|
|
- IRMS - Nicolae Testemitanu SUMPh
- 1. COLECȚIA INSTITUȚIONALĂ
- MedEspera: International Medical Congress for Students and Young Doctors
- MedEspera 2026
Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12710/33914
| Title: | THE ROLE OF ARTIFICIAL INTELLIGENCE (AI) IN SEMISOLID PHARMACEUTICAL FORMULATION |
| Authors: | Tăbîrţă, Olga Sîlnic, Tatiana Ciobanu, Cristina |
| Keywords: | Artificial intelligence (AI);semisolid dosage forms;formulation;gels;creams |
| Issue Date: | 2026 |
| Publisher: | Centrul Editorial-Poligrafic Medicina |
| Citation: | Tăbîrţă, Olga; Sîlnic, Tatiana; Ciobanu, Cristina. THE ROLE OF ARTIFICIAL INTELLIGENCE (AI) IN SEMISOLID PHARMACEUTICAL FORMULATION. In: MedEspera 2026, p. 94. ISBN 978-9975-82-486-6. |
| Abstract: | Introduction. Artificial intelligence (AI) is increasingly being integrated into pharmaceutical formulation and preformulation processes, including the development of semisolid dosage forms. Conventional formulation development is resource-intensive and requires iterative experimental cycles to optimize critical quality attributes of semisolid systems, such as rheological behavior, drug release characteristics, and stability. Al has emerged as an innovative approach to streamline these processes, enabling reduced development timelines and improved predictive accuracy. Aim of study. To review the scientific literature regarding the role of artificial intelligence in the formulation and preformulation of semisolid pharmaceutical dosage forms. Methods and materials. Scientific literature indexed in PubMed, Scopus, MEDLINE, and Embase was analyzed to evaluate the application of AI in the formulation and preformulation of semisolid pharmaceutical systems, including optimization of excipient ratios, prediction of drug-excipient interactions, and modeling of drug release profiles. Results. AI approaches have been applied to the optimization of topical diclofenac gels, where artificial neural networks were used to predict rheological parameters and drug release profiles, as well as to refine polymer concentrations (e.g., Carbopol, HPMC) and cosolvent composition. In dermatological creams containing corticosteroids (e.g., hydrocortisone), machine learning algorithms enabled the estimation of emulsion stability and transdermal permeability, establishing correlations between formulation composition and biopharmaceutical performance. Furthermore, in the development of nanoemulsions and emulgels containing poorly water-soluble active substances (e.g., curcumin), genetic algorithms and predictive modeling were employed to optimize phase ratios, reduce particle size, and enhance system stability. In mucoadhesive formulations and ophthalmic ointments, AI contributed to the prediction of mucoadhesive strength and residence time, supporting the design of systems with improved therapeutic efficacy. Conclusions. Artificial intelligence represents a valuable tool in the development of semisolid pharmaceutical dosage forms, facilitating formulation and preformulation through enhanced predictive capability and resource optimization. The integration of AI-driven methodologies into pharmaceutical practice may improve research efficiency and support the development of safer and more effective therapeutic products. |
| metadata.dc.relation.ispartof: | MedEspera 2026. The 11th International Medical Congress for Students and Young Doctors, 6-8 May 2026 |
| URI: | https://medespera.md/documents/abstract-book-4.pdf https://repository.usmf.md/handle/20.500.12710/33914 |
| ISBN: | 978-9975-82-486-6 |
| Appears in Collections: | MedEspera 2026
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|