INTRODUCTION:

Drug delivery involves the administration of pharmaceuticals in the human body for the treatment of diseases or infections. It addresses the issue of selecting the optimal route of administration of drugs in the body. Currently, several artificial intelligence tools are used worldwide in drug delivery applications, including the selection of drug candidates, optimization of drug structures, or even predicting bioactivity through de novo molecular design. AI helps reduce the time and cost of drug discovery and development. However, AI in drug delivery is still at a nascent stage due to a lack of interpretative capability. AI approaches are known to suffer from opacity and often fail to deliver, but still, there is a globally increasing interest and investment in AI tools pertaining to drug delivery. Nevertheless, there are significant challenges posed by AI in drug delivery. Despite rapidly growing areas of interest, decades of research, enormous investments and efforts, and considerable achievements, the safety and efficacy of complex drug delivery systems are still a major concern [1,2].

Worldwide interest and investment are increasing in the development of artificial intelligence toolkits that address the issue of drug delivery. First-generation tools focus on streamlining clinical drug delivery workflows by designing optimally performing drug delivery Clinical Decision Support Systems to alleviate knowledge disparity. Current second-generation tools operate on molecular biological structures using artificial neural network based “expert” systems that help rapidly pre-screen drug candidates for systemic intravenous delivery. AI is beginning to largely assist drug delivery scientists and engineers in drug delivery design frameworks that incorporate iterative AI learning for drug delivery simulations to develop fixed drug formulations and delivery for approved drugs. AI is picking up pace in drug delivery and allied areas of biomedicine and forming new research areas termed bio- innovation [3,4].

The integration of Al and big data in the field of pharmaceutics has resulted in the development of computational pharmaceutics, which attempts to improve drug delivery systems using multiscale modeling methodologies. Computational pharmaceutics analyses massive datasets and predicts medication activity using Al algorithms and machine learning approaches. Researchers can analyze alternative situations and optimize drug delivery systems by modeling drug formulation and delivery processes, eliminating the need for laborious trial-and-error studies. This shortens the medication development timetable. decreases costs while increasing production. Computational pharmaceutics is the study of drug delivery systems at many scales, from molecular interactions to macroscopic behavior. Algorithms can anticipate drug behavior at each scale by analyzing intricate correlations between drug characteristics, formulation components, and physiological parameters. This makes it possible to comprehend drug delivery mechanisms in greater detail and facilitates the creation of effective drug delivery systems. It aids in the prediction of the medication's stability, in vitro drug release profile, and physicochemical characteristics. Along with in vivo-in vitro correlation research, the same technique is also used for improved assessment of in vivo pharmacokinetic parameters and drug distribution. By applying the correct combination of Al tools, researchers can detect possible risks and obstacles related with drug delivery systems early in the development phase. This makes it possible to proactively make changes and adjustments to reduce risks and enhance the effectiveness of medications. Al and computer modeling minimize the need for costly and time-consuming trial-and-error experiments [5,6]. A number of advancements. In several research fields could be brought about by the application of artificial intelligence (AI) and machine learning (ML) in medication development. Progression in the study of prognostic and predictive biomarkers, enhanced exploration of disease mechanisms, prediction of protein structure, design of molecular compounds, identification of novel targets, and improved understanding of disease and target associations are a few of these advances. Additionally, Al and MI can contribute significantly to biometric data analysis through wearable technology, precision medicine, and the data analysis of clinical trials conducted in the pandemic era using appropriate data collection techniques and site monitoring in order to improve experimental output [7].

In this area, machine learning (ML) and deep learning (DL) are the two basic methodologies used. Target identification and validation [8], drug discovery and design [9], and preclinical drug research [10] all use ML and DL algorithms to examine various data features in various formats. Following a drug candidate’s enrollment in a clinical trial [11], DL is essential in helping to plan the trial as well as overseeing and evaluating data from the clinical phase IV [10]. The market economy and manufacturing are significantly impacted by approved medications [12], and DL can have an effect in these domains as well. Therefore, we provide a thorough summary of the majority of Al’s applications in the pharmaceutical sciences in this review. We consider ways to further speed up the development of this sector and concentrate on using Al to support target discovery and drug discovery.

In the process of developing new pharmaceutical drugs, it is crucial to recognize the limitations of AI/MI. Analysis biases may result from skewed training data or algorithmic biases, which is one such restriction. To guarantee fair and impartial outcomes, efforts must be made to identify and reduce these biases. Obtaining sufficient datasets to train Al models efficiently presents another difficulty. Generalizability and good prediction depend on having access to large and varied datasets. Researchers and institutions can work together to address this obstacle by exchanging data and working together. Other topics that need consideration include the interpretability and transparency of Al models. Understanding the logic underlying the predictions made by complex algorithms, sometimes known as “black boxes,” can be difficult. Creating means to interpret and explain Al-driven results is critical for fostering confidence and simplifying regulatory compliance [13].

