Artificial Intelligence (AI)’S Transformative Impact on Drug Development and Regulatory Affairs: A 2025 Review

Abstract

Artificial Intelligence (AI) is revolutionizing the pharmaceutical industry by accelerating drug discovery, enhancing the efficiency of clinical trials, and enabling the development of personalized medicine. It is also being used in pharmaceutical regulatory affairs to automate the regulatory filling and document management. This review highlights the current applications of AI in drug development and pharmaceutical regulatory affairs, explores key case studies and technological advancements, and discusses the challenges and regulatory considerations associated with these applications. As the AI drug discovery market is growing significantly [1], understanding its integration within pharmaceutical pipelines is critical for stakeholders across industry and academia.

Keywords: Artificial Intelligence, Drug Discovery, Machine Learning, Clinical Trials, Personalized Medicine, Drug Repurposing, Predictive Analytics, Regulatory Frameworks, Generative AI, Pharma Innovation

Abbreviations: AI: Artificial Intelligence; FDA: Food and Drug Administration; NLP: Natural Language Processing; SaMD: Software as a Medical Device.

Introduction

Pharmaceutical industry plays a critical role to address healthcare challenges and respond to medical emergencies which is mainly based on continuous innovation and application of new technologies. The core steps of pharmaceuticals innovation include extensive research and development, manufacturing process devel opment and optimization, packaging considerations, and patient oriented marketing strategies [2].

The traditional drug development process is time-consuming, costly, and fraught with high failure rates. The challenges are even more extensive during the development of novel therapeutics and complex manufacturing process. Every stage of the pharmaceutical product life cycle, including drug discovery, optimization, formulation development, characterization, quality testing, marketing, and post-marketing surveillance, can integrate AI to improve its safety, quality and efficacy [3]. AI offers promising solutions by expediting various phases of drug development, from target identification to clinical trials. In 2025, the market for AI in drug discovery is valued at approximately $1.94 billion and is expected to reach $16.49 billion by 2034. This growth underscores AI’s transformative potential in modernizing pharmaceutical R&D.

AI can be implemented to simplify the regulatory affairs activities like- dossier compilation, documents archiving and review, data extraction, compliance auditing and quality management system. This human AI- Human interaction opens new era in pharmaceutical regulatory affairs [4]. The European Medicines Agency (EMA) and Food and Drug Administration (FDA) have plans to implement AI and are currently consulting stakeholders for their comments.

Materials and Methods

This review was conducted through an extensive literature analysis of peer-reviewed journals, company reports, regulatory documents, and market studies published between 2017 and 2025. Key search terms included “AI in drug discovery,” “machine learning in pharma,” “generative AI for molecules,” and “regulatory AI in medicine.” Data from PubMed, Scopus, and Google Scholar formed the basis of this synthesis.

Results and Discussion

AI in the Life Cycle Management of Pharmaceuticals

Figure 1: AI in various pharmaceutical business subclass, including pharmaceutical product management and drug development [5].

Table 1

AI can support different stages of drug research and development and throughout the life cycle of the pharmaceuticals. AI can actually be implemented from the lab to the bed. Main steps are Drug discovery, Clinical trial design & monitoring, Pharmaceuticals product development, Manufacturing, Quality control & assurance, Product management and post market surveillance. A number of AI tools/technique which are widely use now in the pharmaceuticals industry is tabulated below [5] (Table 1) (Figure 1).

AI’s Role in Modern Drug Formulation

The pharmaceutical industry is increasingly turning to artificial intelligence (AI) to solve complex problems in drug formulation. Traditional dosage forms are being enhanced—or replaced—by more advanced systems like nanoemulsions, capsules, and solid dispersions, thanks in large part to machine learning and neural network models. These technologies help scientists overcome typical formulation barriers such as poor solubility, inadequate stability, and inconsistent bioavailability [6].

Controlled Release Dosage form

To develop tablets that release drugs gradually over time, researchers use AI-based tools to simulate how medications behave in the body. Artificial Neural Networks (ANNs), in particular, have proven effective in fine-tuning how quickly a drug dissolves and is absorbed, helping to align lab-based release profiles with real- life performance [7].

