ObjectiveTo investigate the clinical characteristics and risk factors of Mycoplasma pneumoniae pneumonia （MPP） in children based on a dual classification integrating imaging features and clinical severity. MethodsMedical records of 2 054 pediatric patients with MPP were retrospectively analyzed. The cohort was stratified into severe consolidation （n=253）， severe non-consolidation （n=118）， non-severe consolidation （n=393）， and non-severe non-consolidation groups （n=1 290） based on clinical and radiological findings. Inter group data and characteristics were compared and multiple regression analysis was conducted to construct a prediction model for severe consolidation group. ResultsSignificant differences were observed among the groups in terms of age， duration of fever， length of hospital stay， presence of pulmonary rales， inflammatory markers ［C-reactive protein （CRP） and lactate dehydrogenase （LDH）］， the use of hormones， and bronchoscopic treatment （all P < 0.05）. Compared with the severe non-consolidation group， non-severe consolidation group， and non-severe non-consolidation group， children in severe consolidation group exhibited the longest duration of fever ［8 （6， 11） days vs 6 （2， 9）， 7 （6， 9） and 6 （3， 8） days， respectively］ and the longest length of hospital stay ［7 （5， 8） days vs 6 （5， 8）， 6 （5， 8） and 6 （4， 7） days， respectively］. They also had the highest incidence of reduced breath sounds ［34 cases （13.4%） vs 2 cases （1.7%）， 29 cases （7.4%） and 13 cases （1.0%）， respectively］ and a substantially higher rate of coinfections， particularly viral infections ［63 cases （24.9%） vs 23 cases （19.5%）， 60 cases （15.3%） and 190 cases （14.7%）， respectively］. Multivariate analysis indicated that the independent risk factors for severe MPP （SMPP） were age > 4.5 years， length of hospital stay > 6.5 days， reduced breath sounds， neutrophil-to-lymphocyte ratio （NLR） > 1.66， LDH > 370.5 U/L， CRP > 9.5 mg/L， and coinfection with viruses. Reduced breath sounds （OR = 5.58， 95% CI： 2.45 - 12.69） and coinfection with bacteria （OR = 3.11， 95% CI： 1.43 - 6.75） were identified as the most significant risk factors for pulmonary consolidation in non-severe MPP children. Additionally， reduced breath sounds， coinfection with viruses， LDH > 365.5 U/L， and CRP > 32.1 mg/L were risk factors for severe pneumonia in children with pulmonary consolidation. For non-consolidation MPP children， the presence of pulmonary dry rales （OR = 2.28， 95% CI： 1.46 - 3.56） was the primary independent risk factor for the development of severe pneumonia. ConclusionThe chest imaging findings of MPP are associated with clinical severity， and the risk factor model constructed based on this imaging-clinical classification can assist in achieving precise hierarchical diagnosis and treatment in clinical practice.

ObjectiveTo investigate the risk factors for plastic bronchitis （PB） in children with Mycoplasma pneumoniae pneumonia （MPP） and to construct a predictive model. MethodsPropensity score matching （1∶4 nearest neighbor matching） was used to balance baseline data between the two groups. Univariate and multivariate Logistic regression analyses were performed to identify independent risk factors. Various machine learning algorithms were applied to build predictive models， and model performance was evaluated using receiver operating characteristic curves， decision curves， and calibration curves. SHapley Additive exPlanations （SHAP） method was used for model interpretation. ResultsAfter matching， baseline characteristics were comparable between the two groups. Compared with the non-PB group， the PB group had significantly longer fever duration， higher incidence of pleural effusion and right upper lobe involvement， and higher levels of procalcitonin （PCT）， D-dimer， lactate dehydrogenase （LDH）， alanine aminotransferase （ALT）， aspartate aminotransferase （AST）， immunoglobulin E （IgE）， and red blood cell count in bronchoalveolar lavage fluid （BALF） （all P<0.05）， while lymphocyte and eosinophil counts in blood were significantly lower （P<0.05）. Multivariate Logistic regression showed that PCT>0.207 μg/L， LDH>386.25 U/L， right upper lobe involvement， and red blood cell count in BALF>1 500×10⁶ were independent risk factors. Among machine learning models， the gradient boosting machine （GBM） model achieved an area under the curve of 0.786 in the validation set， demonstrating the best generalization ability. SHAP analysis validated the importance of the above variables. ConclusionThe four indicators above have independent predictive value for PB occurrence， and the GBM model shows certain clinical risk stratification capability.

