Reverse design of Mg-Zn-Mn-Sr-Ca alloys for biodegradable implants by interpretable machine learning and genetic algorithm

• A reverse design approach was employed for biodegradable Mg-Zn-Mn-Sr-Ca alloy. • Interpretable machine learning and multi-objective genetic algorithm were employed. • Four of six optimized alloys met strength and degradation criteria experimentally. • The results support data-driven design of biodegradable Mg alloys for implants. Biodegradable Mg alloys for implants must meet both mechanical strength and biologically compatible degradation rate to promote bone healing. The present study proposes a reverse engineering approach that utilizes interpretable machine learning and a multi-objective genetic algorithm to design biodegradable Mg-Zn-Mn-Sr-Ca (ZMJX) alloys for load-bearing orthopedic implants. The training of neural networks was facilitated by a dataset comprising 1044 data points, which contained chemical compositions, ultimate compressive strengths (UCS), and in vitro degradation rates (DR). The optimized neural network models predicted UCS and DR with a coefficient of determination exceeding 0.92 on testing data. Shapley additive explanations identified Zn as the most influential element affecting both UCS and DR. A total of six optimal alloys were identified from the Pareto front of two fitness functions (UCS ≥ 240 MPa, DR ≤ 1 mm/y). Four of these alloys satisfied the conflicting dual target criteria, although notable performance discrepancies were observed between reverse design and experimental results. The findings emphasize the necessity to incorporate microstructural and textural characteristics into existing databases, thereby enhancing model accuracy and enabling more reliable, data-driven design of biodegradable Mg alloys for load-bearing implant applications.