FUNDAMENTALS OF AI:

AI fundamentals for medication delivery by enhanced pharmaceutical process efficiency, customization, and accuracy artificial intelligence (AI) is significantly transforming medication delivery systems

Optimization of Drug Formulations

In order to guarantee effective and reliable drug administration without sacrificing other requirements like dosage form size or wasting expensive medication, it is important to optimize drug formulations. Delivering the medication at the appropriate time, location, and concentration to provide a positive therapeutic impact is the ultimate objective.

Key aspects of formulation optimization

Determining essential parameters: Determining how formulation and process factors relate to important parameters such as patient compliance, drug stability, pharmacokinetics, and manufacturability [14].

Performing experiments: Creating studies to investigate how different aspects affect the formulation and comprehending the trade-offs between them [14].

Reduced expenses and time: Optimizing the formulation effectively by techniques like Design of Experiments (DoE) and Quality by Design (QbD)[14].

Methods of optimization

Least Square Support Vector Machine (LSSVM) with Particle Swarm Optimization (PSO): An accurate prediction model that can speed up the optimization process and minimize experimental work in determining the optimal formulations [15].

Evolutionary Operation (EVOP): A strategy for optimizing a process by making modest, controlled modifications and analyzing the effects on the output [14].

Simplex Lattice Design: A method for optimizing a mixture’s composition in which the total of its components is constant.

Computational pharmaceutics

In a variety of contexts, including pre-formulation research, formulation screening, in vivo prediction, and precision medicine, computational pharmaceutics can offer multi-scale insights into pharmaceutics by illuminating physical, chemical, mathematical, and data-driven features]. Solid dispersion formulation design has been accelerated through its use, which also includes modeling and predicting drug payload in lipid and polymeric nanocarriers. Through the combination of molecular modeling, PBPK modeling, and machine learning. Trial-and- error experiments take a lot of time, and computational pharmaceutics can help cut that down. Conventional formulation development is expensive and unpredictable. The study and creation of novel medication compositions and delivery methods could be greatly aided by it [13-16].

Advanced Delivery Systems

Targeted drug delivery systems can be revolutionized by using nanorobots, especially micro and nanorobots, which allow for the exact delivery of medication to body parts that are difficult to reach. As opposed to conventional drug delivery techniques, which depend only on systemic circulation, these robotic systems are capable of autonomous navigation [17].

Regulatory compliance and risk management

Risk management and regulatory compliance in medicine distribution are being significantly altered by artificial intelligence (Al). The applications of this technology improve efficiency, safety, and upholding to Good Manufacturing Practices (GMP). Regulatory compliance.

Algorithms examine large datasets to guarantee drug safety and adherence to legal requirements. As an example. Al is able to keep an eye on production processes in real-time, spotting deviations and contamination concerns to preserve product quality and regulatory compliance. While highlighting the need for strong regulatory frameworks to handle the issues brought on by quickly advancing Al technologies, the U.S. FDA acknowledges that Al has the potential to improve drug production processes [17].

Risk management

Al improves risk management by automating crucial steps in the creation and development of pharmaceuticals. It reduces the possibility of noncompliance by forecasting equipment failures, streamlining maintenance plans, and analyzing previous data to identify quality problems. Al tools can also improve compliance by accelerating regulatory procedures like data extraction and monitoring, which reduces the possibility of human error and increases efficiency [18].

APPLICATIONS OF AI:

Applications of AI in drug delivery has completely transformed the way we approach various fields, including healthcare. One of the areas where AI is making a significant impact is in drug delivery. By utilizing AI algorithms and technologies, researchers and pharmaceutical companies are able to optimize drug delivery systems, increase drug efficacy, reduce side effects, and improve patient outcomes.

AI in Drug Design- AI is being used in drug design to identify potential drug candidates and predict their interactions with biological targets. By analyzing vast amounts of data, AI algorithms can quickly and accurately sift through millions of chemical compounds to identify those with the highest likelihood of success as potential drugs. This significantly speeds up the drug discovery process, which traditionally takes years and billions of dollars to complete.

AI in Personalized Medicine- Personalized medicine is an approach that takes into account individual variations in genes, environment, and lifestyle for each person. AI plays a crucial role in personalized medicine by analyzing large datasets to identify biomarkers and predict the best treatment options for individual patients. In drug delivery, AI can help create personalized drug delivery systems tailored to each patient’s specific needs, ensuring maximum efficacy and minimal side effects.

AI in Drug Formulation- AI algorithms are also being used to optimize drug formulations and delivery methods. By analyzing drug properties, patient characteristics, and treatment goals, AI can suggest the most effective drug delivery system, such as nanoparticles, liposomes, or microneedles. These optimized drug formulations can improve drug solubility, stability, and bioavailability, ultimately enhancing drug delivery efficiency.

