funding, notably from the German Federal Ministry for Economic Affairs and Energy, the European Social Fund, the European Regional Development Fund, and the state budget of Saxony — contributing to advancements in screening pipeline benchmarking, information security, and AI-based target discovery.

Introduction

Pharmacy Artificial Intelligence (AI), or pharmaco-intelligence, refers to using AI and information technology to improve drug discovery, development, manufacturing, clinical trials, medication management, and patient care. Traditional drug development is expensive and time-consuming, often taking around 12 years and costing billions of dollars. AI has the potential to shorten these timelines, reduce costs, and improve the safety and effectiveness of medicines.

1. Types of AI

• Artificial Intelligence (AI): Computer systems designed to perform tasks that normally require human intelligence, such as learning, reasoning, problem-solving, and decision-making.

• Machine Learning (ML): A branch of AI in which systems learn patterns from data without being explicitly programmed for every task.

  • Supervised learning: Uses labelled data to make predictions.

  • Unsupervised learning: Finds previously unknown patterns in unlabelled data.

• Deep Learning (DL): A more advanced form of ML using neural networks to analyze complex and unstructured data such as images, biological information, and chemical structures.

2. AI in Drug Discovery and Development

AI can significantly accelerate drug discovery by:

• Identifying promising drug candidates.

• Predicting interactions between drugs and biological targets.

• Designing new molecules with desired properties.

• Predicting ADMET properties—absorption, distribution, metabolism, excretion, and toxicity.

• Identifying new therapeutic targets.

• Repurposing existing drugs for new diseases.

AI can analyze enormous chemical, genetic, and biological datasets much faster than traditional methods, potentially reducing the time and cost required to develop new medicines.

3. AI in Clinical Trials

AI can improve clinical trials by helping with:

• Trial design: Optimizing protocols, sample sizes, dosing schedules, endpoints, trial locations, and duration.

• Patient recruitment: Screening electronic health records and identifying patients who meet trial criteria.

• Patient retention: Predicting dropout risks and personalizing communication with participants.

• Trial monitoring: Detecting adverse events, protocol deviations, and safety signals in real time.

• Digital twins: Creating virtual patient populations to simulate treatment outcomes and potentially reduce the number of participants required.

4. AI in Pharmacokinetics and Pharmacodynamics

AI can predict how drugs behave inside the human body. It can help estimate:

• Drug absorption and bioavailability.

• Distribution and tissue concentrations.

• Metabolism and elimination.

• Appropriate dosage.

• Therapeutic response.

• Drug interactions and possible adverse effects.

These predictions can contribute to personalized medicine, where treatment is adapted to an individual's characteristics and health information.

5. AI in Pharmaceutical Manufacturing

AI can improve pharmaceutical manufacturing through:

• Predictive maintenance of equipment.

• Quality control and detection of manufacturing problems.

• Inventory management and supply-chain optimization.

• Process optimization for greater efficiency.

• Digital twins for testing manufacturing changes virtually.

• Regulatory compliance through automated documentation and monitoring.

6. AI in Patient Care and Pharmacy Practice

AI is also being applied directly to healthcare and pharmacy, including:

• Maintaining and analyzing electronic medical records.

• Designing individualized treatment plans.

• Detecting abnormalities in X-rays, CT scans, ECGs, and other medical images.

• Identifying potential drug interactions and adverse events.

• Supporting medication adherence through reminders and digital tools.

• Assisting pharmacists with prescription verification and clinical decision-making.

• Automating routine pharmacy tasks and improving inventory management.

AI can also support genomic medicine by analyzing genetic information to identify mutations and help develop treatments tailored to individual patients.

7. Example of AI-Based Drug Development

The text describes INS018_055, an antifibrotic drug candidate being developed for idiopathic pulmonary fibrosis (IPF). AI platforms such as PandaOmics and Chemistry42 were used to identify a potential target and design the molecule.

According to the text, the candidate progressed from the beginning of its development program to Phase I clinical trials in less than 30 months, illustrating how AI can potentially accelerate drug development. The Phase I study involved 80 healthy volunteers and evaluated safety, tolerability, and pharmacokinetics.

8. Economic Impact

AI may reduce pharmaceutical costs by:

• Shortening drug discovery and development timelines.

• Reducing failure rates.

