Int J App Pharm, Vol 16, Issue 2, 2024, 52-56Review Article

REVOLUTIONIZING DRUG DELIVERY INNOVATION: LEVERAGING AI-DRIVEN CHATBOTS FOR ENHANCED EFFICIENCY

RUBA MALKAWI

School of Pharmacy, Jadara University, P. O. Box 733, Irbid-21110, Jordan
*Corresponding author: Ruba Malkawi; *Email: r.malkawi@jadara.edu.jo

Received: 19 Dec 2023, Revised and Accepted: 19 Feb 2024

ABSTRACT

This study aims to delineate the pivotal role of ChatGPT, an Artificial intelligence-driven (AI) language model, in revolutionizing drug delivery research within the pharmaceutical sciences domain. The investigation adopted a structured approach involving systematic literature exploration across databases such as PubMed, ScienceDirect, IEEE Xplore, and Google Scholar. A selection criterion emphasizing peer-reviewed articles, conference proceedings, patents, and seminal texts highlights the integration of AI-driven chatbots, specifically ChatGPT, into various facets of drug delivery research and development. ChatGPT exhibits multifaceted contributions to drug delivery innovation, streamlining drug formulation optimization, predictive modeling, regulatory compliance, and fostering patient-centric approaches. Real-world case studies have underscored its efficacy in expediting drug development timelines and enhancing research efficiency. This paper delves into the diverse applications of ChatGPT, showcasing its potential across drug delivery systems. It elucidates its capabilities in accelerating research phases, facilitating formulation development, predictive modeling for efficacy and safety, and simplifying regulatory compliance. This discussion outlines the transformative impact of ChatGPT in reshaping drug delivery methodologies. In conclusion, ChatGPT, an AI-driven chatbot, has emerged as a transformative tool in pharmaceutical research. Their integration expedites drug development pipelines, ensures effective drug delivery solutions, and augments healthcare advancements. Embracing AI tools such as ChatGPT has become pivotal in evolving drug delivery methodologies for global patient welfare.

Keywords: Drug delivery innovation, AI-driven chatbots, Pharmaceutical industry, Artificial intelligence (AI), ChatGPT, Drug discovery, Medication counseling, Drug interactions, Formulation optimization, Predictive modelling

© 2024 The Authors. Published by Innovare Academic Sciences Pvt Ltd. This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/4.0/)
DOI: https://dx.doi.org/10.22159/ijap.2024v16i2.50182 Journal homepage: https://innovareacademics.in/journals/index.php/ijap

INTRODUCTION

ChatGPT, powered by advanced language models, such as GPT-3.5, offers numerous benefits across the pharmacy, pharmaceutical industry, and general research domains [1]. It serves as a versatile resource, providing up-to-date drug information, aiding medication counseling, and ensuring patient safety by highlighting drug interactions and contraindications [2]. In pharmaceutical research, ChatGPT accelerates drug discovery by analyzing complex datasets, predicting interactions, and suggesting potential lead compounds. It aids in the literature review and data extraction, streamlining research processes and ensuring regulatory compliance. Additionally, it optimizes clinical trials, facilitates personalized medicine, and enhances drug safety monitoring [2]. Beyond this, ChatGPT serves as a problem-solving and decision-support tool in research and clinical settings, offering accessibility, cost efficiency, multilingual communication, and the potential for substantial cost savings, ultimately advancing healthcare and pharmaceutical science through its wide-ranging capabilities. Drug delivery plays a pivotal role in the field of pharmaceuticals, impacting the safety, efficacy, and patient experience of medications [3]. The quest for novel drug delivery systems requires rigorous research, creativity, and time. However, with the advent of AI-driven chatbots, such as ChatGPT, the landscape of drug delivery innovation has evolved rapidly [4]. The methodology employed in this review involved a systematic exploration of the literature to comprehensively examine the impact of AI-driven chatbots, particularly ChatGPT, on revolutionizing drug delivery research and innovation. A meticulous and structured approach was adopted to gather pertinent information from various reputable sources in the pharmaceutical sciences.