AI in Drug Delivery Monitoring- Monitoring drug delivery is crucial to ensure that patients receive the right dosage at the right time. AI technologies, such as smart sensors and wearable devices, can track drug levels in the body in real- time and adjust drug delivery accordingly. This real-time monitoring can help prevent overdosing, underdosing, and drug interactions, leading to better patient outcomes [19-21].

ARTIFICIAL INTELLIGENCE IN DRUG DELIVERY SYSTEM:

AI has the potential to improve medication delivery systems in a number of ways, including by forecasting how drugs will behave within the body, anticipating drug interactions, and improving drug formulations. Predicting drug response and analyzing vast datasets of drug behavior in the body are possible with machine learning techniques. This can help when creating drug delivery systems that are tailored to the needs of particular patient groups. The optimization of drug formulations by machine learning algorithms is one instance of AI-assisted drug delivery systems. Large datasets of drug behavior in the body can be used to train machine learning algorithms, which then predict the best possible formulation for a given drug. This may result in improved therapeutic efficacy and a reduction in the time and expense involved in formulation development. Neural network-based drug interaction prediction is another example of an AI-assisted drug delivery system. Large datasets of medication interactions can be used to train neural networks to anticipate possible interactions between various pharmaceuticals. This can help with creating drug delivery systems with fewer adverse effects and minimal drug interactions.AI-powered self - regulated medicine delivery Future developments in artificial intelligence will continue to benefit from research into the human brain. Artificial intelligence algorithms are developing at a rapid pace, yet there has been little incorporation of these systems into clinical and biological practice. The main causes of this are the requirements for contextual analysis, clinical and personal application assessment, and scientific confirmation. In this context, combining AI with human intellect can have major advantages. Using AI in pharmacovigilance and drug safety. The department of drug safety and pharmacovigilance (PV) is responsible for carrying out the procedures and scientific methods necessary to effectively reduce the risk to human health. Prioritizing patient safety while also improving public health is one of the main tenets of such studies [23]. AI’s intelligent automation skills are the main reason why integrating it with PV and medication safety offers so many benefits. Among these benefits is automated data identification. Regulation and ethical aspects to consider When implementing AI technology, a user-centric strategy is essential to guaranteeing the security and safety of the internet and its users. This is embracing a tenet that refrains from going too far. AI systems should also incorporate autonomous capabilities to efficiently manage their operations, apply updates, and handle essential changes in order to handle data responsibly.

A “data minimization” tool must be included in order to eliminate unnecessary data, while any necessary data. Drug Delivery Systems using Artificial Intelligence: A Comparison of Various Drug Delivery Systems hydrogels, cascade molecules, microspheres, liposomes, and nanoparticles. By creating novel drug carriers, forecasting drug release profiles, and maximizing drug dosages, artificial intelligence has made a substantial contribution to the optimization of drug delivery systems [24-25].

Nanoparticles

The study of matter and materials at the nanoscale is known as nanotechnology. The Latin word “Nano,” which meaning dwarf (1nm=10-9m), is the source of the word. Particulate dispersions or solid particles with a size range of 10–1000 nm are referred to as nanoparticles. A nanoparticle matrix is used to dissolve, entrap, encapsulate, or attach the medication. Among the many unique benefits that nanoparticles provide are their capacity to help stabilize medicines and proteins and their practical controlled release characteristics. It can be adjusted to achieve both active and passive targeting; it has a very high drug loading capacity and can be delivered orally, nasally, intraocularly, or parenterally. Drug delivery systems utilizing nanoparticles have been designed and optimized with AI. To optimize drug release profiles and target certain tissues, for example, machine learning techniques have been applied to predict the behavior of nanoparticles in biological systems. AI algorithms have also been utilized to create novel medication carriers that decrease toxicity and increase drug delivery effectiveness [26].

Hydrogels

Three-dimensional, hydrophilic polymeric networks called hydrogels have the capacity to absorb huge volumes of biological fluids or water. The networks consist of homopolymers or copolymers and are insoluble because they have physical crosslinks like crystallites or entanglements, or chemical crosslinks like junctions and tie-points. Since hydrogels and water have a thermodynamic compatibility, they can swell in aqueous conditions. They function as carriers in swellable and swelling-controlled release devices or as regulators of medication release in reservoir-based controlled release systems. Hydrogels are the vanguard of controlled drug delivery because they are stimuli-sensitive and environmentally aware gel systems that may adjust release in response to variations in analyte concentration, pH, temperature, ionic strength, electric field, or any of these factors. These technologies allow for the design of release to happen either via specific places [adhesive or cell receptor specific gels via tethered chains from the hydrogel surface] or inside certain bodily sections [e.g., within a set pH of the digestive tract]. Combining hydrogels with the mol” cula’ imprinting process can make them very promising materials for drug delivery systems [27].

