Machine learning-based fabrication of phytogenic NiO nanoparticles for anticancer activity in HepG2 Cell Culture

Metal oxide nanomaterials play a central role in biomedical applications due to their unique physicochemical properties. In particular, various treatment methods such as drug delivery, hyperthermia therapy, radiation, and chemotherapy are used for the treatment of carcinoma. Current studies prefer to investigate the anticancer activity of nickel oxide nanoparticles were synthesized using a green synthesis approach. The X-ray diffraction (XRD) analysis was used to investigate the cubic crystalline structure and crystallite size varies from 11.08 nm to 12.88 nm due to increased calcination temperature. The crystallite size has a significant impact on the cytotoxicity and toxicity of nanoparticles; smaller crystal sizes frequently result in higher toxicity, because of their larger surface area to volume ratio. The MTT (Tetrazolium salts) assay was performed to test the cytotoxicity of NiO nanoparticles (NPs) against HepG2 cell line. After that, machine learning was applied to connect the biomedical field with artificial intelligence. It can be seen from the results that the NiO NPs that were calcinated at 600 °C gave the average cell viability <40%. At last, the machine learning approach was used to calculate the cytotoxicity of NiO NPs and decision tree was generated by using Google Colab. A correlation matrix was generated using a machine learning approach, providing insights into the interdependence among all parameters.