Optimization of Electrospun PCL–PLGA Substrates for Lung Basement Membrane Applications Using Response Surface Methodology and Machine Learning Approaches
Golestan Salimbeigi, Halima Boutouil, Tanya Levingstone, Garrett B. McGuinness · 2026
Read Optimization of Electrospun PCL–PLGA Substrates for Lung Basement Membrane Applications Using Response Surface Methodology and Machine Learning Approaches by Golestan Salimbeigi, Halima Boutouil, Tanya Levingstone, Garrett B. McGuinness (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13448921.txt.
Description
Golestan Salimbeigi and co-authors combine in 2026 statistical design and machine learning to tune synthetic membranes that imitate the lung's basement membrane. Their electrospun mats blend two degradable polymers, PCL and PLGA, into fine fibers meant to be soft yet strong enough to flex with breathing-like motion. A response surface design first mapped how spinning settings shape fiber diameter, stiffness, strength, and stretch.
The statistical model predicted a best membrane with fibers about 0.386 micrometers wide, and bench checks landed within ten percent of every prediction. Machine learning then widened the search. A CatBoost model best recovered the polymer recipe from desired properties, while an XGBoost surrogate found a candidate mix scoring higher on combined desirability than the bench-confirmed design. The authors present the pairing as a way to shortlist spinning recipes before spending laboratory time.
Catalog record
| CREATOR | Golestan Salimbeigi, Halima Boutouil, Tanya Levingstone, Garrett B. McGuinness |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 74210 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |