Disrupting 3D printing of medicines with machine learning. (September 2021)

• Record Type: Journal Article
• Authors: Elbadawi, Moe; McCoubrey, Laura E.; Gavins, Francesca K.H.; Ong, Jun J.; Goyanes, Alvaro; Gaisford, Simon; Basit, Abdul W.
• Is Part Of: Trends in pharmacological sciences. Volume 42:Number 9(2021)
• Page Start: 745
• Page End: 757
• Publication Date: 2021-09
• Subjects: additive manufacturing -- 3D Printed drug products and formulations -- Industry 4.0 and digital health -- personalized oral drug delivery systems and medical devices -- biomedical engineering and pharmaceutical sciences -- translational pharmaceutics; Pharmacology -- Periodicals; Pharmacology -- trends -- Periodicals; Pharmacologie -- Périodiques; Pharmacology; Electronic journals; Periodicals; 615.1
• DOI: 10.1016/j.tips.2021.06.002
• Languages: English
• ISSNs: 0165-6147

Abstract

Abstract : 3D printing (3DP) is a progressive technology capable of transforming pharmaceutical development. However, despite its promising advantages, its transition into clinical settings remains slow. To make the vital leap to mainstream clinical practice and improve patient care, 3DP must harness modern technologies. Machine learning (ML), an influential branch of artificial intelligence, may be a key partner for 3DP. Together, 3DP and ML can utilise intelligence based on human learning to accelerate drug product development, ensure stringent quality control (QC), and inspire innovative dosage-form design. With ML's capabilities, streamlined 3DP drug delivery could mark the next era of personalised medicine. This review details how ML can be applied to elevate the 3DP of pharmaceuticals and importantly, how it can expedite 3DP's integration into mainstream healthcare. Highlights: 3D printing (3DP), also known as additive manufacturing, is a fabrication technology allowing the precise fabrication of personalised drug-loaded products. 3DP has achieved various successes, including the FDA-approved drug product Spritam®. However, the new technology is underutilised, with the promise of personalised and on-demand application remaining at the proof-of-concept stage. ML has the potential to save costs and streamline the 3DP process by making accurate and rapid predictions for the key process parameters and formulation characteristics of drug-loaded products. The integration of ML with 3DP, both digitalised processes, could facilitate a transition from 'one size fits all' treatments towards data-driven omics and the manufacture of personalised medicines.