ObjectiveTo develop a machine learning (ML)-based prediction model for neurological rehabilitation outcomes of stroke patients. MethodsA total of 420 stroke patients admitted to the Fuzhou First People's Hospital from October, 2022 to October, 2024 were enrolled as the training set. According to the modified Rankin Scale (mRS) scores three months after discharge, the patients were divided into prognosis group (n = 289) and poor prognosis group (n = 131). An additional 180 stroke patients hospitalized in the same hospital from November, 2024 to April, 2025 were selected as the validation set. Univariate analysis, least absolute shrinkage and selection operator regression, and multivariate logistic regression were performed to identify independent influencing factors for the prognosis of neurological function recovery. Using the screened independent influencing factors as feature variables, six ML models were established, including logistic regression, linear discriminant analysis, naive Bayes, support vector machine, random forest and extreme gradient boosting (XGBoost). The area under the receiver operating characteristic curve (AUC), confusion matrix indicators (accuracy, precision, recall and F1-score), calibration curve and decision curve analysis were adopted to evaluate the predictive efficacy, calibration degree and clinical net benefit of each model, with external validation conducted in the validation set. The SHapley Additive exPlanations framework was used to interpret the optimal model, and bar charts were applied to visualize the feature importance of the best model. ResultsAge, National Institutes of Health Stroke Scale (NIHSS) score, collateral circulation grading, fasting plasma glucose (FPG), lymphocyte percentage (LYMPH%), and homocysteine (Hcy) were independent risk factors for poor neurological rehabilitation prognosis (P < 0.05). For the XGBoost model, the AUC of the training and validation sets were 0.963 (95%CI 0.947 to 0.979) and 0.825 (95%CI 0.764 to 0.885), respectively, while the accuracy was 88.81% and 77.22%, the precision was 92.86% and 68.42%, the recall was 69.47% and 47.27%, and the F1-score was 79.48% and 55.91%, optimal in both calibration and clinical net benefit. The feature importance ranking for the XGBoost model from high to low was NIHSS score, age, collateral circulation grading, FPG, Hcy and LYMPH%. ConclusionThe interpretable XGBoost ML model exhibits excellent predictive efficacy and favorable clinical applicability in predicting neurological rehabilitation outcomes for stroke patients.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Osteoporosis is a prevalent skeletal condition characterized by reduced bone mass and strength, leading to increased fragility. Buqi-Tongluo (BQTL) decoction, a traditional Chinese medicine (TCM) prescription, has yet to be fully evaluated for its potential in treating bone diseases such as osteoporosis. To investigate the mechanism by which BQTL decoction inhibits osteoclast differentiation in vitro and validate these findings through in vivo experiments. We employed MTS assays to assess the potential proliferative or toxic effects of BQTL on bone marrow macrophages (BMMs) at various concentrations. TRAcP experiments were conducted to examine BQTL's impact on osteoclast differentiation. RT-PCR and Western blot analyses were utilized to evaluate the relative expression levels of osteoclast-specific genes and proteins under BQTL stimulation. Finally, in vivo experiments were performed using an osteoporosis model to further validate the in vitro findings. This study revealed that BQTL suppressed receptor activator of NF-κB ligand (RANKL)-induced osteoclastogenesis and osteoclast resorption activity in vitro in a dose-dependent manner without observable cytotoxicity. The inhibitory effects of BQTL on osteoclast formation and function were attributed to the downregulation of NFATc1 and c-fos activity, primarily through attenuation of the MAPK, NF-κB, and Calcineurin signaling pathways. BQTL's inhibitory capacity was further examined in vivo using an ovariectomized (OVX) rat model, demonstrating a strong protective effect against bone loss. BQTL may serve as an effective therapeutic TCM for the treatment of postmenopausal osteoporosis and the alleviation of bone loss induced by estrogen deficiency and related conditions.
Animals ; NFATC Transcription Factors/genetics* ; Drugs, Chinese Herbal/pharmacology* ; Ovariectomy ; Osteoclasts/metabolism* ; Female ; Osteogenesis/drug effects* ; Rats, Sprague-Dawley ; Rats ; NF-kappa B/genetics* ; Osteoporosis/genetics* ; Signal Transduction/drug effects* ; Bone Resorption/genetics* ; Cell Differentiation/drug effects* ; Humans ; RANK Ligand/metabolism* ; Mitogen-Activated Protein Kinases/genetics* ; Transcription Factors