Liposome Drug Delivery

Liposomes are defined as a structure made up of one or more lipid bilayer concentric spheres divided into compartments by aqueous buffer or water. The primary constituent of naturally occurring bilayers is phospholipid. Phosphatidylcholines [PC], phosphatidylethanolamines [PE], and phosphatidylserines [PS] are examples of these phospholipids. By anticipating liposome behavior in biological systems and creating new liposomes with increased drug delivery efficacy, artificial intelligence [AI] has been used to optimize liposome drug delivery systems. Liposomes are made up of tiny phospholipid vesicles that enclose an aqueous area with a diameter of between 0.03 and 10 µm. made up of one or more lipid bilayer concentric spheres that enclose aqueous compartments. Liposomes’ ability to transfer both lipophilic and hydrophilic molecules has led to an increasing interest in them as a drug source for drug delivery systems [28]. The beauty and pharmaceutical sectors make extensive use of liposomes as carriers for a wide range of compounds. Furthermore, the food and agriculture sectors have extensively researched the use of liposome encapsulation in the development of delivery systems that might hold onto volatile substances [such flavors, antioxidants, bioactive components, and antimicrobials] and protect their usefulness. Liposomes have the ability to trap both hydrophobic and hydrophilic compounds, prevent the entrapped combinations from breaking down, and release the entrapped at specific sites [29-33].

CURRENT STATUS OF AI IN DRUG DELIVERY SYSTEM:

AI has the ability to change medication distribution systems in a number of ways. AI can be used, for instance, to forecast drug toxicity and efficacy, find new therapeutic targets, and improve drug formulations. Personalized medicine is one exciting area of application for artificial intelligence in drug delivery systems. Genetic and demographic data from patients can be analyzed by AI systems to forecast how A given medication will have an effect on a certain patient, allowing for the creation of individualized treatments. The following are some important applications of AI in cutting-edge drug delivery systems [35].

Prediction of drug release

Drug release rates from a variety of drug delivery methods, including liposomes, nanoparticles, and microspheres, can be predicted using artificial intelligence [AI]. Drug dosages can be optimized and drug release schedules can be followed with the help of this information.

Formulation Design

In order to improve medication efficacy and lower toxicity, artificial intelligence [AI] can be utilized to optimize the composition of drug delivery systems, such as liposomes and nanoparticles. In order to create formulations that are optimal, AI algorithms can analyze data on the physicochemical qualities of medications and the features of delivery methods. Deep learning algorithms, for example, can be used to determine the ideal circumstances for drug loading and release as well as anticipate the characteristics of various formulations [36].

Personalized Drug Delivery

Pharmacological delivery systems that are customized for each patient can be created using AI. AI systems are capable of analyzing patient data, including genetics, medical history, and lifestyle choices, to create customized dosage schedules and medication formulations. AI-driven medication delivery systems, for instance, have been created to manage diabetes. These systems utilize predictive algorithms and continuous glucose monitoring to modify insulin dosage in real-time [37].

Quality Control

AI can be employed during production to keep an eye on the reliability and quality of drug delivery systems. Artificial intelligence algorithms are capable of analyzing manufacturing parameter data, including temperature, pressure, and flow rates, in order to identify and avoid quality faults. Deep learning systems, for example, have been used to analyze production-related photos of pharmaceutical tablets in order to identify flaws [38].

RECENT TRENDS IN AL:

Current Advanced in AI medications delivery could undergo a revolutionary changes as a result of artificial intelligence which can optimize medications design improve drug targeting and enhance drug release these are few current developments in Ai driven medications delivery systems

A. Drug discovery machine learning: Large datasets are analyzed using machine learning algorithms to find possible therapeutic targets, forecast drug efficacy, and enhance drug characteristics. Millions of molecules may be screened via al-powered drug discovery platforms, which significantly cuts down on the time and expense of drug development. [39].

B. Drug delivery systems based on nanoparticles: It is possible to create nanoparticles so that they deliver medications to particular human tissues or cells. In order to enhance Al is being utilized to optimize

C. the design of these nanoparticles. Drug release prediction models: Al models are able to forecast the actions of pharmaceuticals in the body and create drug delivery systems that administer the medication in a regulated way. This can aid in making sure that medications are released when they’re supposed to [40].

D. Smart drug delivery systems: Doctors can modify medicine dosages and enhance treatment regimens for specific patients by using alarmed sensors to track drug release in real-time.

E. Personalized medicine: By analyzing patient data, Al can be utilized to create customized drug distribution

plans.