Methods

The literature search encompassed databases such as PubMed, ScienceDirect, IEEE Xplore, and Google Scholar. Keywords including "drug delivery innovation," "AI-driven chatbots," "pharmaceutical industry," "Artificial intelligence (AI)," "ChatGPT," "drug discovery," "medication counseling," "drug interactions," "formulation optimization," and "predictive modeling" were utilized to ensure a comprehensive scope. The search included publications published between January 2010 and December 2023 [5]. The selection criteria prioritized peer-reviewed articles, conference proceedings, patents, and seminal texts, focusing on the integration of AI-driven chatbots, especially ChatGPT, into various facets of drug delivery research and development.

Inclusion and exclusion criteria

The included literature emphasized empirical studies, case reports, reviews, and scholarly articles that expounded on the applications, benefits, challenges, and future directions of employing AI-driven chatbots for drug delivery [6]. Publications that were not available in English or lacked relevance to a specified topic were excluded from the review.

Data extraction and synthesis

The selected literature was critically analyzed using key findings, methodologies, and insights synthesized to present a cohesive narrative regarding the transformative role of ChatGPT in revolutionizing drug delivery innovation.

RESULTS

The power of ChatGPT in drug delivery

ChatGPT is a state-of-the-art AI model that is renowned for its natural language understanding and generation capabilities. Although its application in various domains is well documented, its potential in drug delivery is a recent exciting development [7]. Here, we comprehensively examined how ChatGPT enhances the efficiency of drug delivery [8].

The ChatGPT can autonomously review vast volumes of scientific literature, extract pertinent information on drug delivery technologies, and generate concise summaries. This expedites the initial research phase and saves considerable time and resources [9].

Formulation optimization

The development of drug delivery systems involves intricate formulations. ChatGPT can propose optimized drug formulations based on existing data and research, shortening the formulation development process and reducing experimentation time. Factors such as drug solubility, stability, and release kinetics can even be considered when recommending tailored formulations [10].

Predictive modeling

Leveraging machine learning algorithms, ChatGPT can predict the potential efficacy and safety of various drug delivery approaches. This assists in the prioritization of promising candidates for further in vitro and in vivo testing, resulting in more targeted research. By analyzing data from previous studies and clinical trials, ChatGPT can offer valuable insights into the likely success of specific delivery methods.

Regulatory compliance

ChatGPT can provide guidance on the regulatory requirements and documentation necessary for drug delivery system approval. This ensures that the research remains compliant with rigorous regulatory standards, reducing the risk of setbacks in the development process. ChatGPT can also help to generate comprehensive submission documents and simplify interactions with regulatory agencies.

Patient-centric approach

In final stages of drug development, ChatGPT can generate patient-friendly educational materials, simplify complex drug delivery concepts, and enhance patient compliance and understanding [11]. Tailoring information to patients' language preferences and health literacy levels facilitates informed decision-making and adherence to treatment plans.

Prediction of drug-drug interactions: Drug-drug interactions (DDIs) pose significant risks to the health and well-being of patients. Individuals concurrently using multiple medications may face a heightened likelihood of encountering adverse effects or drug toxicity when unaware of the potential interactions between their prescribed treatments. Frequently, patients may engage in self-medication practices, oblivious to potential DDIs. One study aimed to assess the utility of ChatGPT, a sophisticated language model, in predicting and explaining common drug-drug interactions (DDIs), which can significantly impact patient health. Patients taking multiple medications may unknowingly expose themselves to risks if they are unaware of potential interactions between their drugs. To investigate this, 40 DDI scenarios were compiled from the existing literature. Two-stage questions were posed to ChatGPT: the first inquiring, "can I take X and Y together?" and the second, "why should I not take X and Y together?" Responses were reviewed by two pharmacologists, leading to categorization as "correct" or "incorrect," with "correct" further subdivided into "conclusive" and "inconclusive." The text was also assessed for readability using Flesch reading ease scores and educational grade levels. Results revealed that one answer was incorrect in the first question, and for the second question, one answer was also incorrect. Among the correct responses, 19 were conclusive and 20 were inconclusive for the first question, whereas 17 were conclusive and 22 were inconclusive. Reading ease scores showed a minor difference between questions, and both exceeded the hypothetical 6th-grade reading level. In conclusion, ChatGPT shows promise as a tool for DDI prediction and explanation, potentially aiding patients who lack immediate access to health care information. However, improvements are needed to ensure more comprehensive guidance for patients seeking insights into DDIs [12].