Computational approaches,encompassing both physics-based and machine learning(ML)methodolo-gies,have gained substantial traction in drug repurposing efforts targeting specific therapeutic entities.The human dopamine(DA)transporter(hDAT)is the primary therapeutic target of numerous psychi-atric medications.However,traditional hDAT-targeting drugs,which interact with the primary binding site,encounter significant limitations,including addictive potential and stimulant effects.In this study,we propose an integrated workflow combining virtual screening based on weighted holistic atom localization and entity shape(WHALES)descriptors with in vitro experimental validation to repurpose novel hDAT-targeting drugs.Initially,WHALES descriptors facilitated a similarity search,employing four benztropine-like atypical inhibitors known to bind hDAT's allosteric site as templates.Consequently,from a compound library of 4,921 marketed and clinically tested drugs,we identified 27 candidate atypical inhibitors.Subsequently,ADMETlab was employed to predict the pharmacokinetic and toxi-cological properties of these candidates,while induced-fit docking(IFD)was performed to estimate their binding affinities.Six compounds were selected for in vitro assessments of neurotransmitter re-uptake inhibitory activities.Among these,three exhibited significant inhibitory potency,with half maximal inhibitory concentration(IC50)values of 0.753 μM,0.542 μM,and 1.210 μM,respectively.Finally,molecular dynamics(MD)simulations and end-point binding free energy analyses were con-ducted to elucidate and confirm the inhibitory mechanisms of the repurposed drugs against hDAT in its inward-open conformation.In conclusion,our study not only identifies promising active compounds as potential atypical inhibitors for novel therapeutic drug development targeting hDAT but also validates the effectiveness of our integrated computational and experimental workflow for drug repurposing.

Objective:To construct a machine learning model based on localization CT-based radiomics, dosiomics and clinical features for predicting radiotherapy response in non-small cell lung cancer (NSCLC) and validate its application value.Methods:A retrospective case series study was conducted. A total of 138 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022 were selected. The efficacy was evaluated according to the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, and the patients were stratified according to the objective remission (complete remission+partial remission). Random stratified sampling was used to divide the 138 patients into a training group (96 cases) and an internal validation group (42 cases) at a ratio of 7∶3. Additionally, 33 patients who received radiotherapy at Jining Cancer Hospital from January 2019 to December 2022 were included as the external validation group. Based on the pre-radiotherapy data of the radiotherapy planning system, PyRadiomics software package was used to extract 107 radiomics features and 107 dosiomics features for each patient. Pearson correlation analysis and LASSO regression analysis were used for dimensionality reduction screening; the final selected features were weighted and integrated to generate radiomics-dosiomics scores (RDS), which were then input into logistic regression (LR), support vector machine (SVM), extremely randomized forest (Extra Trees), K-nearest neighbor algorithm (KNN), lightweight gradient boosting machine (Light GBM), and multi-layer perceptron (MLP) machine learning algorithms to construct 6 radiomics-dosiomics models (RDM) for predicting the objective remission. RECIST 1.1 standard was used to evaluate objective remission as the gold standard, receiver operating characteristic (ROC) curve of 6 RDM for predicting objective remission was plotted, and the optimal algorithm for RDM was selected. Univariate and multivariate logistic regression were performed on demographic characteristics, hematological indicators and radiotherapy parameters of the training group to screen independent risk factors for NSCLC patients who received radiotherapy but did not achieve objective remission. These factors were input into the optimal machine learning algorithm to construct a clinical model (CM). Combined with features from RDS and CM, the clinical feature-radiomics-dosiomics combined model (CRDM) was established, and the nomogram of the model for predicting objective remission in NSCLC patients with radiotherapy was