Perspective on features and obstacles The field of medication research and discovery is seeing an increase in the use of artificial intelligence. With the increasing advancement of Al algorithms, which can leverage larger and more accurate datasets, researchers will be able to make faster and more informed conclusions. According to one study, Al might produce more than 50 novel treatments in ten years, saving $50 billion just in preclinical expenses. To take advantage of these prospects, numerous pharmaceutical corporations are increasingly collaborating with Al start- ups. Over $5,2 million was invested in Al for drug research. Artificial intelligence presents several issues for drug delivery systems (Al). One of these challenges has to do with the need for precise and controlled drug release

The majority of Al's uses throughout the medication RandD process have been covered in detail in this review. However, many research methods are still awaiting Al’s “optimization” at this point, as Al has not truly overthrown the established pharmaceutical system. Al is still being progressively investigated for deeper inquiry in the area of pharmacological formulations. For instance, Al technology has been employed by certain researchers to help with the investigation of how medicinal excipients interact with biomolecules [41].

The following are some of the difficulties associated with using Al in drug discovery

· lack of standardization;

· cost and technical expertise;

· interpretability and transparency;

· data privacy and regular and compliances

LIMITATIONS:

Some of the drawbacks of Al, Academic Natural Based models are their lack of interpretability, propensity for bias, and requirement for vast datasets. To guarantee the safety and effectiveness of medications, Al-based models should be utilized in conjunction with conventional experimental techniques [42]. Below are some of The restrictions that are highlighted.

A lack of openness Al models are sometimes referred to as “black boxes” because it is challenging to comprehend how the model arrives at its predictions. These models employ sophisticated algorithms. Because of this lack of transparency, it may be difficult to prove that the model is producing dependable and accurate predictions, which could make it difficult to regularly obtain permission for Al-based drug development tools. Moreover, a lack of confidence in the model’s predictions may result from the lack of transparency [43].

Limited Data Accessibility for Al models to make accurate predictions, a substantial amount of data is needed. On the other hand, in certain situations, there might not be enough information available for a specific medication or demographic, which could result in biased or less reliable conclusions. For example, establishing Al models for rare diseases may face considerable challenges due to limited data availability. Furthermore, outcomes from Ai models may be skewed if the data used to train them is not representative of the target population. Furthermore, not all data types are easily accessible, such as real-world evidence or longitudinal data, which can restrict the use of Al models. These imitations serve as a reminder of the importance of giving quality and representation serious thought [43].

Data Biases The quality of the data used to train Al models determines both its efficacy and precision. Predictions that are made as a result of incomplete data may potentially be prejudiced. A disease state’s representation in the training dataset can have a negative impact on the model’s ability to accurately forecast how effective a medicine will be for that specific activity [44]. Furthermore, if the model is insufficient, it can provide inaccurate assumptions, which could lead to poor forecasts. One of the biggest challenges in using Al models to guide healthcare decision-making is their complexity [45].

Unable to Include New Information Updating an Al model or adding new data might be difficult once it has been trained. In the context of drug development procedures, where fresh data and information are continually coming, this might be a severe restriction. For instance, an Al model could need to be updated to take into account new information when new medications are released or as more data from clinical trials is obtained. Limited capacity to take variability into account large datasets are typically used to train Al models, which may skew the results toward the average responses seen in the data. Because of this, the models might not be able to predict drug responses for people whose responses differ greatly from the normal [46].

Results Interpretation Even for Academic Natural Professionals in the area, Al models can produce outputs that are challenging to understand due to their complexity. Clinicians and researchers may find it difficult to comprehend and interpret the results if the models are unable to clearly explain how they came to their conclusions. It could occasionally be challenging to interpret the data into useful information for medication development or clinical practice. Further limiting their utility is the possibility that using Al models may call for a degree of technical expertise that not all researchers and practitioners have access to. Improved interpretability and explain ability of Al models are therefore required.

Moral Aspects Patient privacy is a big problem when employing Al technology for medication development, as is the case with any usage of Al. This is because Al models are frequently trained using sensitive health data. Data security and safety are important factors that should not be disregarded and require careful consideration. Making sure that patient data is gathered and handled in a way that upholds their rights and preserves their privacy is crucial. Another ethical issue with Al in medication development is data ownership. Patients’ information may occasionally be gathered without their express consent, and it may not always be obvious who is entitled to use or control the information [47].

Insufficient Clinical Experience Even while Al is capable of finding correlations, it’s important to understand that treatment plans for particular patients may differ in spite of these correlations. Artificial intelligence algorithms are generally based on a statistical model, which may restrict their understanding of the complex variables and the significant impacts that particular parameters can have. The intricate structure, in which different individual aspects impact treatment decisions, presents a difficulty for Al models that largely concentrate on statistical association.