Fast-Acting Tablets

When immediate effects are needed, AI again plays a key role. Rather than relying solely on trial and error, formulators use neural networks and optimization algorithms to evaluate the right mix of ingredients and manufacturing processes [8]. These approaches provide more reliable results than traditional statistical models.

Capsule Formulation

Hard gelatin capsules—often used for drugs with poor water solubility—also benefit from AI. These systems mimic human reasoning to predict how different ingredients will interact. Though early versions struggled with accuracy, refinements in machine learning have led to much better predictive models, especially when working with data from similar drug types [9].

Solid Dispersions

AI is widely used in improving formulations where the active drug is embedded in a solid base. These systems are known for enhancing solubility and stability. Using techniques like random forest models, scientists can now identify which factors—such as polymer choice or humidity levels—most influence final product quality.

Emulsions and Nanoemulsions

These complex mixtures of oil and water are stabilized with emulsifiers and require careful formulation. AI tools assist in adjusting ingredients to achieve the right balance of particle size, texture, and shelf-life [10]. In some cases, neural networks can even predict product performance based on thermal and structural data.

Self-Emulsifying Systems (SEDDS)

SEDDS are designed to help drugs dissolve in the body more effectively. AI is used here to model how the formulation behaves during digestion, ensuring optimal absorption. Researchers apply advanced algorithms to determine the right blend of oils, surfactants, and drugs, tailoring each formulation to meet specific bioavailability needs.

Other Applications

Beyond these examples, AI continues to be integrated into the creation of microparticles [11-15], nanoparticles [16-29], liposomes [30], microspheres [31-33], and various solid and liquid drug forms. Its ability to process complex data quickly makes it an invaluable tool for modern pharmaceutical development.

AI’s Role in Pharmaceutical Regulatory Affairs

Traditional Approach

The manual process of regulatory affairs involves:

i. Data collection and dossier preparation, which is time-consuming, prone to manual errors, and results in a heavy workload.

ii. Document review and dossier submission are also labor- intensive and inefficient.

AI-Driven Regulatory Affairs

With AI implementation, the process is transformed, offering [34]:

a) Easy documentation and submissions

b) Real-time monitoring and seamless data exchange

c) Enhanced regulatory intelligence

d) Improved decision-making and compliance

e) Optimization of workflows

f) Risk assessment and predictive modeling

g) Faster approval with a higher success rate

Overall, AI streamlines and enhances the efficiency, accuracy, and speed of regulatory processes in pharmaceutical and healthcare sectors.

Conclusion

AI is driving a paradigm shift in drug development, offering solutions to overcome long-standing pharmaceutical R&D challenges. Addressing integration barriers, regulatory clarity, and ethical use will ensure its sustained impact. The use of AI in pharmaceutical formulations is predictable and will continue to be transformative. AI aids researchers in identifying new drug targets, drug interactions, and patient populations that can most benefit from treatment. With increasingly advanced AI systems, researchers can accurately simulate biological systems and develop more personalized treatments, leading to more efficient and targeted drug development. In the fast-paced and rapidly changing environment of pharmaceutical regulatory affairs, the ability to apply AI to the many tasks involved is a major step up. That includes not only more time-efficient regulatory dossier creation, but also better processes for risk analysis and other key regulatory aspects.

Acknowledgements

The authors acknowledge support from Dona Roy Chowdhury for her technical support in the review and carry out this research work.

Conflict of Interest

The authors declare no conflict of interest.

