OBJECTIVE To develop and validate interpretable machine learning models for predicting the risk of medication-related osteonecrosis of the jaw （MRONJ） and surgical outcomes， thereby providing quantitative support for MRONJ risk assessment and treatment decision-making.METHODS Two study cohorts were established. Cohort A adopted a nested case-control study design to develop a predictive model for the risk of MRONJ onset. Cohort B comprised patients with MRONJ from Cohort A who underwent surgical treatment and met the follow-up eligibility criteria， and employed a prospective follow-up cohort study design to develop a predictive model for the efficacy of MRONJ surgery. After missing-data processing， variable standardization， and encoding， predictive features were selected using the least absolute shrinkage and selection operator （LASSO） regression， and collinearity was assessed using the variance inflation factor （VIF）. Random Forest （RF）， eXtreme Gradient Boosting （XGB）， Multi-layer Perceptron （MLP）， Support Vector Machine （SVM）， and Gaussian Naive Bayes （NB） models were subsequently developed using the selected features. Hyperparameter optimization and internal performance evaluation were performed using two-level nested cross-validation repeated 20 times. In Cohort B， the synthetic minority over-sampling technique （SMOTE） was applied within the inner training folds to address class imbalance. Model performance was comprehensively evaluated using the receiver operating characteristic （ROC） curve， the precision-recall （PR） curve， calibration curve， and decision curve analysis （DCA）. Shapley additive explanations （SHAP） were used to quantify the relative contributions of individual clinical features to model predictions.RESULTS Seven clinical features， including alkaline phosphatase and tooth extraction， were retained for Cohort A； whereas eight clinical features， including age and duration of medication use， were retained for Cohort B. In Cohort A， the area under the ROC curve， the area under the PR curve， Brier score， sensitivity， and specificity of the RF model were 0.94， 0.92， 0.09， 0.92， and 0.85， respectively； the corresponding values in Cohort B were 0.93， 0.93， 0.12， 0.83， and 0.93， respectively. The results of calibration curves and DCA indicated that the RF models achieved favorable calibration and clinical net benefit， with VIF values for all variables below 5. SHAP visualization results showed that alkaline phosphatase， tooth extraction， and cumulative drug dose made substantial contributions to MRONJ risk prediction in Cohort A， whereas age， duration of medication use， and MRONJ stage contributed substantially to surgical outcome prediction in Cohort B.CONCLUSIONS The RF-based models for predicting MRONJ risk and surgical outcomes demonstrated good discrimination， accuracy of probabilistic predictions， and potential clinical utility during internal validation. These models may provide decision support for comprehensive MRONJ risk management and individualized clinical decision-making. However， external validation in independent， multicenter， and geographically diverse cohorts is still required.

Objective To investigate the expression of neural-nitric oxide synthase (nNOS) in renal clear cell carcinoma and its clinical significance.Methods The expression of nNOS mRNA in 533 samples of TCGA database was analyzed with Student t test,and statistical analysis was performed to assess the relationship between nNOS expression and clinical prognosis with Kapla-Meier test.Western blot analysis of nNOS protein expression in 10 cases of clear cell renal cell carcinoma(ccRCC) from department of urology of Wuhan union hospital with student t test.Results The mRNA levels of nNOS in 72 cases of ccRCC in tumor tissues and adjacent tissues and were 2.99 ± 0.28 and-1.57 ± 0.17,it is significantly lower than those in adjacent tissues (P ＜ 0.01).The mRNA levels of nNOS in 533 cases of ccRCC,in tumor tissues and adjacent tissues and were 2.99 ± 0.28 and-1.76 ± 0.05,it is significantly lower than those in adjacent tissues (P ＜ 0.01).A total of 533 sample studies showed a low correlation between nNOS expression and clinical T stage,T1-1.59 ±0.08,T2-1.96 ±0.13,T3-1.90 ±0.09,T4-2.38 ±0.28 (P =0.0029) and -1.63 ±0.06 and-2.16 ± 0.13 between non-metastasis and no-metastasis (P =0.0009),and-1.57 ± 0.08 and-2.03 ± 0.11 between non-recurrence and recurrence (P =0.008).Survival analysis showed that the overall survival time were (40.3 ± 5.6) months and (48.3 ± 5.7) months in lower and higher nNOS expression,and disease free survival time were (37.1 ± 2.1) months and (40.3 ± 5.6) months in lower and higher nNOS expression,both with shorter time in low expression of nNOS (P ＜ 0.01).nNOS proteins were 1.02 ± 0.16 and 0.61 ± 0.1 1 in tumor tissues and adjacent tissues with significantly lower expression(P＜0.05).Conclusions The mRNA and protein of nNOS are lower in ccRCC with a poor prognosis of ccRCC.