Patient-individual 3D-printing of drugs within a machine-learning-assisted closed-loop medication management – Design and first results of a feasibility study
Related Research units
Abstract
3D-printing of medicines is an innovative manufacturing method that is characterised by a high degree of digitalisation and automation and enables patient-specific care. Its integration into routine healthcare processes currently fails mainly due to the requirements of a digital environment. Our hospital was the first hospital in Europe to introduce a fully comprehensive patient record in 2011 and to digitalise and automate the drug supply process.
The aim of our study is to evaluate the integration of a machine-learning assisted 3D printing of medicines into the already existing, fully digital medication process of the hospital (closed-loop medication management, CLMM). Here, the design of this feasibility study and first results of subprojects are presented.
First, a suitable and clinically relevant active ingredient (levodopa/carbidopa) was identified in a multi-step approach by an interdisciplinary panel of experts using defined evaluation criteria, taking into account galenic, clinical and machine learning aspects. In the next step, a galenic formulation using a suitable printing technology for manufacturing a drug according to pharmaceutical quality criteria in different dosages is to be developed and to be evaluated for compliance with quality criteria according to the European Pharmacopoeia. Furthermore, an IT concept was developed and adapted to the hospital's current IT infrastructure. Likewise, a machine learning algorithm is to be developed to determine the optimal dose for each individual patient using data from smart wearable devices. For this purpose, a clinical trial was set up as a proof-of-principle study for the use of wearables to detect and grade clinical symptoms from Parkinson’s Disease. Finally, the process is to be connected to the digital medication process of the hospital taking into account regulatory requirements.
Thus, this interdisciplinary feasibility study will provide important insights into the possibilities of integrating patient-specific 3D printing of medicines into everyday clinical practice in the hospital.
The aim of our study is to evaluate the integration of a machine-learning assisted 3D printing of medicines into the already existing, fully digital medication process of the hospital (closed-loop medication management, CLMM). Here, the design of this feasibility study and first results of subprojects are presented.
First, a suitable and clinically relevant active ingredient (levodopa/carbidopa) was identified in a multi-step approach by an interdisciplinary panel of experts using defined evaluation criteria, taking into account galenic, clinical and machine learning aspects. In the next step, a galenic formulation using a suitable printing technology for manufacturing a drug according to pharmaceutical quality criteria in different dosages is to be developed and to be evaluated for compliance with quality criteria according to the European Pharmacopoeia. Furthermore, an IT concept was developed and adapted to the hospital's current IT infrastructure. Likewise, a machine learning algorithm is to be developed to determine the optimal dose for each individual patient using data from smart wearable devices. For this purpose, a clinical trial was set up as a proof-of-principle study for the use of wearables to detect and grade clinical symptoms from Parkinson’s Disease. Finally, the process is to be connected to the digital medication process of the hospital taking into account regulatory requirements.
Thus, this interdisciplinary feasibility study will provide important insights into the possibilities of integrating patient-specific 3D printing of medicines into everyday clinical practice in the hospital.
Bibliographical data
| Original language | English |
|---|---|
| ISSN | 2588-9141 |
| DOIs | |
| Publication status | Published - 2023 |