Table 1 outlines the impact of ChatGPT integration on different phases of drug development timelines, including preclinical research, clinical trials, and regulatory approval, demonstrating overall time savings.

Table 1: Impact on Drug Development Timelines

Drug development phase Traditional timeline (months) ChatGPT-integrated timeline (months) Time savings (%) Ref
Preclinical research 12 8 33.3% [13]
Clinical trials 24 18 25% [14]
Regulatory approval 9 6.75 25% [15]
Overall 45 32.75 27.8%

Controllable calculations using ChatGPT

ChatGPT has exhibited the capability of performing calculations while maintaining a conversational context. For drug delivery researchers, this opens the door to on-demand calculations for various purposes [16].

Drug dosage calculations: Researchers can leverage ChatGPT to compute precise drug dosages tailored to individual patients, factoring in variables such as patient weight, age, and medical history, thereby ensuring personalized and effective treatment plans.

Formulation optimization: ChatGPT can be employed for real-time discussions of formulation parameters, with the ability to perform calculations that optimize drug formulations for specific delivery methods. This capability accelerates the formulation development process.

Pharmacokinetic modeling: ChatGPT can generate pharmacokinetic models and simulate drug behavior in the body, aiding in the prediction of absorption, distribution, metabolism, and excretion (ADME) properties. Such simulations inform decision-making in drug delivery research [17].

Dissolution Profiling: Researchers can request ChatGPT to calculate the dissolution profiles of different drug formulations, facilitating the selection of optimal formulations for further experimental testing [18].

ChatGPT's role in research ideas and literature simplification

In addition to its quantitative capabilities, the ChatGPT can predict and provide ideas for future research. It can analyze existing data, recommend research methodologies, and suggest novel approaches based on available information.

ChatGPT also simplifies the complex landscape of scientific literature. While the literature remains an indispensable resource, ChatGPT serves as a valuable tool for extracting, summarizing, and simplifying the information found in research papers and journals. When faced with intricate data or terminology, ChatGPT can break down complex concepts into more digestible forms, thereby enhancing comprehension.

Case studies: ChatGPT in action

To illustrate the real-world impact of ChatGPT in drug delivery, we present two compelling case studies [19].

Optimizing oral drug delivery

Researchers have harnessed ChatGPT to analyze the extensive literature on oral drug delivery methods. Utilizing the formulation optimization capabilities of ChatGPT, they designed an innovative oral drug delivery system. This approach significantly reduces research time and resources, leading to promising breakthroughs in drug delivery [20–22]. Furthermore, ChatGPT identified potential compatibility issues between drugs and excipients, allowing researchers to proactively address these concerns [23].

Accelerating regulatory approval

A pharmaceutical company employs ChatGPT to navigate the complex landscape of regulatory compliance for their drug delivery system. ChatGPT generates detailed regulatory documentation, facilitating a smoother approval process and expediting the path to the market. By incorporating ChatGPT's expertise, the company gained a competitive edge by launching its products ahead of schedule [24].

DISCUSSION

Hypothetical scenario

Suppose you are conducting drug formulation research, and we will break down the research phases, as shown in table 2.

Table 2: Estimated time reductions in drug formulation research phases with ChatGPT integration

Research phase Traditional time (weeks/mo) Estimated reduction with ChatGPT (%) Estimated time reduction (weeks/mo) References
Literature Review 8 w 70% 5 w [2]
Data extraction 4 w 90% 3.6 w
Model development 6 mo 40% 2.4 mo
Optimization 3 mo 30% 0.9 mo
Validation 3 mo 35% 1.05 mo
Regulatory approval 3 mo 25% 0.75 mo
Overall 18 mo 8.4 mo

Quantitative predictions with ChatGPT

Now, let us estimate the potential time reduction for each phase by integrating ChatGPT:

Table 3 shows a direct comparison between the time required for each research phase in traditional methods and when assisted by ChatGPT. This demonstrates the percentage improvement in efficiency across these phases.