Objective:To investigate the clinicopathological features including immunophenotype, molecular characteristics, differential diagnosis and prognosis of SMARCB1-deficient renal medullary carcinoma (RMC) without sickle cell trait.Methods:The clinicopathological data of 12 cases of SMARCB1-deficient RMC without sickle cell trait were collected from 7 domestic institutions during the period of 2015 to 2024. Their clinical characteristics, morphological features and immunohistochemical properties were observed and analyzed. High-throughput DNA-targeted next-generation sequencing was performed, and follow-up data were gathered along with relevant literature review.Results:Among the 12 patients, 5 were female and 7 were male. The patients age ranged from 27 to 84 years with a median age of 58.5 (46.0, 71.0) years. None of them had sickle cell disease or other hemoglobinopathies. Eight cases occurred in the left kidney and 4 cases were located in the right kidney. The average maximum diameter of the tumor was 6.1 (4.0,7.5) cm, with a range of 2.0 to 14.9 cm (the median maximum diameter 5.5 cm). Histologically, the tumors showed poorly differentiated adenocarcinoma, arranged in solid and tubular patterns. Papillary structure was noted in 5 cases, cribriform structure in 3 cases, rhabdoid differentiation in 3 cases, and sarcomatoid differentiation in 2 cases. Inflammatory desmoplastic stromal reaction was observed in 8 cases, among which stromal myxoid degeneration was seen in 6 cases. Tumor necrosis was apparent in 6 cases. The tumor cells had abundant eosinophilic or clear cytoplasm and prominent nucleoli. The nuclear grading was grade 3 or 4 according to the International Society of Urological Pathology (ISUP). Immunohistochemical staining showed that the tumor cells of all 12 cases expressed PAX8 and loss of SMARCB1/INI1 protein expression, and 5 of 10 cases expressed OCT3/4. Seven samples had valid archived paraffin tissues for high-throughput DNA-targeted next-generation sequencing. The results showed that all 7 cases had pathogenic mutations in the SMARCB1 gene. The mutation sites included exon5 c.595A>T (p.K199*), exon2 c.200_207del (p.S67*), exon2 p.G69VfsTer16, exon7 c.986G>T (p.S329I), exon7 c.886A>T (p.K296*), exon6 c.635T>A (p.L212*), exon5 c.577del (p.M193Wfs16), and exon6 c.784del (p.V262Sfs5). Follow-up data were obtained for 6 of 12 patients. Among them, 1 patient had lung and bone metastases, 1 patient had liver and bone metastases and 1 patient had multiple bone metastases at the time of diagnosis; 1 patient had bone metastases 5 months after surgery. One patient died of postoperative complications 10 days after surgery, 4 patients died of tumors (the survival time ranged from 4 to 8 months), and 1 patient had no recurrence or metastasis during the 8-month follow-up after surgery.Conclusions:SMARCB1-deficient RMC without sickle cell trait is a highly aggressive and poorly differentiated renal cell carcinoma. It has similar histomorphology, immunophenotype, molecular characteristics and prognosis to RMC, which further supports that it is a sporadic subtype of RMC related to sickle cell trait.

Objective To summarize the characteristics and sources of infection risk of Bacillus cereus(B.cereus)septicemia in low birth weight(LBW)infants,and provide reference for infection prevention and control.Methods Characteristics of 3 LBW infants with B.cereus septicemia were reported and analyzed,relevant literatures were searched for systematically summarizing the characteristics and sources of infection risk of B.cereus septicemia in infants.Results Among 3 LBW infants reported in this paper,2 died and 1 was cured.No clear infection source was found in the environment through object surface sampling analysis.A total of 43 cases were reported in the pre-vious literatures,41 cases had reported on survival status,the mortality was 36.6％.The main risk factors for in-fection were auxiliary ventilation,umbilical vein catheterization or central vein catheterization and enteral feeding.In the reported 3 cases with clear sources of infection,the pathogens came from mother's milk,decoration area,sur-face of infant incubator and ultrasonic probe.Conclusion Premature LBW infants with B.cereus septicemia have high mortality and poor prognosis,which is a healthcare-associated infectious disease seriously threatening the life and health of LBW infants.Neonatal intensive care unit(NICU)and relevant departments of healthcare-associated infection(HAI)management need to pay attention to the prevention,monitoring,early detection,as well as active diagnosis and treatment of HAI caused by this bacteria.

