Objective To explore whether transanal total mesorectal excision (taTME) specimens were more suitable for extraction through the anus or through the abdominal auxiliary incision, as well as to analyze the related influencing factors and construct a prediction model. Methods A retrospective cohort study was conducted. Clinical data of the initial 104 cases undergoing taTME in our hospital from July 2016 to July 2021 were collected. Logistic regression analysis was performed, and receiver operating characteristic (ROC) curves were plotted. The clinical effect of the model was evaluated by the area under the curve (AUC). Results Among the 104 patients, 3 cases failed transanal extraction, 45 cases had difficult transanal extraction and 56 cases had easy transanal extraction. Univariate regression analysis showed that gender, age, BMI, tumor diameter, mesangial area, levator ani angle and neoadjuvant therapy were risk factors for difficult specimen retrieval. The results of multivariate regression analysis showed that BMI, tumor diameter, mesentery area, and levator anus angle were independent factors affecting whether the specimen could be removed through the anus. A clinical predictive model was constructed based on the multivariate analysis results. The model had an AUC of 0. 959. The sensitivity was 0. 857 and the specificity was 0. 938. Conclusions The clinical predictive model constructed by incorporating BMI, tumor diameter, mesorectal area and levator ani angle can guide the prediction of whether taTME specimens are suitable for transanal extraction.