Table 3: Comparative analysis of research phases

Research phase Traditional time (weeks/months) ChatGPT-assisted time (weeks/months) Efficiency improvement (%) References
Literature review 8 w 3 w 62.5% [25]
Data extraction 4 w 1 w 75%
Model development 6 mo 3.5 mo 41.7%
Optimization 3 mo 2 mo 33.3%
Validation 3 mo 1.5 mo 50%
Regulatory approval 3 mo 2.25 mo 25%
Overall 18 mo 11.25 mo 37.5%

Overall time reduction

By adding up the time reduction estimates for each phase, the integration of ChatGPT can potentially reduce the overall project timeline from 18 mo (traditional) to 8.4 mo.

This quantitative prediction provides a more detailed breakdown of the time savings at each research phase, showcasing the potential impact of ChatGPT in streamlining the drug formulation research process. Remember to adjust these estimates according to the specific characteristics of your research and the ChatGPT's capabilities.

Table 4: User experience metrics

Metrics User satisfaction rate (%) Ease of use (Rating out of 5) Feedback summary References
ChatGPT-Assisted Research Users 90% 4.5 Positive feedback regarding time-saving and accuracy [26]
Traditional Methods Users 65% 3.2 Mixed feedback on efficiency improvements

Table 4 compares user experience metrics from researchers utilizing ChatGPT-assisted methods with those using traditional research approaches. It highlights user satisfaction rates, ease of use, and a brief summary of feedback.

As a future direction and application, the integration of ChatGPT into drug delivery research not only transforms current methodologies but also paves the way for future innovations and advancements. Their potential applications in ongoing and forthcoming research initiatives hold promising avenues for the pharmaceutical industry [27]. Enhanced Drug Targeting and Delivery Systems: As research progresses, ChatGPT could play an instrumental role in refining drug targeting strategies and developing more precise delivery systems. By leveraging its predictive modeling capabilities, ChatGPT can contribute to the development of targeted therapies, ensuring that drugs reach specific cells or tissues with heightened accuracy. Precise targeting can minimize off-target effects and optimize therapeutic outcomes. Personalized Medicine and Patient-Centric Approaches: Future applications of ChatGPT in personalized medicine hold immense promise. Its ability to assimilate vast amounts of patient data and clinical insights can contribute to tailoring treatment for individual patients. By analyzing patient-specific factors, such as genetics, lifestyle, and medical history, ChatGPT can aid in the creation of personalized medication regimens, optimizing efficacy while minimizing adverse effects [28]. Accelerated Drug Development and Iterative Research: ChatGPT can catalyze iterative research methodologies in drug development [29-31]. Its capacity to rapidly shift through existing data, propose formulations, and predict outcomes expedites R and D cycles. This acceleration could lead to shorter development timelines, cost savings, and increased efficiency in bringing novel therapies to the market. Augmented Collaboration and Multidisciplinary Research: ChatGPT's role extends beyond individual research projects; it holds promise in fostering collaborative endeavors and multidisciplinary approaches. As a communication and idea-generation tool, ChatGPT can facilitate seamless collaboration among researchers, scientists, clinicians, and regulatory experts across geographies. Their ability to synthesize and simplify complex information fosters cross-disciplinary dialogue, leading to innovative breakthroughs [11]. Integration with Advanced Technologies: Integrating ChatGPT with emerging technologies such as virtual reality (VR) and augmented reality (AR) could revolutionize drug delivery research [32]. By providing immersive experiences and interactive simulations, researchers can visualize drug interactions, formulations, and delivery mechanisms in virtual environments, thereby facilitating deeper insights and refining of experimental methodologies [22]. Ethical Considerations and Regulation: As ChatGPT becomes more embedded in pharmaceutical research, ethical considerations and regulatory frameworks become imperative. Ensuring data privacy, maintaining ethical research practices, and adhering to regulatory standards are essential aspects that require ongoing attention and refinement.

CONCLUSION

AI-driven chatbots, such as ChatGPT, are poised to revolutionize drug delivery research and innovation. By expediting the literature review, formulation optimization, predictive modeling, regulatory compliance, and patient education, ChatGPT offers a multifaceted approach to enhance efficiency throughout the drug development pipeline. As we continue to witness AI's transformative potential of AI in pharmaceuticals, embracing tools such as ChatGPT has become essential in ensuring timely and effective drug delivery solutions for patients worldwide.

