Glioblastoma multiforme (GBM) is the most common and most lethal brain tumour in adults. One of the most aggressive forms of cancer, it has a 5-year survival rate of 5%. Although great strides have been made in the understanding of the cause of these tumours, the current survival rate, and standard of care remain largely unchanged. The biggest challenge that exists in treating these diseases is how biologically variable this disease is within a patient and even between patients. In order to have develop more targeted therapies, we need accurate markers, which assist with treatment planning and prognosis. An additional challenge is the degree of difficulty in surgically removing these tumours, which plays a crucial role in survival, as better surgical resection leads to longer survival times. Our current study aims to improve the molecular diagnosis and improve surgical accuracy using machine learning and artificial intelligence. The iKnife is a technology that can use smoke from cauterized tissue to generate a chemical profile. This approach has been validated in other forms of cancer such as cervical cancer, breast cancer, and ovarian cancer, and has tremendous promise in brain tumour therapy. By utilizing patient tumour samples to develop a machine learning model to distinguish between normal brain and GBM, we can not only improve the ability for surgeons to remove GBM but also develop markers to inform treatment plans and targeted therapy intraoperatively. Once validated in GBM, we believe this methodology is scalable and applicable to other cancers of the central nervous system, particularly those found in eloquent brain or spine regions.