drawn. ROC curves were used to evaluate the efficacy of CM, RDM and CRDM in predicting the objective remission in NSCLC patients with radiotherapy in the training group, internal validation group and external validation group.Results:Four radiomics features (including grayscale variance, low grayscale long-range operation emphasis, low grayscale area emphasis, and small area low grayscale area emphasis, all of which were texture features) and 6 dosiomics features [including 1 first-order feature (robust mean absolute deviation), 4 texture features (grayscale non-uniformity, large area emphasis, large area high grayscale emphasis, contrast) and 1 shape feature (shortest axis length)] were selected. ROC curve analysis showed that the area under the curve (AUC) of the RDM constructed using SVM algorithm for judging the objective remission in the training group and the internal validation group was 0.907 (95% CI: 0.836-0.977) and 0.822 (95% CI: 0.685-0.959), which were higher than RDM constructed using other algorithms, and the sensitivity (96.2% and 91.7%), specificity (78.6% and 76.7%) and accuracy (83.3% and 81.0%) at the optimal cut-off values were all higher. Considering the stability and generalization ability of the model, SVM algorithm was ultimately used to construct RDM, CM and CRDM uniformly. Based on training group data, univariate and multivariate logistic regression analysis showed that elevated platelet-to-lymphocyte ratio (PLR) ( OR = 1.001, 95% CI: 1.000-1.003, P = 0.035) and increased target volume of radiotherapy plan ( OR = 1.001, 95% CI: 1.000-1.001, P = 0.008) were independent risk factors for failure to achieve objective remission. ROC curve analysis showed that in the training group and the internal validation group, the AUC of CRDM predicting objective remission were 0.914 (95% CI: 0.856-0.972) and 0.864 (95% CI: 0.754-0.974), respectively, which were better than CM [AUC were 0.735 (95% CI: 0.612-0.857) and 0.697 (95% CI: 0.507-0.888)] and RDM, respectively. In the external validation group, the AUC of CRDM, CM and RDM were 0.778 (95% CI: 0.500-1.000), 0.667 (95% CI: 0.434-0.899) and 0.741 (95% CI: 0.463-1.000), respectively. Conclusions:The CRDM constructed by combining radiomics, dosiomics and clinical features can comprehensively and accurately evaluate the radiotherapy response of NSCLC patients, and may have important clinical application value in achieving precision medicine and optimizing treatment strategies.

Computational approaches, encompassing both physics-based and machine learning (ML) methodologies, have gained substantial traction in drug repurposing efforts targeting specific therapeutic entities. The human dopamine (DA) transporter (hDAT) is the primary therapeutic target of numerous psychiatric medications. However, traditional hDAT-targeting drugs, which interact with the primary binding site, encounter significant limitations, including addictive potential and stimulant effects. In this study, we propose an integrated workflow combining virtual screening based on weighted holistic atom localization and entity shape (WHALES) descriptors with in vitro experimental validation to repurpose novel hDAT-targeting drugs. Initially, WHALES descriptors facilitated a similarity search, employing four benztropine-like atypical inhibitors known to bind hDAT's allosteric site as templates. Consequently, from a compound library of 4,921 marketed and clinically tested drugs, we identified 27 candidate atypical inhibitors. Subsequently, ADMETlab was employed to predict the pharmacokinetic and toxicological properties of these candidates, while induced-fit docking (IFD) was performed to estimate their binding affinities. Six compounds were selected for in vitro assessments of neurotransmitter reuptake inhibitory activities. Among these, three exhibited significant inhibitory potency, with half maximal inhibitory concentration (IC₅₀) values of 0.753 μM, 0.542 μM, and 1.210 μM, respectively. Finally, molecular dynamics (MD) simulations and end-point binding free energy analyses were conducted to elucidate and confirm the inhibitory mechanisms of the repurposed drugs against hDAT in its inward-open conformation. In conclusion, our study not only identifies promising active compounds as potential atypical inhibitors for novel therapeutic drug development targeting hDAT but also validates the effectiveness of our integrated computational and experimental workflow for drug repurposing.

