Efficient Compressive Strength Prediction of Alkali-Activated Waste Materials Using Machine Learning.

This study explores the integration of machine learning (ML) techniques to predict and optimize the compressive strength of alkali-activated materials (AAMs) sourced from four industrial waste streams: blast furnace slag, fly ash, reducing slag, and waste glass. Aimed at mitigating the labor-intensive trial-and-error method in AAM formulation, ML models can predict the compressive strength and then streamline the mixture compositions. By leveraging a dataset of only 42 samples, the Random Forest (RF) model underwent fivefold cross-validation to ensure reliability. Despite challenges posed by the limited datasets, meticulous data processing steps facilitated the identification of pivotal features that influence compressive strength. Substantial enhancement in predicting compressive strength was achieved with the RF model, improving the model accuracy from 0.05 to 0.62. Experimental validation further confirmed the ML model's efficacy, as the formulations ultimately achieved the desired strength threshold, with a significant 59.65% improvement over the initial experiments. Additionally, the fact that the recommended formulations using ML methods only required about 5 min underscores the transformative potential of ML in reshaping AAM design paradigms and expediting the development process.

Engineering a biomimetic bone scaffold that can regulate redox homeostasis and promote osteogenesis to repair large bone defects.

The reconstruction of a large bone defect to an extent that exceeds its self-healing capacity has been a great clinical challenge. In pursuit of this goal, a biomaterial-based scaffold that comprises radially aligned mineralized collagen (RA-MC) fibers that incorporate nanosilicon (RA-MC/nSi), is proposed. The chemical composition of the MC fibers is similar to that of natural bone matrices. The therapeutic efficacy of the RA-MC/nSi scaffold is evaluated in a mouse model with an experimentally created large calvarial defect. In vitro and in vivo results reveal that the RA-MC fibers of the scaffold guide the directional infiltration and migration of reparative cells from the host tissue toward the center of the defect, suggesting a potential application in promoting osteoconductivity. The incorporated nSi renders the scaffold able sustainably to release gaseous hydrogen and water-soluble silicic acid during the healing process. The released hydrogen gas can effectively regulate redox homeostasis and mitigate excessive inflammation, and the silicic acid can promote the proliferation of reparative cells and enhance their osteogenic differentiation, indicative of osteoinductivity. These findings support the use of the as-proposed biomimetic RA-MC/nSi scaffold as a promising bone substitute to enhance the regeneration of large bone defects.