Pilonidal sinus disease (PSD) is a suppurative inflammatory condition characterized by a sinus tract in the sacrococcygeal gluteal cleft and surrounding skin. Surgical resection is an important treatment for PSD; however, postoperative recurrence occurs in some patients, severely affecting their quality of life. Due to the lack of objective clinical indicators for predicting recurrence, developing an artificial intelligence-based prediction model is an effective approach. In this study, postoperative hematoxylin and eosin (H&E) stained pathological sections from PSD patients were used. The horizontal and vertical distance network (HoVer-Net) deep learning model for automated nuclei segmentation and classification was employed to extract nuclear features from lesion regions. These features were then integrated with multidimensional clinical characteristics to select key features. And then a machine learning classifier was incorporated to construct a recursive feature elimination-balanced random forest (RFE-BalancedRF) ensemble model to predict PSD recurrence. Experimental results demonstrate that the proposed PSD recurrence prediction model achieves an area under the curve of receiver operating characteristic (ROC_AUC) of 0.751 ± 0.048 and an accuracy (Acc) of 0.715 ± 0.066. Furthermore, a correlation exists between multimodal features and the risk of PSD recurrence, confirming the effectiveness of the proposed model in predicting PSD recurrence. This study innovatively integrates radiomics features with clinical characteristics from the dual perspectives of pathological image analysis and multimodal feature fusion to construct a PSD recurrence risk prediction model, potentially providing a new pathway with considerable clinical translation potential for artificial intelligence assisted medicine.