Objective:To develop and validate a combined model integrating radiomics, dosiomics, and clinical parameters based on CT simulation and dosimetric images in order to predict the occurrence of radiation pneumonitis (RP) in patients with non-small cell lung cancer (NSCLC).Methods:A retrospective study was conducted on the clinic data of 143 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022. Patients were randomly stratified into a training group ( n = 100) and an internal validation group ( n = 43) at a 7∶3 ratio. Moreover, clinic data were collected from 34 NSCLC patients who received radiotherapy at the Jining Cancer Hospital between January 2019 and December 2022 as an external validation group. All three groups (the training group, internal validation, and external validation groups) were further categorized into two groups based on the RP severity (i.e., RP ≥ grade 2 and RP < grade 2). Their radiotherapy dose, CT simulation, and 3D dose distribution images were collected. Then, the total lung minus planning target volume (TL-PTV) was defined as the region of interest (ROI) for radiomics and dosiomic feature extraction, followed by feature dimensionality reduction. Consequently, key features associated with RP were determined. Four predictive models were developed using machine learning approaches (especially multilayer perceptron, MLP): a clinical model (CM), a radiomics model (RM), a dosiomics model (DM), and a radiomics and dosiomics nomogram (RDN), with a nomogram subsequently constructed. Ultimately, the performance and clinical feasibility of these models were assessed using receiver operating characteristic (ROC), area under the curve (AUC), and decision curve analysis (DCA). Results:A total of 1 834 radiomic features and 1 834 dosiomic features were extracted. Using the occurrence of RP ≥ grade 2 as the marker variable, 14 radiomic features, 15 dosiomic features, and three clinical features were selected from the training group to construct the prediction models (CM, RM, DM, and RDN). The performance and generalizability of these models were subsequently validated in both the internal validation and external validation groups. Specifically, the RDN exhibited AUCs of 0.915 (95% CI: 0.852-0.978), 0.879 (95% CI: 0.777-0.982), and 0.838 (95% CI: 0.701-0.975) in the three groups, respectively. A nomogram was established for RDN by integrating the radiomics score (R-score), dosiomics score (D-score), mean lung dose (MLD), V20, and V30. This nomogram allowed for individualized risk estimation of RP and facilitated personalized radiotherapy planning. Conclusions:The RDN model that is developed based on CT simulation and 3D dose distribution images and integrates radiomics, dosiomics, and clinical features can effectively predict the RP risk of NSCLC patients. The integration of multidimensional data contributes to the formation of the optimal predictive model, offering guidance for clinicians.

Objective:To construct a machine learning model based on localization CT-based radiomics, dosiomics and clinical features for predicting radiotherapy response in non-small cell lung cancer (NSCLC) and validate its application value.Methods:A retrospective case series study was conducted. A total of 138 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022 were selected. The efficacy was evaluated according to the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, and the patients were stratified according to the objective remission (complete remission+partial remission). Random stratified sampling was used to divide the 138 patients into a training group (96 cases) and an internal validation group (42 cases) at a ratio of 7∶3. Additionally, 33 patients who received radiotherapy at Jining Cancer Hospital from January 2019 to December 2022 were included as the external validation group. Based on the pre-radiotherapy data of the radiotherapy planning system, PyRadiomics software package was used to extract 107 radiomics features and 107 dosiomics features for each patient. Pearson correlation analysis and LASSO regression analysis were used for dimensionality reduction screening; the final selected features were weighted and integrated to generate radiomics-dosiomics scores (RDS), which were then input into logistic regression (LR), support vector machine (SVM), extremely randomized forest (Extra Trees), K-nearest neighbor algorithm (KNN), lightweight gradient boosting machine (Light GBM), and multi-layer perceptron (MLP) machine learning algorithms to construct 6 radiomics-dosiomics models (RDM) for predicting the objective remission. RECIST 1.1 standard was used to evaluate objective remission as the gold standard, receiver operating characteristic (ROC) curve of 6 RDM for predicting objective remission was plotted, and the optimal algorithm for RDM was selected. Univariate and multivariate logistic regression were performed on demographic characteristics, hematological indicators and radiotherapy parameters of the training group to screen independent risk factors for NSCLC patients who received radiotherapy but did not achieve objective remission. These factors were input into the optimal machine learning algorithm to construct a clinical model (CM). Combined with features from RDS and CM, the clinical feature-radiomics-dosiomics combined model (CRDM) was established, and the nomogram of the model for predicting objective remission in NSCLC patients