Objective:To develop and validate a deep learning-based multimodal model integrating clinical and radiomic features for predicting acute kidney injury（AKI）risk after partial nephrectomy.Methods:A retrospective analysis was conducted on 416 patients who underwent partial nephrectomy at Zhongshan Hospital，Fudan University from January 2023 to January 2025. The cohort included 100 AKI patients［defined by a ≥ 25% reduction in postoperative evaluated glomerular filtration rate（eGFR）within 48 hours sustained for >24 hours］and 316 non-AKI patients（1∶3 ratio，randomly matched with 16 additional cases for redundancy）. Clinical and radiomic features were extracted from preoperative contrast-enhanced CT scans using PyRadiomics. Demographics included 259 males and 158 females，with a median age of 57（49，65）years，body mass index of（24.1 ± 3.3）kg/m2，preoperative eGFR of（88.5 ± 18.3）ml/（min·1.73 m2），postoperative eGFR（48-hour）of（76.0 ± 21.9）ml/（min·1.73 m2），Zhongshan Score（ZSscore）of 7.34 ± 2.01，and R.E.N.A.L. score of 7.50 ± 1.71. All tumors were T 1a stage. Patients were divided into training（n = 312）and test（n = 104）sets（3∶1 ratio）. A clinical model was constructed via multivariate logistic regression，while radiomic and combined（clinical + radiomic）models utilized an artificial neural network（ANN）with 1 input layer，5 hidden layers，1 output layer，and 10 5 training epochs. Model performance was evaluated by using receiver operating characteristic（ROC）curves and area under the curve（AUC），and was compared to the Martini model. Feature contributions were interpreted via SHapley Additive exPlanations（SHAP）. Results:In the test set，the results of multivariate logistic regression showed that patient’s weight，preoperative eGFR，R.E.N.A.L. score，surgical approach，and operation time were risk factors for AKI（ P < 0.05）. The AUC of the clinical feature prediction model constructed based on the above factors was 0.852（95% CI 0.775?0.929）. In the test set，the AUC of the Martini model was 0.725（95% CI 0.565?0.791）. The radiomic model，trained on 1 315 imaging features，achieved an AUC of 0.898（95% CI 0.804?0.993）with 94.2%（98/104）accuracy. The combined clinical and radiomic model，integrating 1 315 radiomic features and clinical features，demonstrated superior performance with an AUC of 0.946（95% CI 0.887?1.000）and 96.2%（100/104）accuracy，outperforming both the clinical model（ P = 0.03）and the Martini model（ P < 0.01）. SHAP analysis identified the top five predictors in the combined model：ZSscore（SHAP value：0.78），long-run low gray-level emphasis（SHAP value：0.61），run-length non-uniformity（SHAP value：0.58），size-zone non-uniformity（SHAP value：0.46），and gray-level co-occurrence matrix joint energy（SHAP value：0.36）. Conclusions:The deep learning-based multimodal model integrating clinical and radiomic features accurately predicts AKI risk after partial nephrectomy，offering a novel strategy for preoperative risk stratification and personalized intervention.