ABBREVIATION

AI: Artificial intelligence, DDIs: Drug-Drug interactions, VR: Virtual reality, AR: Augmented reality

FUNDING

No applicable funding was received.

AUTHORS CONTRIBUTIONS

Ruba Malkawi: Sole authorship. Conceived the article topic, conducted the research, wrote the manuscript, and compiled the reference list. Provided expertise in pharmaceuticals, drug delivery, and AI integration in the pharmaceutical industry.

CONFLICT OF INTERESTS

There is no conflict of interest.

REFERENCES

  1. Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, Lee G. Applications of machine learning in drug discovery and development. Nat Rev Drug Discov. 2019 Apr;18(6):463-77. doi: 10.1038/s41573-019-0024-5, PMID 30976107.

  2. Zhao A, Wu Y. Future implications of ChatGPT in the pharmaceutical industry: drug discovery and development. Front Pharmacol. 2023 Jul;14(5):1194216. doi: 10.3389/fphar.2023.1194216, PMID 37529703.

  3. Al-Malah Ki. Optimization of drug solubility using aspen plus: acetylsalicylic acid (aspirin) solubility-a second case study. Asian J Pharm Clin Res. 2020 Apr;13(4):178-84. doi: 10.22159/ajpcr.2020.v13i4.37143.

  4. Azodi CB, Tang J, Shiu SH. Opening the black box: interpretable machine learning for geneticists. Trends Genet. 2020 Jun;36(6):442-55. doi: 10.1016/j.tig.2020.03.005, PMID 32396837.

  5. Maru AD, Lahoti SR. Formulation and evaluation of ointment containing sunflower wax. Asian J Pharm Clin Res. 2019 Aug;12(8):115-20.

  6. Mak KK, Pichika MR. Artificial intelligence in drug development: present status and future prospects. Drug Discov Today. 2019 Mar;24(3):773-80. doi: 10.1016/j.drudis.2018.11.014, PMID 30472429.

  7. Zhavoronkov A, Mamoshina P, Vanhaelen Q, Scheibye Knudsen M, Moskalev A, Aliper A. Artificial intelligence for aging and longevity research: recent advances and perspectives. Ageing Res Rev. 2019 Jan;49(2):49-66. doi: 10.1016/j.arr.2018.11.003, PMID 30472217.

  8. Davies NM. Adapting artificial intelligence into the evolution of pharmaceutical sciences and publishing: technological Darwinism. J Pharm Pharm Sci. 2023 Mar;26(3):11349. doi: 10.3389/jpps.2023.11349, PMID 37034476.

  9. Heck TG. What artificial intelligence knows about 70 kDa heat shock proteins, and how we will face this ChatGPT era. Cell Stress Chaperones. 2023 May;28(3):225-9. doi: 10.1007/s12192-023-01340-1, PMID 37058213.

  10. AL-Malah KI. Optimization of drug solubility using aspen plus: acetylsalicylic acid (aspirin) solubility-a second case study. Asian J Pharm Clin Res. 2020 Apr;13:178-84. doi: 10.22159/ajpcr.2020.v13i4.37143.

  11. Car LT, Dhinagaran DA, Kyaw BM, Kowatsch T, Joty S, Theng YL. Conversational agents in health care: a scoping review and conceptual analysis. J Med Internet Res. 2020 Aug;22(8):17-58.

  12. Juhi A, Pipil N, Santra S, Mondal S, Behera JK, Mondal H, Sr SS, Mondal S, IV JKB, Mondal H. The capability of ChatGPT in predicting and explaining common drug-drug interactions. Cureus. 2023 Mar;15(3):1-7.

  13. Huang J, Tan M. The role of ChatGPT in scientific communication: writing better scientific review articles. Am J Cancer Res. 2023 Mar;13(4):1148-54. PMID 37168339.

  14. Ruksakulpiwat S, Kumar A, Ajibade A. Using ChatGPT in medical research: current status and future directions. J Multidiscip Healthc. 2023 May;16(3):1513-20. doi: 10.2147/JMDH.S413470, PMID 37274428.

  15. Javaid M, Haleem A, Singh RP. ChatGPT for healthcare services: an emerging stage for an innovative perspective. Benchcounc Trans Benchmarks Stand Eval. 2023 Feb;3(1):100-5. doi: 10.1016/j.tbench.2023.100105.