References

• Global Market Insights (2024) Artificial Intelligence in Drug Discovery Market Size Report.
• Chavda VP, Vihol D, Patel A, Redwan EM, Uversky VN, et al. (2023) Bioinformatics Tools for Pharmaceutical Drug Product Development. John Wiley Sons Ltd Hoboken NJ USA Introduction to Bioinformatics AI and ML for Pharmaceuticals: 1-18.
• Debleena Paul, Gaurav Sanap, Snehal Shenoy, Dnyaneshwar Kalyane, Kiran Kalia, et al. (2020) Artifcial intelligence in drug discovery and development. Drug Discov Today 26(1): 80-93.
• Patil RS, Kulkarni SB, Gaikwad VL (2023) Artificial intelligence in pharmaceutical regulatory affairs. Drug Discov Today 28(9): 103700.
• Kazi Asraf Ali, SK Mohin, Puja Mondal, Susmita Goswami, Soumya Ghosh, et al. (2024) Influence of artificial intelligence in modern pharmaceutical formulation and drug development. Futur J Pharm Sci: 10(53).
• Ahmed Al Kuwaiti, Khalid Nazer, Abdullah Al Reedy, Shaher Al Shehri, Afnan Al Muhanna, et al. (2023) a review of the role of artificial intelligence in healthcare. J Pers Med 13(6): 951.
• Landin M, Rowe RC (2013) Artificial neural networks technology to model, understand, and optimize drug formulations. In Formulation tools for pharmaceutical development: 7-37.
• Katsila T, Spyroulias GA, Patrinos GP, Matsoukas MT (2016) Computational approaches in target identification and drug discovery. Comput Struct Biotechnol J 14: 177-184.
• Dorothea Emig, Alexander Ivliev, Olga Pustovalova, Lee Lancashire, Svetlana Bureeva, et al. (2013) Drug target prediction and repositioning using an integrated network-based approach. PLoS One 8(4): e60618.
• Solans C, Izquierdo P, Nolla (2005) Nano-emulsions. Curr Opin Colloid Interface Sci 10:102-110.
• Gursoy RN, Benita S (2004) Self-emulsifying drug delivery systems (SEDDS) for improved oral delivery of lipophilic drugs. Biomed Pharmacother Biomedecine Pharmacother 58(3): 173-182.
• Bhupinder Singh, Shantanu Bandopadhyay, Rishi Kapil, Ramandeep Singh, O Katare, et al. (2009) Self-emulsifying drug delivery systems (SEDDS): formulation development, characterization, and applications. Crit Rev Ther Drug Carrier Syst 26(5): 427-521.
• Dimitrios G Fatouros, Flemming Seier Nielsen, Dionysios Douroumis, Leontios J Hadjileontiadis, Anette Mullertz, et al. (2008) In vitro-in vivo correlations of self-emulsifying drug delivery systems combining the dynamic lipolysis model and neuro-fuzzy networks. Eur J Pharm Biopharm Off J Arbeitsgemeinschaft Pharm Verfahrenstechnik EV 69(3): 887-898.
• Parikh KJ, Sawant KK (2018) Comparative study for optimization of pharmaceutical self-emulsifying pre-concentrate by design of experiment and artificial neural network. AAPS PharmSciTech 19(7): 3311-3321.
• Chen Wen Li, Sheng Yong Yang, Rui He, Wan Jun Tao, Zong Ning Yin, et al. (2011) Development of quantitative structure-property relationship models for self-emulsifying drug delivery system of 2-aryl propionic acid NSAIDs. J Nanomater :1-12.
• Giang Thi Thu Vu, Nghia Thi Phan, Huyen Thi Nguyen, Hung Canh Nguyen, Yen Thi Hai Tran, et al. (2020) Application of the artificial neural network to optimize the formulation of self-nanoemulsifying drug delivery system containing rosuvastatin. J Appl Pharm Sci: 10(9).
• Ying Huang, Qinghe Yao, Chune Zhu, Xuan Zhang, Lingzhen Qin, et al. (2015) Comparison of novel granulated pellet-containing tablets and traditional pellet-containing tablets by artificial neural networks. Pharm Dev Technol 20(6): 670-675.
• Aleksander Mendyk, Peter Kleinebudde, Markus Thommes, Angelina Yoo, Jakub Szlęk, et al. (2010) Analysis of pellet properties with use of artificial neural networks. Eur J Pharm Sci Off J Eur Fed Pharm Sci 41(3-4): 421-429.
