Machine learning approaches to the prediction of powder flow behaviour of pharmaceutical materials from physical properties

Understanding powder flow in the pharmaceutical industry facilitates the development of robust production routes and effective manufacturing processes. In pharmaceutical manufacturing, machine learning (ML) models have the potential to enable rapid decision-making and minimise the time and material required to develop robust processes. This work focused on using ML models to predict the powder flow behaviour for routine, widely available pharmaceutical materials. A library of 112 pharmaceutical powders comprising a range of particle size and shape distributions, bulk densities, and flow function coefficients was developed. ML models to predict flow properties were trained on the physical properties of the pharmaceutical powders (size, shape, and bulk density) and assessed.

The data were sampled using 10-fold cross-validation to evaluate the performance of the models with additional experimental data used to validate the model performance with the best performing models achieving a performance of over 80%. Important variables were analysed using SHAP values and found to include particle size distribution D10, D50, and aspect ratio D10. The very promising results presented here could pave the way toward a rapid digital screening tool that can reduce pharmaceutical manufacturing costs.

Tabelle 1 „Materials included in the training data set”

Material	Supplier	Material	Supplier
4-Aminobenzoic acid	Sigma-Aldrich	Ibuprofen 70	Sigma-Aldrich
Ac-Di-Sol	DuPont	Lactose	Sigma-Aldrich
Acetazolamide	Sigma-Aldrich	Lidocaine	Sigma-Aldrich
Affinisol	DuPont	Lubritose AN	Kerry
Aspirin	Sigma-Aldrich	Lubritose mannitol	Kerry
Avicel PH-101	DuPont	Lubritose MCC	Kerry
Avicel PH-102	DuPont	Lubritose PB	Kerry
Benecel K100M	Ashland	Lubritose SD	Kerry
Benzoic acid	Sigma-Aldrich	Magnesium stearate	Roquette
Benzydamine hydrochloride	Sigma-Aldrich	Magnesium stearate	Sigma-Aldrich
Bromhexine hydrochloride	Sigma-Aldrich	Mefenamic acid	Sigma-Aldrich
Caffeine	Sigma-Aldrich	Methocel MC2	Colorcon
Calcium carbonate	Sigma-Aldrich	Microcel MC-102	Roquette
Calcium phosphate dibasic	Sigma-Aldrich	Microcel MC-200	Roquette
Cellulose	Sigma-Aldrich	Nimesulide	Sigma-Aldrich
Croscarmellose Na	DuPont	Paracetamol granular special	Sigma-Aldrich
d-Glucose	Sigma-Aldrich	Paracetamol powder	Sigma-Aldrich
d-Mannitol	Sigma-Aldrich	Pearlitol 300DC	Roquette
d-Sorbitol	Sigma-Aldrich	Plasdone povidone	Ashland
Dropropizine	Sigma-Aldrich	Plasdone K29/32	Ashland
FastFlo 316	DuPont	Phenylephedrine	Sigma-Aldrich
FlowLac 90	Meggle Pharma	Roxithromycin	Sigma-Aldrich
Granulac 140	Meggle Pharma	S-Carboxymethyl-l-cysteine	Sigma-Aldrich
Granulac 230	Meggle Pharma	Soluplus	BASF
HPMC	Sigma-Aldrich	Span 60	Sigma-Aldrich
Ibuprofen 50	BASF	Stearic acid	Sigma-Aldrich

Download the full article as PDF here Machine learning approaches to the prediction of powder flow behaviour of pharmaceutical materials from physical properties

or read it here

Laura Pereira Diaz, Cameron J. Brown, Ebenezer Ojo, Chantal Mustoe and Alastair J. Florence, Machine learning approaches to the prediction of powder flow behaviour of pharmaceutical materials from physical properties Check for updates, Future Manufacturing Research Hub, Technology and Innovation Centre, 99 George Street, Glasgow G1 1RD, UK, Strathclyde, Institute of Pharmacy & Biomedical Sciences, University of Strathclyde, Glasgow G4 0RE, UK

---

Read more on Magnesium Stearate here