ARTIFICIAL INTELLIGENCE IN POST MARKET SURVEILLANCE:

Al for after-market monitoring A medication goes through a protracted examination to further monitor and assess the drug safety once it is approved and effectively enters the market following the clinical phase. For Al applications in post- market surveillance, electronic health record (HER) mining is a crucial source of data. Structured data can streamline the pre-processing of this data. The temporal pattern-discovery algorithms, cohort and case-control approaches and self-control case series (SCCS) model are some of the existing techniques employed in HER [48].

A scalable technique for utilizing SCCS to predict longitudinal features is called convolutional SCCS. Step functions and exposures were employed by Morel et al. to get around the issue with standard SCCS models, which call for a precisely defined risk window. The method's computational speed and accuracy were significantly improved by the results, which also made it possible to apply it to the identification of adverse drug reactions (ADRs) in a patient cohort with diabetes. In addition to structured data applications, natural language processing (NLP) techniques can be applied to unstructured data from biomedical and clinical corpora for drug- drug interaction (DDI) detection and classification and ADR prediction. Based on systems biology, systems pharmacology examines how medications affect the system as a whole [49].

To test the method, they coupled pharmacovigilance statistics with systems pharmacology models. The outcomes demonstrated a notable increase in the prediction of side effects for four medications. A disease’s prognosis is an estimate of how the illness will progress and turn out in the future. It was challenging to provide correct results since, in the past, professionals typically depended on their professional experience and conventional statistical analysis to estimate clinical prognosis. Al technology has now made it possible to analyze multi-patient and multi-factor data, increasing the precision of prediction outcomes. Recurrence of the disease and patient survival are typically predicted in cancer prognoses. Enchase and associates [50].

AL IN THE PRODUCTION AND ADMINISTRATION OF DRUGS:

Advanced drug delivery systems have grown quickly in tandem with improvements in new drug development techniques, supporting clinical translation and being linked to patient compliance, safety, and efficiency. One way to conceptualize a medication delivery system is as a “cart,” or carrier, that delivers “goods,” or treatments, to the right place. The word “carrier” has become more inclusive with the development of materials, engineering, and biological technologies, encompassing nano carriers, cells, eluting devices, Nano carriers have the potential to enhance drug solubility and lessen the negative effects of traditional drug carriers as compared to conventional ones. Nano carriers have the ability to give drugs a targeting function in addition to shielding them from deterioration However, the process of preparing an appropriate Nano carrier is incredibly intricate for the treatment of diseases, a drug’s release pattern is also essential. The development of medications that are released in response to variations in the physiological signals of different types of organs, and organelles can improve medication efficacy, avoid harmful side effects brought on by non-specific off- targets, and provide accurate and safe treatment. The design of responsive drug nano carriers has taken into account a number of natural signals, such as pH, active redox species, enzymes, glucose, different ions, adenosine triphosphate (ATP), and oxygen. Drug release is influenced by the target tissue environment in addition to the material’s characteristics. Al can help with the assessment of a drug- release mode and offer suggestions for how to design drug carriers using machine learning.

CONCLUSION:

In summary, Al is helpful for new medicine RandD in every way. In addition to significantly lowering the cycle time and cost of medication RandD, it can be utilized in preclinical research, clinical trial design, post-market surveillance, drug target discovery, and the design and development of new pharmaceuticals. The RandD process for drugs based on Al still has certain limitations. However, we think that Al is becoming an essential tool in the pharmacological RandD process and that it is increasingly helping us to solve the puzzle of huge and complicated biological systems. The area of medicine could undergo a revolution if artificial intelligence is used to create innovative drug delivery methods. Al has the potential to advance medication delivery methods in the direction of tailored, focused, and adaptable treatments. Al and machine learning have proven through exploratory data analysis and pattern identification to be able to improve medicine efficacy and decrease side effects. Because they allow for predictive research with minimal animal testing and creative methods to data management, these tools have revolutionized preclinical pharmacokinetic and pharmacodynamic modeling. Al can clarify illness more clearly. In order to bring fresh vigor to this sector, more research is required in this procedure.

REFERENCES:

1. LK Vora, AD Gholap, K Jetha, RRS Thakur, HK Solanki… - Pharmaceutics, 2023 mdpi.com. Artificial intelligence in pharmaceutical technology and drug delivery design. Cited by 204

2. Kotta Kranthi Kumar. Importance and Applications of Artificial Intelligence (Metastorm Software) in Pharmaceutical Process Life-Cycle. Res. J. Pharma. Dosage Forms and Tech.2019; 11(2):116-120.

3. W Wang, Z Ye, H Gao, D Ouyang-Journal of Controlled Release, 2021-Elsevier. Computational pharmaceutics- A new paradigm of drug delivery.

4. Sidhartha Jyoti Bora, Runa Chakravorty, Payal Das Gupta. The use of Artificial Intelligence in Pharmacy. Asian Journal of Pharmacy and Technology. 2023; 13(3):229-4.

