The Future of Artificial Intelligence in Pharmaceutical Product Formulation

Conventional approach of formulating a new dosage form is a comprehensive task and uses various sources like man, money, time and experimental efforts. The use of AI can help to obtain optimized pharmaceutical formulation with desired (best) attributes. AI minimizes the use of resources and increases the understanding of impact, of independent variable over desired dependent responses/variables. Thus, the aim of present work is to explore the use of Artificial intelligence in designing pharmaceutical products as well as the manufacturing process to get the pharmaceutical product of desired attributes with ease. The review is presenting various aspects of Artificial intelligence like Quality by Design (QbD) & Design of Experiment (DoE) to confirm the quality profile of drug product, reduce interactions among the input variables for the optimization, modelization and various simulation tools used in pharmaceutical manufacturing (scale up and production). Hence, the use of QbD approach in Artificial intelligence is not only useful in understanding the products or process but also helps in building an excellent and economical pharmaceutical product.

[1]  John Fox,et al.  Artificial intelligence-enabled healthcare delivery , 2018, Journal of the Royal Society of Medicine.

[2]  S. Katz,et al.  Some problems in particle technology: A statistical mechanical formulation , 1964 .

[3]  Steven J. M. Jones,et al.  Modern drug design: the implication of using artificial neuronal networks and multiple molecular dynamic simulations , 2017, Journal of Computer-Aided Molecular Design.

[4]  Ola Engkvist,et al.  On the Integration of In Silico Drug Design Methods for Drug Repurposing , 2017, Front. Pharmacol..

[5]  Benjamin J. Glasser,et al.  Discrete element simulation of free flowing grains in a four‐bladed mixer , 2009 .

[6]  Buket Aksu,et al.  Towards a European strategy for medicines research (2014-2020): The EUFEPS position paper on Horizon 2020. , 2012, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[7]  Hossein Hosseinkhani,et al.  3D in vitro technology for drug discovery. , 2012, Current drug safety.

[8]  W. Pan,et al.  Formulation Optimization Technique Based on Artificial Neural Network in Salbutamol Sulfate Osmotic Pump Tablets , 2000, Drug development and industrial pharmacy.

[9]  Lalit Singh and Vijay Sharma.  Quality by Design (QbD) Approach in Pharmaceuticals: Status, Challenges and Next Steps , 2014 .

[10]  Buket Aksu,et al.  Quality by design approach for tablet formulations containing spray coated ramipril by using artificial intelligence techniques , 2012 .

[11]  Michael M. Leane,et al.  The use of artificial neural networks for the selection of the most appropriate formulation and processing variables in order to predict the in vitro dissolution of sustained release minitablets , 2003, AAPS PharmSciTech.

[12]  Fatemeh Atyabi,et al.  Transferrin-conjugated magnetic dextran-spermine nanoparticles for targeted drug transport across blood-brain barrier. , 2017, Journal of biomedical materials research. Part A.

[13]  Pierantonio Facco,et al.  Latent variable modeling to assist the implementation of Quality-by-Design paradigms in pharmaceutical development and manufacturing: a review. , 2013, International journal of pharmaceutics.

[14]  Bharat Kumar Shukla,et al.  Artificial intelligence in clinical research , 2016 .

[15]  B. Aksu,et al.  Development and comparative evaluation of extended release indomethacin capsules , 2013 .

[16]  Esher ÖZÇELİK,et al.  Quetiapine Fumarate Extended-release Tablet Formulation Design Using Artificial Neural Networks , 2017, Turkish journal of pharmaceutical sciences.

[17]  Buket Aksu,et al.  A quality by design approach using artificial intelligence techniques to control the critical quality attributes of ramipril tablets manufactured by wet granulation , 2013, Pharmaceutical development and technology.

[18]  Hossein Hosseinkhani,et al.  Polymeric nanoparticles for therapy and imaging , 2014 .

[19]  T. B. Anderson,et al.  Fluid Mechanical Description of Fluidized Beds. Equations of Motion , 1967 .

[20]  Mohammad Ali Shokrgozar,et al.  Silk fibroin nanoparticle as a novel drug delivery system. , 2015, Journal of controlled release : official journal of the Controlled Release Society.

[21]  Mohammad Ramezani,et al.  Folate receptor-targeted multimodal polymersomes for delivery of quantum dots and doxorubicin to breast adenocarcinoma: In vitro and in vivo evaluation. , 2016, International journal of pharmaceutics.

[22]  M. Hadžiabdić,et al.  A robust near-wall elliptic-relaxation eddy-viscosity turbulence model for CFD , 2004 .

[23]  P. York,et al.  Quality by Design Approach: Application of Artificial Intelligence Techniques of Tablets Manufactured by Direct Compression , 2012, AAPS PharmSciTech.

[24]  Lawrence X. Yu.  Pharmaceutical Quality by Design: Product and Process Development, Understanding, and Control , 2008, Pharmaceutical Research.

[25]  Buket Aksu,et al.  Optimisation of Ondansetron Orally Disintegrating Tablets Using Artificial Neural Networks , 2014 .

[26]  Hossein Hosseinkhani,et al.  Overview on natural hydrophilic polysaccharide polymers in drug delivery , 2018, Polymers for Advanced Technologies.