Abstract: Objective: To explore the risk factors for lymph node metastasis in patients with T1 stage gastric cancer and construct a prediction model using the LASSO machine learning algorithm. Methods: A retrospective collection of clinical and pathological data of gastric cancer patients who received treatment at the First Affiliated Hospital of Bengbu Medical University from 2010 to 2017 was conducted.Patients were grouped based on lymph node metastasis results from postoperative pathological reports.The T1 stage gastric cancer patients were divided into a training set and a validation set.In the training set,the LASSO machine learning algorithm was utilized to identify independent risk factors for lymph node metastasis in T1 stage gastric cancer and construct a prediction model and a nomogram.The prediction model was validated using the validation set. Results: A total of 433 patients with T1 stage gastric cancer were included.Results of univariate logistic regression analysis showed that NLR,CEA,histological grade,tumor location,and T stage infiltration depth were significant risk factors for lymph node metastasis (P<0.05 to P<0.01).LASSO variable selection indicated that gender,NLR,HB,CEA,histological grade,tumor size,and infiltration depth were the seven factors used to construct the prediction model for lymph node metastasis in T1 stage gastric cancer.The model exhibited good predictive ability for lymph node metastasis in both the training set and validation set(AUC=0.745,0.694). Conclusions: The prediction model based on the LASSO machine learning algorithm can effectively identify lymph node metastasis in T1 stage gastric cancer,providing valuable insights for clinical diagnosis and treatment.