• Peh KK, Lim CP, Quek SS, Khoh KH (2000) Use of artificial neural networks to predict drug dissolution profiles and evaluation of network performance using similarity factor. Pharm Res 17(11): 1384-1388.
• Sankalia MG, Mashru RC, Sankalia JM, Sutariya VB (2005) Papain entrapment in alginate beads for stability improvement and site-specific delivery: physicochemical characterization and factorial optimization using neural network modeling. AAPS PharmSciTech 6(2): E209-222.
• Vaithiyalingam S, Khan MA (2002) Optimization and characterization of controlled release multi- particulate beads formulated with a customized cellulose acetate butyrate dispersion. Int J Pharm 234(1-2): 179-193.
• Asadi H, Rostamizadeh K, Salari D, Hamidi M (2011) Preparation of biodegradable nanoparticles of tri-block PLA-PEG-PLA copolymer and determination of factors controlling the particle size using artificial neural network. J Microencapsul 28(5): 406-416.
• Baharifar H, Amani A (2017) Size, loading efficiency, and cytotoxicity of albumin-loaded chitosan nanoparticles: an artificial neural networks study. J Pharm Sci 106(1): 411-417.
• Rania A Hashad, Rania A H Ishak, Sherif Fahmy, Samar Mansour, Ahmed S Geneidi, et al. (2016) Chitosan-tripolyphosphate nanoparticles: optimization of formulation parameters for improving process yield at a novel pH using artificial neural networks. Int J Biol Macromol 86: 50-58.
• Shahsavari S, Rezaie Shirmard L, Amini M, Abedin Dokoosh F (2017) Application of artificial neural networks in the design and optimization of a nanoparticulate fingolimod delivery system based on biodegradable Poly(3-Hydroxybutyrate-Co-3-Hydroxyvalerate). J Pharm Sci 106(1): 176-182.
• Karim S Shalaby, Mahmoud E Soliman, Luca Casettari, Giulia Bonacucina, Marco Cespi, et al. (2014) Determination of factors controlling the particle size and entrapment efficiency of noscapine in PEG/PLA nanoparticles using artificial neural networks. Int J Nanomed 9: 4953-4964.
• Leonardi D, Salomón CJ, Lamas MC, Olivieri AC (2009) Development of novel formulations for Chagas’ disease: optimization of benznidazole chitosan microparticles based on artificial neural networks. Int J Pharm 367(1-2): 140-147.
• Yongqiang Li, Mohammadreza R Abbaspour, Paul V Grootendorst, Andrew M Rauth, Xiao Yu Wu, et al. (2015) Optimization of controlled release nanoparticle formulation of verapamil hydrochloride using artificial neural networks with genetic algorithm and response surface methodology. Eur J Pharm Biopharm Off J Arbeitsgemeinschaft Pharm Verfahrenstechnik EV 94: 170-179.
• Metwally AA, Hathout RM (2015) Computer-assisted drug formulation design: novel approach in drug delivery. Mol Pharm 12(8): 2800-2810.
• Hassanzadeh P, Atyabi F, Dinarvand R (2017) Application of modelling and nanotechnology-based approaches: the emergence of breakthroughs in theranostics of central nervous system disorders. Life Sci 182: 93-103.
• Youshia J, Ali ME, Lamprecht A (2017) Artificial neural network based particle size prediction of polymeric nanoparticles. Eur J Pharm Biopharm Off J Arbeitsgemeinschaft Pharm Verfahrenstechnik EV 119: 333-342.
• Rizkalla N, Hildgen P (2005) Artificial neural networks: comparison of two programs for modeling a process of nanoparticle preparation. Drug Dev Ind Pharm 31(10): 1019-1033.
• Rosalia Rodríguez Dorado, Mariana Landín, Ayça Altai, Paola Russo, Rita P Aquino, et al. (2018) A novel method for the production of core-shell microparticles by inverse gelation optimized with artificial intelligent tools. Int J Pharm 538(1-2): 97-104.
• Ruchika S Patil, Samruddhi B Kulkarni, Vinod L Gaikwad (2023) Artificial intelligence in pharmaceutical regulatory affairs. Drug Discovery Today 28(9): 103700.