5. Lou H.. Lian B., Hageman M.J. Applications of Machine Learning in Solid Oral Dosage Form Development. J. Pharm. Sci. 2021:110:3150-3165. Doi: 10.1016/j.xphs.2021.04.013,

6. Suyash Ingale, Nikhil Shrisunder, Ganesh Gophane, Avinash Birajdar. Ascent of Artificial Intelligence (AI) in Pharmacy. International Journal of Technology. 2024; 14(1):54-8.

7. Advances in artificial intelligence for drug delivery and development: A comprehensive review Amol D. Gholap, Md Jasim Uddin, Md Faiyazuddin. Abdelwahab Omri S. Gowri, Mohammad Khalid, https://doi.org/10.1016/j.compbiomed.2024.108702

8. RNSK Kartheek, V Rama Raju, R Md. Shafi. Blue Brain – A New Subway to Artificial Intelligence and Human Machine: A Proposal. Int. J. Tech. 4(2): July-Dec. 2014; Page 287-290.

9. Riniker, Y. Wang, JL. Jenkins, G.A. Landrum Using information from historical high-throughput screens to predict active compounds J Chem Inf Model, 54 (7) (2014), pp. 1880-1891

1. S. Cruz Rivera, X. Liu, A.W. Chan, A.K. Denniston, M.J. Calvert The SPIRIT-AI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-Al extension Lancet Digit Health, 2 (10) (2020), pp. e549-6560

2. S. Steiner, J. Wolf, S. Glatzel, A. Andreou, J.M. Granda, G. Keenan, et al. Organic synthesis in a modular robotic system driven by a chemical programming language Science, 363 (6423) (2019), Article eaav2211

3. Lalitkumar K.Vora, Amol D. Gholap, Keshava Jetha , Raghu Raj Singh Thakur Hetvi K. Solanki and Vivek P. Chavda Artificial Intelligence in Pharmaceutical Technology and Drug Delivery Design. Pharmaceutics. 2023 Jul: 15(7): 1916. Published online 2023 Jul 10. Doi: 10.3390/pharmaceutics15071916

10. Pusukuri Navya. Prigarini K. Tejaswi K. Prasanti D Optimization Techniques in Designing Pharmaceutical Formulations.

11. Prasad Patil, Nripesh Kumar Nrip, Ashok Hajare, Digvijay Hajare, Mahadev K. Patil, Rajesh Kanthe, Anil T. Gaikwad. Artificial Intelligence and Tools in Pharmaceuticals: An Overview. Research Journal of Pharmacy and Technology 2023; 16(4):2075-2.

12. Sanjay S. Patel, Sparsh A. Shah. Artificial Intelligence: Comprehensive Overview and its Pharma Application. Asian Journal of Pharmacy and Technology; 12(4):337-8.

13. Debleena Paul, Gaurav Sanap. Snehal Shenoy. Dnyaneshwar Kalyane, Kiran Kalia, Rakesh K. Tekade Artificial intelligence in drug discovery and development.

14. Aakash Bairagi, Akhlesh K. Singhai, Ashish Jain. Artificial Intelligence: Future Aspects in the Pharmaceutical Industry an Overview. Asian Journal of Pharmacy and Technology. 2024; 14(3):237-6.

15. Aliper. A., Realty. B. H., Issa, N. T., Volchenboum, S. L.. Grossman, R. L., and Zhavoronkov, A. (2016). Deep Learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data. Molecular pharmaceutics. 13(7).2524-2530

16. Asane Varad Arun, Pangavhane Namrata Balasaheb, Jori Vikas Babasaheb, Jadhav Dipak Kailas, Kale Rushikesh Adinath, Nalawade Dipak Dadasaheb. Artificial Intelligence and Challenges in Ayurveda Pharmaceutics: A Review. Research Journal of Science and Technology. 2024; 16(3):237-4.

17. Lu. Z., Su, M., Zeng. L., and Liu. Z. (2018). Advances in drug repositioning using transcriptomic data. Drug discovery today, 23(1), 276-282

18. Lachman’s/lieberman’s CBSDistributors, 2013, 872,902,905. 943.

19. Shaikh Habeeba. Use of Artificial Intelligence in Drug Discovery and its Application in Drug Development. Asian Journal of Research in Chemistry. 2023; 16(1):83-0.

20. Salazar, J., Müller, R.H. and Möschwitzer, J.P., 2014. Combinative particle size reduction Technologies for the production of Drug nanocrystals. Journal of pharmaceutics, 2014.

21. Kedar Prasad Meena, J.S. Dangi, PK Samal and Manoj Kumar review on Nanoparticles Technology and Recent Advances in Novel Drug Delivery systems 2011:1 (1): 1-5.