with radiotherapy was drawn. ROC curves were used to evaluate the efficacy of CM, RDM and CRDM in predicting the objective remission in NSCLC patients with radiotherapy in the training group, internal validation group and external validation group.Results:Four radiomics features (including grayscale variance, low grayscale long-range operation emphasis, low grayscale area emphasis, and small area low grayscale area emphasis, all of which were texture features) and 6 dosiomics features [including 1 first-order feature (robust mean absolute deviation), 4 texture features (grayscale non-uniformity, large area emphasis, large area high grayscale emphasis, contrast) and 1 shape feature (shortest axis length)] were selected. ROC curve analysis showed that the area under the curve (AUC) of the RDM constructed using SVM algorithm for judging the objective remission in the training group and the internal validation group was 0.907 (95% CI: 0.836-0.977) and 0.822 (95% CI: 0.685-0.959), which were higher than RDM constructed using other algorithms, and the sensitivity (96.2% and 91.7%), specificity (78.6% and 76.7%) and accuracy (83.3% and 81.0%) at the optimal cut-off values were all higher. Considering the stability and generalization ability of the model, SVM algorithm was ultimately used to construct RDM, CM and CRDM uniformly. Based on training group data, univariate and multivariate logistic regression analysis showed that elevated platelet-to-lymphocyte ratio (PLR) ( OR = 1.001, 95% CI: 1.000-1.003, P = 0.035) and increased target volume of radiotherapy plan ( OR = 1.001, 95% CI: 1.000-1.001, P = 0.008) were independent risk factors for failure to achieve objective remission. ROC curve analysis showed that in the training group and the internal validation group, the AUC of CRDM predicting objective remission were 0.914 (95% CI: 0.856-0.972) and 0.864 (95% CI: 0.754-0.974), respectively, which were better than CM [AUC were 0.735 (95% CI: 0.612-0.857) and 0.697 (95% CI: 0.507-0.888)] and RDM, respectively. In the external validation group, the AUC of CRDM, CM and RDM were 0.778 (95% CI: 0.500-1.000), 0.667 (95% CI: 0.434-0.899) and 0.741 (95% CI: 0.463-1.000), respectively. Conclusions:The CRDM constructed by combining radiomics, dosiomics and clinical features can comprehensively and accurately evaluate the radiotherapy response of NSCLC patients, and may have important clinical application value in achieving precision medicine and optimizing treatment strategies.

Objective:To develop and validate a combined model integrating radiomics, dosiomics, and clinical parameters based on CT simulation and dosimetric images in order to predict the occurrence of radiation pneumonitis (RP) in patients with non-small cell lung cancer (NSCLC).Methods:A retrospective study was conducted on the clinic data of 143 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022. Patients were randomly stratified into a training group ( n = 100) and an internal validation group ( n = 43) at a 7∶3 ratio. Moreover, clinic data were collected from 34 NSCLC patients who received radiotherapy at the Jining Cancer Hospital between January 2019 and December 2022 as an external validation group. All three groups (the training group, internal validation, and external validation groups) were further categorized into two groups based on the RP severity (i.e., RP ≥ grade 2 and RP < grade 2). Their radiotherapy dose, CT simulation, and 3D dose distribution images were collected. Then, the total lung minus planning target volume (TL-PTV) was defined as the region of interest (ROI) for radiomics and dosiomic feature extraction, followed by feature dimensionality reduction. Consequently, key features associated with RP were determined. Four predictive models were developed using machine learning approaches (especially multilayer perceptron, MLP): a clinical model (CM), a radiomics model (RM), a dosiomics model (DM), and a radiomics and dosiomics nomogram (RDN), with a nomogram subsequently constructed. Ultimately, the performance and clinical feasibility of these models were assessed using receiver operating characteristic (ROC), area under the curve (AUC), and decision curve analysis (DCA). Results:A total of 1 834 radiomic features and 1 834 dosiomic features were extracted. Using the occurrence of RP ≥ grade 2 as the marker variable, 14 radiomic features, 15 dosiomic features, and three clinical features were selected from the training group to construct the prediction models (CM, RM, DM, and RDN). The performance and generalizability of these models were subsequently validated in both the internal validation and external validation groups. Specifically, the RDN exhibited AUCs of 0.915 (95% CI: 0.852-0.978), 0.879 (95% CI: 0.777-0.982), and 0.838 (95% CI: 0.701-0.975) in the three groups, respectively. A nomogram was established for RDN by integrating the radiomics score (R-score), dosiomics score (D-score), mean lung dose (MLD), V20, and V30. This nomogram allowed for individualized risk estimation of RP and facilitated personalized radiotherapy planning. Conclusions:The RDN model that is developed based on CT simulation and 3D dose distribution images and integrates radiomics, dosiomics, and clinical features can effectively predict the RP risk of NSCLC patients. The integration of multidimensional data contributes to the formation of the optimal predictive model, offering guidance for clinicians.

