Background: Deep Learning Language Models (LLMs) show significant potential in analyzing complex data, particularly in oncology, where they can predict and stratify patient risks, detect non-linear interactions, and weigh multiple variables. This study applies LLMs to stage II/III localized colon cancer patients to assess their effectiveness in identifying risk subgroups. Methods: In this retrospective study, we examined a cohort of stage II and III localized colorectal cancer patients diagnosed from September 2016 to December 2022 at La Paz University Hospital. Utilizing the GPT-4 API beta version, patients were stratified into high and low-risk groups for relapse based on various risk parameters outlined in the table. Notably, adjuvant treatment data was excluded from the input. The model was prompted with the question, "Given the following risk parameters for localized colorectal cancer {param}, guess whether the patient is in low risk or high risk for relapse," and the model provided dichotomic responses categorized as either 1 (high risk) or 0 (low risk). Results: Patient characteristics are depicted in the table. During a median follow-up of 23.68 months, 63 recurrence events and 73 deaths were observed. The GPT-4 model stratified patients into low (37.9%) and high-risk (62.1%) groups, with the survival curves showing a significant difference in outcomes between the groups. Low-risk patients had a relapse-free rate of 93% at 36 months vs 63% in the high-risk group. In univariate analysis, the high-risk variable had a hazard ratio (HR) of 4.26 (95% CI: 2.03-8.95; p < 0.005). When stratified by adjuvant treatment, no significant difference in relapse probability was observed for those receiving therapy. However, without adjuvant therapy, high-risk patients had an HR of 12.41 (95% CI: 3.72-41.97; p < 0.005) for relapse. Conclusions: GPT-4 demonstrated its potential in predicting oncology outcomes by accurately understanding colorectal cancer risk factors. To fully harness the benefits of LLMs in the future of oncology, they must be fine-tuned on extensive oncological datasets to improve patient risk stratification and treatment selection, ultimately leading to better patient outcomes.