Role of Machine Learning in Liquid Biopsy of Brain Tumours

Abstract

Liquid biopsy has multiple benefits and is used extensivelyin other fields of oncology, but its role in neuro-oncologyhas been limited so far. Multiple tumour-derived materialslike circulating tumour cells (CTCs), tumour-educatedplatelets (TEPs), cell-free DNA (cfDNA), circulating tumourDNA (ctDNA), and miRNA are studied in CSF, blood (plasma,serum) or urine. Large and complex amounts of data fromliquid biopsy can be simplified by machine learning usingvarious algorithms. By using this technique, we candiagnose brain tumours and differentiate low versus highgradeglioma and true progression frompseudo-progression. The potential of liquid biopsy in braintumours has not been extensively studied, but it has abright future in the coming years. Here, we present aliterature review on the role of machine learning in liquidbiopsy of brain tumours.