22. Junyaprasert. V.B., Teeranachaideekul, V. and Supaperm. T., 2008. Effect of charged and non-ionic Membrane additives on Physicochemical properties and stability of niosomes. Aaps Pharm SciTech. 9(3). Pp.851-859

23. Patela J., Patelb R.. Khambholjab K., Patela N., “An overview of phytosomes as an advanced herbal drug delivery system”, 2009. Asian Journal of Pharmaceutical Sciences, 4(6):363-371

24. Sarika Anand Jadhav, Prof. Prashant Patil and Dr. Ramesh Kalkotwar Vol 5. Issue 10, 2016 wjpps.research article of NANOPARTICLES AS-PARTICULATE DRUG DELIVERY SYSTEll wjpps

25. 30.Mura, S., Pirot, F., Menconi, M., Falson, F. and Fadda, A.III., 2007. Liposomes and niosomes as Potential carriers for derma.

26. Chaturvedi, M., Kumar, M., Singhal. A. and Saifi, A., 2011. Recent development in novel drug Delivery systems of herbal Drugs. International Journal of Green Pharmacy (Medknow Publications and Media Pvt. Ltd.).

27. Verma, S., Singh, S.K., Syan, N., Mathur, P. and Valecha, V..2010. Nanoparticle vesicular stems: a Versatile tool for drug Delivery. J Chem Pharm Res. 2(2). Pp.496-509.

28. Atrooz, O.M., 2011. Effects of alkylresorcinolic lipids obtained from acetonic extract of Jordanian Wheat grains on liposome Properties. Int J BioChem, 5(5), pp.314-321.

29. Shehata, T., Ogawara, K.J., Higaki, K. and Kimura, T., 2008. Prolongation of residence time of liposome by surface modification with mixture of hydrophilic polymers. International journal of pharmaceutics, 359(1-2).pp.272-279

30. 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.

31. Poonam Joshi, Itika Guleria, Agush Dangwal, Purabi Saha. Sunil Kothari, Sapna Rawat Artificial Intelligence in Controlled Drug Delivery System 1430-1437,2022.

32. D.E. Pankevich et al. Improving and accelerating drug Development for nervous system disorders Neuron (2014)Υ.ΗΗ

33. Yun et Controlled drug delivery: historical perspective for the next generation. J. Contr. Release (2015)

34. Krikorian G., Torreele E. We Cannot Win the Access to Medicines Struggle Using the Same Thinking That Causes the Chronic Access Crisis. Health Hum. Rights. 2021:23:119-127. [PMC free article] [PubMed] [Google Scholar]

35. Chavda V.P., Vihol D., Patel A., Redwan E.III., Uversky V.N. Bioinformatics Tools for Pharmaceutical Drug Product Development. John.

36. Wiley and Sons, Ltd: Hoboken, NJ, USA: 2023. Introduction to Bioinformatics, Al, and IML for Pharmaceuticals: pp. 1-18. [Google Scholar] References (248).

37. Hachen M. Hawk Car Auch dedinicama conNat Rev Drug Day 2017,1604)381-2121 Masre 11 hung Anderson Alexander CC Estics tevotal trials tved therapeia επι ερευνed by the US fund and Drug Admin Med 2018178(1):1451.

38. Y. Li et al. In vivo delivery of BCNU from a MEMS device. To a tumor modell. Control. Release (2005

39. L. Cao et al. Design and simulation of an implantable medical drug delivery system using microelectromechanical systems technology Sensors Actuators A (2001)

40. T. NisisakoRecent advances in microfluidic production of Janus droplets and particles Curr. Opin, Colloid Interface Sci. (2016)

41. H.B. Grangeja et al. Quality by design in pharmaceutical manufacturing: a systematic review of current status, challenges and future perspectives Eur. J. Pharm. Biopharm. (2020).

42. AB Talat et al. Artificial intelligence as a smart approach to develop antimicrobial drug molecules: paradigm to combat drug-resistant infections

43. Kamal Singh Rathore, Rohit lowalekar. Nema RK, The Pharma Review, 2006: 30-32.

44. Charman WN. Chan K, Finnin BC and Charman SA. Drug Delivery: A Key Factor in Realising the Full Therapeutic Potential of Drug. Drug Development Research, 46, 316-27. 1999.6. Kopecek J. Smart and genetically engineered biomaterials and drug delivery systems. European Journal of Pharmaceutical Sciences 2003: 20:1-16.

45. Torchilin, VP. Structure and design of polymeric surfactant-based drug delivery systems, Journal of Controlled Release 2001:73:137-721JFMR2302493 Volume 5, Issue 2. March-April 2023.

Received on 29.10.2024 Revised on 15.11.2024

Accepted on 30.11.2024 Published on 11.12.2024

Available online on December 31, 2024

International Journal of Technology. 2024; 14(2):115-124.

DOI: 10.52711/2231-3915.2024.00017

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Creative Commons License.