Objective To investigate the clinical efficacy and safety of wentong guasha combined with herbal enema in the treatment of acute attack of chronic pelvic inflammatory disease.Methods From January 2023 to December 2024,patients with acute attack of chronic pelvic inflammatory disease diagnosed and treated at Foshan Women and Children Hospital Affiliated to Guangdong Medical University were selected and randomly divided into an experimental group and a control group.The control group received herbal enema therapy,while the experimental group received additional wentong guasha therapy on the basis of the control group's treatment.Both groups were treated for two weeks.The clinical efficacy,safety outcomes,as well as Visual Analog Scale(VAS)scores for pain and Pittsburgh Sleep Quality Index(PSQI)scores before treatment and after the 3rd and 7th days of treatment were compared between the two groups.Results A total of 120 patients were included,with 60 cases in each group.After treatment,the total effective rate was 90.00%in the experimental group and 76.67%in the control group,showing a statistically significant difference between the two groups(P<0.05).On the 3rd day of treatment,the VAS score of the experimental group was significantly lower than that of the control group(P<0.05).By the 7th day of treatment,both the VAS and PSQI scores of the experimental group were significantly lower than those of the control group(P<0.05).No adverse reactions were observed in either group.Conclusion Compared with herbal enema therapy,wentong guasha combined with herbal enema demonstrated more significant clinical efficacy in patients with acute attack of chronic pelvic inflammatory disease,markedly reduced pain scores,improved sleep quality,and showed good safety,indicating its potential value for clinical promotion and application.

Objective To summarize the characteristics and sources of infection risk of Bacillus cereus(B.cereus)septicemia in low birth weight(LBW)infants,and provide reference for infection prevention and control.Methods Characteristics of 3 LBW infants with B.cereus septicemia were reported and analyzed,relevant literatures were searched for systematically summarizing the characteristics and sources of infection risk of B.cereus septicemia in infants.Results Among 3 LBW infants reported in this paper,2 died and 1 was cured.No clear infection source was found in the environment through object surface sampling analysis.A total of 43 cases were reported in the pre-vious literatures,41 cases had reported on survival status,the mortality was 36.6％.The main risk factors for in-fection were auxiliary ventilation,umbilical vein catheterization or central vein catheterization and enteral feeding.In the reported 3 cases with clear sources of infection,the pathogens came from mother's milk,decoration area,sur-face of infant incubator and ultrasonic probe.Conclusion Premature LBW infants with B.cereus septicemia have high mortality and poor prognosis,which is a healthcare-associated infectious disease seriously threatening the life and health of LBW infants.Neonatal intensive care unit(NICU)and relevant departments of healthcare-associated infection(HAI)management need to pay attention to the prevention,monitoring,early detection,as well as active diagnosis and treatment of HAI caused by this bacteria.

Objective To investigate the clinical efficacy and safety of wentong guasha combined with herbal enema in the treatment of acute attack of chronic pelvic inflammatory disease.Methods From January 2023 to December 2024,patients with acute attack of chronic pelvic inflammatory disease diagnosed and treated at Foshan Women and Children Hospital Affiliated to Guangdong Medical University were selected and randomly divided into an experimental group and a control group.The control group received herbal enema therapy,while the experimental group received additional wentong guasha therapy on the basis of the control group's treatment.Both groups were treated for two weeks.The clinical efficacy,safety outcomes,as well as Visual Analog Scale(VAS)scores for pain and Pittsburgh Sleep Quality Index(PSQI)scores before treatment and after the 3rd and 7th days of treatment were compared between the two groups.Results A total of 120 patients were included,with 60 cases in each group.After treatment,the total effective rate was 90.00%in the experimental group and 76.67%in the control group,showing a statistically significant difference between the two groups(P<0.05).On the 3rd day of treatment,the VAS score of the experimental group was significantly lower than that of the control group(P<0.05).By the 7th day of treatment,both the VAS and PSQI scores of the experimental group were significantly lower than those of the control group(P<0.05).No adverse reactions were observed in either group.Conclusion Compared with herbal enema therapy,wentong guasha combined with herbal enema demonstrated more significant clinical efficacy in patients with acute attack of chronic pelvic inflammatory disease,markedly reduced pain scores,improved sleep quality,and showed good safety,indicating its potential value for clinical promotion and application.