• Improving clinical trial recruitment and design.

• Optimizing manufacturing.

• Reducing unnecessary experiments and resource use.

• Supporting drug repurposing.

The technology may also create new roles requiring expertise in AI, machine learning, pharmaceutical data analysis, and digital health, while changing existing pharmacy and pharmaceutical jobs.

9. Challenges and Ethical Issues

Despite its benefits, AI in pharmacy has important limitations:

• Data quality: Incorrect or incomplete data can produce unreliable results.

• Bias: Biased datasets may lead to unequal or inappropriate outcomes for certain populations.

• Privacy: Patient information must be protected and handled according to applicable privacy regulations.

• Regulation: AI-generated decisions and pharmaceutical applications require appropriate oversight.

• Accountability: It can be difficult to determine responsibility when an AI-supported decision results in harm.

• Lack of human judgment and empathy: AI cannot completely replace human clinical expertise and patient interaction.

10. Future of AI in Pharmacy

The future of pharmaceutical AI is expected to involve greater use of personalized medicine, AI agents, electronic health records, decentralized clinical trials, genomic analysis, digital twins, and automated pharmacy services.

Conclusion

AI involves the combination of human knowledge and resources with Artificial Intelligence. As research into AI continues, with many interesting applications of it in progress, one may consider it a necessary evil even for those that see it as an enemy. Therefore, it is strongly recommended that pharmacists should acquire the relevant hard skills that promote AI augmentation. Education about and exposure to AI is necessary throughout all domains of pharmacy practice. Pharmacy students should be introduced to the essentials of data science and fundamentals of AI through a health informatics curriculum during their PharmD education. 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.