The correlation between hearing loss (HL) and physical performance in patients receiving maintenance hemodialysis (MHD) remains poorly investigated. This study explored the association between HL and physical performance in patients on MHD. Methods: This multicenter cross-sectional study was conducted between July 2020 and April 2021 in seven hemodialysis centers in Shanghai and Suzhou, China. The hearing assessment was performed using pure-tone average (PTA). Physical performance was assessed using the Timed Up and Go Test (TUGT), handgrip strength, and gait speed. Results: Finally, 838 adult patients (male, 516 [61.6%]; 61.2 ± 2.6 years) were enrolled. Among them, 423 (50.5%) had mild to profound HL (male, 48.6% and female, 53.4%). Patients with HL had poorer physical performance than patients without HL (p < 0.001). TUGT was positively correlated with PTA (r = 0.265, p < 0.001), while handgrip strength and gait speed were negatively correlated with PTA (r = –0.356, p < 0.001 and r = –0.342, p < 0.001, respectively). Physical performance in patients aged <60 years showed significant dose-response relationships with HL. After adjusting for confounders, the odds ratios (95% confidence intervals) for HL across the TUGT quartiles (lowest to highest) were 1.00 (reference), 1.15 (0.73–1.81), 1.69 (1.07–2.70), and 2.87 (1.69–4.88) (p for trend = 0.005). Conclusion: Lower prevalence of HL was associated with a faster TUGT and a stronger handgrip strength in patients on MHD.

Background The benchmark dose (BMD) method calculates the dose associated with a specific change in response based on a specific dose-response relationship. Compared with the traditional no observed adverse effect level (NOAEL) method, the BMD method has many advantages, and the 95% lower confidence limit of benchmark dose lower limit (BMDL) is recommended to replace NOAEL in deriving biological exposure limits. No authority has yet published any health-based guideline for rare earth elements. Objective To evaluate genotoxicity threshold induced by acute exposure to neodymium nitrate in mice using BMD modeling through micronucleus test and comet assay. Methods SPF grade mice (n=90) were randomly divided into nine groups, including seven neodymium nitrate exposure groups, one control group (distilled water), and one positive control group (200 mg·kg⁻¹ ethyl methanesulfonate), 10 mice in each group, half male and half female. The seven dose groups were fed by gavage with different concentrations of neodymium nitrate solution (male: 14, 27, 39, 55, 77, 109, and 219 mg·kg⁻¹; female: 24, 49, 69, 97, 138, 195, and 389 mg·kg⁻¹) twice at an interval of 21 h. Three hours after the last exposure, the animals were neutralized by cervical dislocation. The bone marrow of mice femur was taken to calculate the micronucleus rate of bone marrow cells, and the liver and stomach were taken for comet test. Results The best fitting models for the increase of polychromatophil micronucleus rate in bone marrow of female and male mice induced by neodymium nitrate were the exponential 4 model and the hill model, respectively. The BMD and the BMDL of female mice were calculated to be 31.37 mg·kg⁻¹ and 21.90 mg·kg⁻¹, and those of male mice were calculated to be 58.62 mg·kg⁻¹ and 54.31 mg·kg⁻¹, respectively. The best fitting models for DNA damage induced by neodymium nitrate in female and male mouse hepatocytes were the exponential 5 model and the exponential 4 model, respectively, and the calculated BMD and BMDL were 27.15 mg·kg⁻¹ and 11.99 mg·kg⁻¹ for female mice, and 16.28 mg·kg⁻¹ and 10.47 mg·kg⁻¹ for male mice, respectively. The hill model was the best fitting model for DNA damage of gastric adenocytes in both female and male mice, and the calculated BMD and BMDL were 36.73 mg·kg⁻¹ and 19.92 mg·kg⁻¹ for female mice, and 24.74 mg·kg⁻¹ and 14.08 mg·kg⁻¹ for male mice, respectively. Conclusion Taken the micronucleus rate of bone marrow cells, DNA damage of liver cells and gastric gland cells as the end points of genotoxicity, the BMDL of neodymium nitrate is 10.47 mg·kg⁻¹, which can be used as the threshold of genotoxic effects induced by acute exposure to neodymium nitrate in mice.