Explainable AI for predicting crystallinity in doped hydroxyapatite: Implications for biomedical applications en en Hydroxyapatite (HAp) is a widely used bioactive material in medical applications such as bone tissue engineering, where the crystallinity plays a critical role in determining mechanical strength, bioactivity, and bioelectric behavior. The crystallinity is strongly affected by complex interactions between dopant elements and processing conditions. In this study, a public database was used to develop an explainable artificial intelligence (AI) framework to predict the crystallinity of multi-doped HAp based on compositional parameters. A public dataset comprising 37 samples with various dopants (e.g., Sr, Zn, Ag, F, and transition metals), processing temperatures, and durations was used. Three machine learning (ML) models, including XGBoost, random forest, and decision tree, were developed using all features. An explainable AI method, Shapley additive explanations (SHAP), was used to identify the most relevant features for each model. The features relevant to all models were selected (temperature, processing duration, Zn, HAp, Er, and Al). Model performance was assessed before and after feature reduction. XGBoost achieved the best performance with all features (R2 = 0.917, root mean squared error as RMSE = 6.03), while feature reduction slightly decreased its performance (R2 = 0.881, RMSE = 6.18). In contrast, RF and DT showed notable improvements after feature selection, with RF increasing from R2 = 0.814 to 0.872 and DT from R2 = 0.574 to 0.688, indicating reduced overfitting and improved generalization. Final model interpretation using SHAP revealed that processing parameters (time and temperature) dominate crystallinity prediction, followed by specific dopants such as Zn and Er. It was demonstrated that combining SHAP-based consensus feature selection with ML provides both accurate prediction and meaningful interpretation, offering valuable insights into the factors governing HAp crystallinity. 35 40 Shahla Azizi Department of Electrical and Electronic Engineering Eastern Mediterranean University, Gazimağusa, Mersin 10 Türkiye shahla.alikamar@emu.edu.tr Sintering XGBoost XAI Random forest Vol 6 No 1 Paper 4.pdf [1] E. Fiume, G. Magnaterra, A. Rahdar, E. Verné, F. Baino, Hydroxyapatite for biomedical applications: A short overview, Ceramics. 4 (2021) 542–563. https://doi.org/10.3390/ceramics4040039. ##[2] R.O. Kareem, N. Bulut, O. Kaygili, Hydroxyapatite biomaterials: a comprehensive review of their properties, structures, medical applications, and fabrication methods, J. Chem. Rev. 6 (2024) 1–26. https://doi.org/10.48309/jcr.2024.415051.1253. ##[3] Y. Jin, G. Lou, J. Zhao, F. Du, M. Jin, et al., Hydroxyapatite in medical aesthetics: Current status, advantages, and limitations, Chinese Chem. Lett. (2026) 112513. https://doi.org/10.1016/j.cclet.2026.112513. ##[4] V.G. DileepKumar, M.S. Sridhar, P. Aramwit, V.K. Krut’ko, O.N. Musskaya, et al., A review on the synthesis and properties of hydroxyapatite for biomedical applications, J. Biomater. Sci. Polym. Ed. 33 (2022) 229–261. https://doi.org/10.1080/09205063.2021.1980985. ##[5] M.S.F. Hussin, H.Z. Abdullah, M.I. Idris, M.A.A. Wahap, Extraction of natural hydroxyapatite for biomedical applications—A review, Heliyon. 8 (2022) e10356. https://doi.org/10.1016/j.heliyon.2022.e10356. ##[6] S. Balakrishnan, V.P. Padmanabhan, R. Kulandaivelu, T.S.S.N. Nellaiappan, S. Sagadevan, et al., Influence of iron doping towards the physicochemical and biological characteristics of hydroxyapatite, Ceram. Int. 47 (2021) 5061–5070. https://doi.org/10.1016/j.ceramint.2020.10.084. ##[7] A.F. Pradana, I.S. Sari, A. Federico, R.S.P. Kaban, Y. Yusuf, et al., The prediction of hydroxyapatite crystallinity under various ion doping using machine learning, Results Chem. 18 (2025) 102701. https://doi.org/10.1016/j.rechem.2025.102701. ##[8] M.L. Habib, S.A. Disha, M.S. Hossain, M.N. Uddin, S. Ahmed, Enhancement of antimicrobial properties by metals doping in nano-crystalline hydroxyapatite for efficient biomedical applications, Heliyon. 