Objective:To develop and validate a deep learning-based multimodal model integrating clinical and radiomic features for predicting acute kidney injury（AKI）risk after partial nephrectomy.Methods:A retrospective analysis was conducted on 416 patients who underwent partial nephrectomy at Zhongshan Hospital，Fudan University from January 2023 to January 2025. The cohort included 100 AKI patients［defined by a ≥ 25% reduction in postoperative evaluated glomerular filtration rate（eGFR）within 48 hours sustained for >24 hours］and 316 non-AKI patients（1∶3 ratio，randomly matched with 16 additional cases for redundancy）. Clinical and radiomic features were extracted from preoperative contrast-enhanced CT scans using PyRadiomics. Demographics included 259 males and 158 females，with a median age of 57（49，65）years，body mass index of（24.1 ± 3.3）kg/m2，preoperative eGFR of（88.5 ± 18.3）ml/（min·1.73 m2），postoperative eGFR（48-hour）of（76.0 ± 21.9）ml/（min·1.73 m2），Zhongshan Score（ZSscore）of 7.34 ± 2.01，and R.E.N.A.L. score of 7.50 ± 1.71. All tumors were T 1a stage. Patients were divided into training（n = 312）and test（n = 104）sets（3∶1 ratio）. A clinical model was constructed via multivariate logistic regression，while radiomic and combined（clinical + radiomic）models utilized an artificial neural network（ANN）with 1 input layer，5 hidden layers，1 output layer，and 10 5 training epochs. Model performance was evaluated by using receiver operating characteristic（ROC）curves and area under the curve（AUC），and was compared to the Martini model. Feature contributions were interpreted via SHapley Additive exPlanations（SHAP）. Results:In the test set，the results of multivariate logistic regression showed that patient’s weight，preoperative eGFR，R.E.N.A.L. score，surgical approach，and operation time were risk factors for AKI（ P < 0.05）. The AUC of the clinical feature prediction model constructed based on the above factors was 0.852（95% CI 0.775?0.929）. In the test set，the AUC of the Martini model was 0.725（95% CI 0.565?0.791）. The radiomic model，trained on 1 315 imaging features，achieved an AUC of 0.898（95% CI 0.804?0.993）with 94.2%（98/104）accuracy. The combined clinical and radiomic model，integrating 1 315 radiomic features and clinical features，demonstrated superior performance with an AUC of 0.946（95% CI 0.887?1.000）and 96.2%（100/104）accuracy，outperforming both the clinical model（ P = 0.03）and the Martini model（ P < 0.01）. SHAP analysis identified the top five predictors in the combined model：ZSscore（SHAP value：0.78），long-run low gray-level emphasis（SHAP value：0.61），run-length non-uniformity（SHAP value：0.58），size-zone non-uniformity（SHAP value：0.46），and gray-level co-occurrence matrix joint energy（SHAP value：0.36）. Conclusions:The deep learning-based multimodal model integrating clinical and radiomic features accurately predicts AKI risk after partial nephrectomy，offering a novel strategy for preoperative risk stratification and personalized intervention.

Objective To observe the effect of δ-opioid receptor on proliferation and migration of human epidermal stem cells (hESCs) in vitro so as to offer treatment theory for skin injury.Methods hESCs from fresh foreskin tissues of normal young volunteers were isolated and cultured by enzyme digestion and differential adherence technique.Immunofluorescent staining was used to determine expression of integrin β1 and cytokeratin 19 (CK19) and flow cytometry was used for cell count.Second generation of cells were cultured for 5 consecutive days with keratinocyte serum-free medium (K-SFM) supplemented with 1 nmol/L (D-Ala2,K-Leu5)-enkephalin in Group A,with K-SFM supplemented with 1 nmol/L naltrindole and 1 nmol/L (D-Ala2,K-Leu5)-enkephalin in Group B,and with isolated K-SFM in Group C.Cellular division and proliferation were detected by MTT method.An in vitro 100 μm scratch-wound model was created on the confluent monolayer cells at 24 hours of incubation.Cells migrating from the wound margin were determined by inverted phase contrast microscope at 24,48,72,and 96 hours after wound formation,while wound closure rate was calculated at 72 hours.Results Primary cultured hESCs presented cobblestone-like shape after adherence growth,Immunofluorescence staining showed positive results for integrin β1 and CK19 and cell purity reached 95.6％.Moreover,MTT findings revealed proliferation of hESCs enhanced significantly in Group A,but lowered in Group B as compared to Group C (P ＜ 0.05).hESCs migrated from the wound margin in all groups at 24 hours.However,more migrated cells were seen in Group A than in Group C and less in Group B than in Group C.Rate of wound closure was (89.5 ±0.7)％ in Group A,(76.1 ±0.3)％ in Group B,and (81.1 ±0.6)％ in Group C at 72 hours,indicating significant differences among groups (P ＜ 0.05).Conclusion Activation of δ-opioid receptor promotes the proliferation and migration of hESCs in vitro and may be implicated in wound healing.