  16. Musolf AM, Holzinger ER, Malley JD, Bailey Wilson JE. What makes a good prediction? Feature importance and beginning to open the black box of machine learning in genetics. Hum Genet. 2022 Sep;141(9):1515-28. doi: 10.1007/s00439-021-02402-z, PMID 34862561.

  17. Petch J, Di S, Nelson W. Opening the black box: the promise and limitations of explainable machine learning in cardiology. Can J Cardiol. 2022 Feb;38(2):204-13. doi: 10.1016/j.cjca.2021.09.004, PMID 34534619.

  18. Kumar D, Kumar P, Ahmed I, Singh S. Integrating artificial intelligence in disease diagnosis, treatment, and formulation development: a review. Asian J Pharm Clin Res. 2023 Nov;16(3):1-8. doi: 10.22159/ajpcr.2023.v16i11.48193.

  19. Sallam M. ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare (Basel). 2023 Mar;11(6):1-20. doi: 10.3390/healthcare11060887, PMID 36981544.

  20. Talevi A. Computer-aided drug discovery and design: recent advances and future prospects. Methods Mol Biol. 2024 May;2714(5):1-20. doi: 10.1007/978-1-0716-3441-7_1, PMID 37676590.

  21. Lavecchia A. Machine-learning approaches in drug discovery: methods and applications. Drug Discov Today. 2015 Mar;20(3):318-31. doi: 10.1016/j.drudis.2014.10.012, PMID 25448759.

  22. Paul D, Sanap G, Shenoy S, Kalyane D, Kalia K, Tekade RK. Artificial intelligence in drug discovery and development. Drug Discov Today. 2021 Jan;26(1):80-93. doi: 10.1016/j.drudis.2020.10.010, PMID 33099022.

  23. Yang F, Darsey JA, Ghosh A, Li HY, Yang MQ, Wang S. Artificial intelligence and cancer drug development. Recent Pat Anticancer Drug Discov. 2022;17(1):2-8. doi: 10.2174/1574892816666210728123758, PMID 34323201.

  24. Sharma G, Thakur A. ChatGPT in drug discovery. Theor Comp Chem. 2023 Jan;2(10):1-10.

  25. Ahmed I, Kajol M, Hasan U, Datta PP. ChatGPT vs. bard: a comparative study. Tech RXIV. 2023 Jul;3(8):1-10.

  26. Menon D, Shilpa K. Chatting with ChatGPT’: analyzing the factors influencing users’ intention to use the open AI’s ChatGPT using the UTAUT model. Heliyon. 2023 Nov;9(11):e20962. doi: 10.1016/j.heliyon.2023.e20962, PMID 37928033.

  27. Sarker A, Klein AZ, Mee J, Harik P, Gonzalez Hernandez G. An interpretable natural language processing system for written medical examination assessment. J Biomed Inform. 2019 Oct;98(4):103268. doi: 10.1016/j.jbi.2019.103268, PMID 31421211.

  28. Roukos DH. Systems medicine: a real approach for future personalized oncology? Pharmacogenomics. 2010 Mar;11(3):283-7. doi: 10.2217/pgs.10.36, PMID 20235782.

  29. Xu R, Li L, Wang QQ. dRiskKB: a large-scale disease-disease risk relationship knowledge base constructed from biomedical text. BMC Bioinform. 2014 Apr;15(1):105. doi: 10.1186/1471-2105-15-105, PMID 24725842.

  30. Herland M, Khoshgoftaar TM, Wald R. A review of data mining using big data in health informatics. J Big Data. 2014 Dec;1(1):1-35.

  31. Wu WT, Li YJ, Feng AZ, Li L, Huang T, Xu AD. Data mining in clinical big data: the frequently used databases, steps, and methodological models. Mil Med Res. 2021 Dec;8(1):44. doi: 10.1186/s40779-021-00338-z, PMID 34380547.

  32. Hassanzadeh P, Atyabi F, Dinarvand R. The significance of artificial intelligence in drug delivery system design. Adv Drug Deliv Rev. 2019 Nov;151-152(5):169-90. doi: 10.1016/j.addr.2019.05.001, PMID 31071378.