Background: Endoscopic resection has the potential to completely treat T1 colorectal cancers (CRC). However, T1 CRCs have a 10% risk of lymph node metastases (LNM), requiring colonic resection and lymph node dissection. Several high risk clinico-histopathological features are associated with LNMs and subsequently multiple risk stratification scores have been developed. In this systematic review, we analyse these scores to identify which is most accurate and clinically useful score. Method: A search of MEDLINE, Cochrane Database of Systematic Review and EMBASE for T1 CRC risk assessment scores was performed following PRISMA guidelines. Results: Of 323 studies, 22 full text and 3 abstracts met inclusion criteria. Twelve studies developed clinicopathological scores presented as nomograms or algorithms. They used an average of 4.8 (SD +/-1.72) parameters, the most utilised being tumour grade, lymphovascular invasion and tumour budding. Two studies incorporated pre-operative CT results in their risk score. Artificial intelligence (AI) machine learning models were used for 10 studies, with pathologist-dependent parameters and pathologist-independent whole slide imaging. The scores AUC ranged from 0.57 to 0.99. Only two scores were externally validated, including a nomogram with an AUC of 0.77 and an AI model with an AUC of 0.83. The generalisability of several scores is limited by the use of special histopathology tests and AI programming/equipment. Conclusion: An AI risk-assessment tool had the highest AUC of 0.99, however this algorithm is not available publicly. The nomogram developed by Oh et al(2019) which was externally validated, provided good clinical applicability, with a moderate AUC of 0.77.