References

[1] Mak, K.-K. and Pichika M.R., Artificial intelligence in drug development: present status and future prospects. Drug discovery today, 2019. 24(3): p. 773-780. [DOI] [PubMed] [Google Scholar] [2] Das, S., Dey R., and Nayak A.K., Artificial Intelligence in Pharmacy. INDIAN JOURNAL OF PHARMACEUTICAL EDUCATION AND RESEARCH, 2021. 55(2): p. 304-318. [Google Scholar] [3] Russell, S., Dewey D., and Tegmark M., Research priorities for robust and beneficial artificial intelligence: an open letter. AI Magazine, 2015. 36(4). [Google Scholar] [4] Dasta, J., Application of artificial intelligence to pharmacy and medicine. Hospital pharmacy, 1992. 27(4): p. 312-5, 319. [PubMed] [Google Scholar] [5] Deopujari, S., et al. , Algoman: Gearing up for the “Net Generation” and Era of Artificial Intelligence, One Step at a Time. The Indian Journal of Pediatrics, 2019. 86(12): p. 1079-1080. [DOI] [PMC free article] [PubMed] [Google Scholar] [6] Dasta, J.F., Application of artificial intelligence to pharmacy and medicine. Hosp Pharm, 1992. 27(4): p. 312-5, 319-22. [PubMed] [Google Scholar] [7] Honavar, V., Artificial intelligence: An overview. Artificial Intelligence Research Laboratory, 2006: p. 1-14. [Google Scholar] [8] Lopes, V. and Alexandre L.A., An overview of blockchain integration with robotics and artificial intelligence. arXiv preprint arXiv:1810.00329, 2018. [Google Scholar] [9] Kawal, F., A Tour to the World of Artificial Intelligence. CYBERNOMICS, 2020. 2(5): p. 33-35. [Google Scholar] [10] SIRI. [cited 2022 20 May]; Available from: https://www.techtarget.com/searchmobilecomputing/definition/Siri. [11] What Is Alexa? [cited 2022 20 May]; Available from: https://itchronicles.com/artificial-intelligence/is-alexa-an-ai/#:~:text=What%20Is%20Alexa%3F,Echo%20and%20Dot%20smart%20speakers. [12] How Google’s Self-Driving Car Will Change Everything. [cited 2022 20 May]; Available from: https://www.eescorporation.com/do-self-driving-cars-use-ai/. [13] Das, S., et al. , Applications of artificial intelligence in machine learning: review and prospect. International Journal of Computer Applications, 2015. 115(9). [Google Scholar] [14] Heudin, J.-C. Artificial life and evolutionary computing in machine perception. in Proceedings of Conference on Computer Architectures for Machine Perception. 1995. IEEE. [Google Scholar] [15] State Of AI And Machine Learning In 2019.; Available from: https://www.forbes.com/sites/louiscolumbus/2019/09/08/state-of-ai-and-machine-learning-in-2019/?sh=133dd64c1a8d. [16] Mulholland, M., et al. , A comparison of classification in artificial intelligence, induction versus a self-organising neural networks. Chemometrics and Intelligent Laboratory Systems, 1995. 30(1): p. 117-128. [Google Scholar] [17] Shakya, S., Analysis of artificial intelligence based image classification techniques. Journal of Innovative Image Processing (JIIP), 2020. 2(01): p. 44-54. [Google Scholar] [18] Arend Hintze. Understanding the four types of AI. [cited 2022. 13 June]; Available from: https://theconversation.com/understanding-the-four-types-of-ai-from-reactive-robots-to-self-aware-beings-67616. [19] Ganapathy, K., Abdul S.S., and Nursetyo A.A., Artificial intelligence in neurosciences: A clinician’s perspective. Neurology India, 2018. 66(4): p. 934. [DOI] [PubMed] [Google Scholar] [20] Manikiran, S. and Prasanthi N., Artificial Intelligence: Milestones and Role in Pharma and Healthcare Sector. Pharma times, 2019. 51: p. 9-56. [Google Scholar] [21] Deep Mind’s health team. [cited 2022 13 June]; Available from: https://www.deepmind.com/blog/deepminds-health-team-joins-google-health. [22] IBM Watson for Oncology.; Available from: https://www.ibm.com/common/ssi/cgi-bin/ssialias?appname=skmwww&htmlfid=897%2FENUS5725-W51&infotype=DD&subtype=SM&mhsrc=ibmsearch_a&mhq=IBM%20WATSON%20ONcology#:~:text=IBM%20Watson%20for%20Oncology%2C%20software,Center%20physicians%20and%20other%20analysts. [23] IBM. Medical Sieve.. [cited 2022 13 June]; Available from: https://researcher.watson.ibm.com/researcher/view_group.php?id=4384. [24] MOLLY, THE VIRTUAL NURSE. [cited 2022 13 June]; Available from: http://adigaskell.org/2015/03/20/meet-molly-the-virtual-nurse/. [25] AiCure. THE RIGHT DOSE FOR THE RIGHT PATIENT. [cited 2022 13 June]; Available from: https://aicure.com/. [26] Deep Genomics. Programming RNA Therapies Any Gene, Any Genetic Condition. [cited 2022 13 June]; Available from: https://www.deepgenomics.com/. [27] Shampo, M.A. and Kyle R.A., J. Craig Venter--The Human Genome Project. Mayo Clinic proceedings, 2011. 86(4): p. e26-e27. [DOI] [PMC free article] [PubMed] [Google Scholar] [28] Atomwise. Artificial Intelligence for Drug Discovery.; Available from: https://www.atomwise.com/. [29] Open AI Ecosystem.; Available from: https://www.scientificamerican.com/article/open-ai-ecosystem-portends-a-personal-assistant-for-everyone/. [30] eInvoicing in The Netherlands.; Available from: https://ec.europa.eu/digital-building-blocks/wikis/display/DIGITAL/eInvoicing+in+The+Netherlands. [31] Fleming, N., How artificial intelligence is changing drug discovery. Nature, 2018. 557(7706): p. S55-S55. [DOI] [PubMed] [Google Scholar] [32] Okafo, G., Adapting drug discovery to artificial intelligence. Drug Target Rev, 2018: p. 50-52. [Google Scholar] [33] Ferrero, E., Dunham I., and Sanseau P., In silico prediction of novel therapeutic targets using gene–disease association data. Journal of translational medicine, 2017. 15(1): p. 1-16. [DOI] [PMC free article] [PubMed] [Google Scholar] [34] Katsila, T., et al. , Computational approaches in target identification and drug discovery. Computational and structural biotechnology journal, 2016. 14: p. 177-184. [DOI] [PMC free article] [PubMed] [Google Scholar]

Copyright

Copyright © 2026 Tarang Chaube, Mr. Pramod Mishra, Mr. Sujeet Pratap Singh, Dr. Tarkeshwar P. Shukla. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.