10 (2024) e23845. https://doi.org/10.1016/j.heliyon.2023.e23845. ##[9] S. Lala, M. Ghosh, P.K. Das, T. Kar, S.K. Pradhan, Mechanical preparation of nanocrystalline biocompatible single-phase Mn-doped A-type carbonated hydroxyapatite (A-cHAp): effect of Mn doping on microstructure, Dalt. Trans. 44 (2015) 20087–20097. https://doi.org/10.1039/C5DT03398E. ##[10] W. Liu, Y. Fang, H. Qiu, C. Bi, X. Huang, et al., Determinants and performance prediction on photocatalytic properties of hydroxyapatite by machine learning, Opt. Mater. 146 (2023) 114510. https://doi.org/10.1016/j.optmat.2023.114510. ##[11] Z. Liu, Y. Shi, H. Chen, T. Qin, X. Zhou, et al., Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes, NPJ Comput. Mater. 7 (2021) 142. https://doi.org/10.1038/s41524-021-00618-1. ##[12] T. Sugihartono, B. Wijaya, M. Marini, A.P. Alkayess, H.A. Anugerah, Optimizing stunting detection through SMOTE and machine learning: a comparative study of XGBoost, random forest, SVM, and k-NN, J. Appl. Data Sci. 6 (2025) 667–682. https://doi.org/10.47738/jads.v6i1.494. ##[13] L. Breiman, Random forests, Mach. Learn. 45 (2001) 5–32. https://doi.org/10.1023/A:1010933404324. ##[14] V.G. Costa, C.E. Pedreira, Recent advances in decision trees: An updated survey, Artif. Intell. Rev. 56 (2023) 4765–4800. https://doi.org/10.1007/s10462-022-10275-5. ##[15] M.M. Mundu, J.I. Sempewo, A. Goparaju, D.E. Uti, Comparative analysis of model evaluation metrics in energy systems, environmental modeling, and sustainability science, Int. J. Energy Res. 2026 (2026) 6170467. https://doi.org/10.1155/er/6170467. ##[16] G. Muralithran, S. Ramesh, The effects of sintering temperature on the properties of hydroxyapatite, Ceram. Int. 26 (2000) 221–230. https://doi.org/10.1016/S0272-8842(99)00046-2. ##[17] S. Aarthy, D. Thenmuhil, G. Dharunya, P. Manohar, Exploring the effect of sintering temperature on naturally derived hydroxyapatite for bio-medical applications, J. Mater. Sci. Mater. Med. 30 (2019) 21. https://doi.org/10.1007/s10856-019-6219-9. ##[18] J. Vivanco, J. Slane, R. Nay, A. Simpson, H.-L. Ploeg, The effect of sintering temperature on the microstructure and mechanical properties of a bioceramic bone scaffold, J. Mech. Behav. Biomed. Mater. 4 (2011) 2150–2160. https://doi.org/10.1016/j.jmbbm.2011.07.015. ##[19] M. Trzaskowska, V. Vivcharenko, A. Przekora, The impact of hydroxyapatite sintering temperature on its microstructural, mechanical, and biological properties, Int. J. Mol. Sci. 24 (2023) 5083. https://doi.org/10.3390/ijms24065083. ##[20] B.K. Mahmood, O. Kaygili, N. Bulut, S.V Dorozhkin, T. Ates, et al., Effects of strontium-erbium co-doping on the structural properties of hydroxyapatite: An Experimental and theoretical study, Ceram. Int. 46 (2020) 16354–16363. https://doi.org/10.1016/j.ceramint.2020.03.194. ##[21] M. Wang, L. Wang, C. Shi, T. Sun, Y. Zeng, Y. Zhu, The crystal structure and chemical state of aluminum-doped hydroxyapatite by experimental and first principles calculation studies, Phys. Chem. Chem. Phys. 18 (2016) 21789–21796. https://doi.org/10.1039/C6CP03230C. ##[22] N.P. Varma, A. Sinha, S.K. Gupta, J.K. Mahato, P. Chand, Enhanced defluoridation by nano-crystalline alum-doped hydroxyapatite and artificial intelligence (AI) modeling approach, Front. Environ. Sci. 12 (2024) 1363724. https://doi.org/10.3389/fenvs.2024.1363724.