Supervised Learning for Predictive Pore Size Classification of Regenerated Cellulose Membranes Based on Atomic Force Microscopy Measurements.

Nanoporous dialysis membranes made of regenerated cellulose are used as molecular weight cutoff standards in bioseparations. In this study, mesoporous standards with Stokes' radii (50 kDa/2.7 nm, 100 kDa/3.4 nm and 1000 kDa/7.3 nm) and overlapping skewed distributions were characterized using AFM, with the specific aim of generating pore size classifiers for biomimetic membranes using supervised learning. Gamma transformation was used prior to conducting discriminant analysis in terms of the area under the receiver operating curve (AUC) and classification accuracy (Acc). Monte Carlo simulations were run to generate datasets (n = 10) on which logistic regression was conducted using a constant ratio of 80:20 (measurement:algorithm training), followed by algorithm validation by WEKA. The proposed algorithm can classify the 1000 kDa vs. 100 kDa (AUC > 0.8) correctly, but discrimination is weak for the 100 kDa vs. 50 kDa (AUC < 0.7), the latter being attributed to the instrument accuracy errors below 5 nm. As indicated by the results of the cross-validation study, a test size equivalent to 70% (AUCtapping = 0.8341 ± 0.0519, Acctapping = 76.8% ± 5.9%) and 80% (AUCfluid = 0.7614 ± 0.0314, Acctfluid = 76.2% ± 1.0%) of the training sets for the tapping and fluid modes are needed for correct classification, resulting in predicted reduction of scan times.

Three-Dimensional (3D) Printed Microneedles for Microencapsulated Cell Extrusion.

Cell-hydrogel based therapies offer great promise for wound healing. The specific aim of this study was to assess the viability of human hepatocellular carcinoma (HepG2) cells immobilized in atomized alginate capsules (3.5% (w/v) alginate, d = 225 µm ± 24.5 µm) post-extrusion through a three-dimensional (3D) printed methacrylate-based custom hollow microneedle assembly (circular array of 13 conical frusta) fabricated using stereolithography. With a jetting reliability of 80%, the solvent-sterilized device with a root mean square roughness of 158 nm at the extrusion nozzle tip (d = 325 µm) was operated at a flowrate of 12 mL/min. There was no significant difference between the viability of the sheared and control samples for extrusion times of 2 h (p = 0.14, α = 0.05) and 24 h (p = 0.5, α = 0.05) post-atomization. Factoring the increase in extrusion yield from 21.2% to 56.4% attributed to hydrogel bioerosion quantifiable by a loss in resilience from 5470 (J/m³) to 3250 (J/m³), there was no significant difference in percentage relative payload (p = 0.2628, α = 0.05) when extrusion occurred 24 h (12.2 ± 4.9%) when compared to 2 h (9.9 ± 2.8%) post-atomization. Results from this paper highlight the feasibility of encapsulated cell extrusion, specifically protection from shear, through a hollow microneedle assembly reported for the first time in literature.