OBJECTIVE To investigate the application status of prescription pre-review systems in healthcare institutions of Yunnan province， evaluate their system functions and management capabilities， and provide a practical basis for promoting rational drug use. METHODS A questionnaire survey was conducted among public healthcare institutions at or above the secondary level in Yunnan province to investigate the deployment status of the systems. A capability maturity assessment framework was constructed， encompassing 6 dimensions and 39 indicators， including real-time prescription review， prescription correlation review， rule setting， evidence-based information support， prescription authority management， and system operation management. This framework was then used to evaluate the institutions that had implemented the pre-review systems. RESULTS A total of 100 valid questionnaires were collected， with 37 institutions having adopted prescription pre-review systems， mainly tertiary hospitals. The system predominantly adopted a modular architecture and was embedded into the hospital information system through application programming interfaces and middleware， providing certain capabilities for real-time prescription risk identification. Evaluation results indicated that basic functions such as reviewing indications， contraindications， and drug compatibility performed well， while deficiencies remained in functions related to parenteral nutrition prescription， review of drug dosage for specific diseases， individual patient characteristic recognition， and rule setting. Moreover， the construction of review centers and establishment of management systems were also not well-developed. CONCLUSIONS The overall application rate of prescription pre-review systems in Yunnan province remains low. System functions and management mechanisms require further improvement. It is recommended to enhance information infrastructure in lower-level institutions and explore regionally unified review models to promote standardized and intelligent development of prescription review practices.

BACKGROUND: Over 20 million colonoscopies are performed in China annually. An automatic clinical decision support system (CDSS) with accurate semantic recognition of colonoscopy reports and guideline-based is helpful to relieve the increasing medical burden and standardize the healthcare. In this study, the CDSS was built under a hierarchical-label interpretable classification framework, trained by a state-of-the-art transformer-based model, and validated in a multi-center style. METHODS: We conducted stratified sampling on a previously established dataset containing 302,965 electronic colonoscopy reports with pathology, identified 2041 patients' records representative of overall features, and randomly divided into the training and testing sets (7:3). A total of five main labels and 22 sublabels were applied to annotate each record on a network platform, and the data were trained respectively by three pre-training models on Chinese corpus website, including bidirectional encoder representations from transformers (BERT)-base-Chinese (BC), the BERT-wwm-ext-Chinese (BWEC), and ernie-3.0-base-zh (E3BZ). The performance of trained models was subsequently compared with a randomly initialized model, and the preferred model was selected. Model fine-tuning was applied to further enhance the capacity. The system was validated in five other hospitals with 3177 consecutive colonoscopy cases. RESULTS: The E3BZ pre-trained model exhibited the best performance, with a 90.18% accuracy and a 69.14% Macro-F1 score overall. The model achieved 100% accuracy in identifying cancer cases and 99.16% for normal cases. In external validation, the model exhibited favorable consistency and good performance among five hospitals. CONCLUSIONS The novel CDSS possesses high-level semantic recognition of colonoscopy reports, provides appropriate recommendations, and holds the potential to be a powerful tool for physicians and patients. The hierarchical multi-label strategy and pre-training method should be amendable to manage more medical text in the future.
Humans ; Colonoscopy/methods* ; Deep Learning ; Decision Support Systems, Clinical ; Female ; Male

To address the problem of data silos in dental specialties caused by equipment heterogeneity, this study developed an Intelligent Internet of Things (IoT)-enabled dental chair platform (hereinafter referred to as the intelligent platform) based on the concept of medical-engineering integration. The platform adopts a three-tier chair-domain interconnection architecture: the bottom tier integrates multi-source sensors and standardized interfaces for automated data acquisition and linkage with hospital information systems; the middle tier provides clinic-level management and remote teaching collaboration; and the top tier employs a blockchain-based secure cloud database for resource allocation and data management. Clinical validation at The Affiliated Stomatological Hospital of Nanjing Medical University demonstrated that, compared with a control group from the same period in 2023, the trial group achieved a 38.0% increase in average daily patient visits (80.6±6.8 vs. 58.4±5.2, t=15.16, P<0.001), a 24.6% reduction in average treatment time [(36.1±6.3) min vs. (47.9±8.5) min, t=7.72, P<0.001], a 39.2% reduction in waiting time [23.3 (16.5, 30.1) min vs. 38.3 (28.3, 48.3) min, U=32.00, P<0.001], a 30.4% reduction in equipment idle rate [8.7% (5.1%, 12.3%) vs. 12.5% (7.4%, 17.6%), U=251.00, P=0.003], and an increase in patient satisfaction from 88.2% (1 519/1 723) to 94.3% (2 186/2 318) ( t=7.26, P<0.001). User research confirmed that the functions most favored by clinicians and patients were "dental chair parameter updating and clinical data integration" [74.7% (80/107)] and "chairside display of diagnostic images" [76.8% (119/155)], respectively. Looking forward, the intelligent platform has the potential to integrate artificial intelligence-assisted diagnosis and 5G-enabled multicenter collaboration to further expand its clinical applications and accelerate the digital transformation of dental healthcare.

OBJECTIVE: To explore, identify, and develop novel blood-based indicators using machine learning algorithms for accurate preoperative assessment and effective prediction of postoperative complication risks in patients with rheumatoid arthritis (RA) undergoing total knee arthroplasty (TKA). METHODS: A retrospective cohort study was conducted including RA patients who underwent unilateral TKA between January 2019 and December 2024. Inpatient and 30-day postoperative outpatient follow-up data were collected. Six machine learning algorithms, including decision tree, random forest, logistic regression, support vector machine, extreme gradient boosting, and light gradient boosting machine, were used to construct predictive models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), F1-score, accuracy, precision, and recall. SHapley Additive exPlanations (SHAP) values were employed to interpret and rank the importance of individual variables. RESULTS: According to the inclusion criteria, a total of 1 548 patients were enrolled. Ultimately, 18 preoperative indicators were identified as effective predictive features, and 8 postoperative complications were defined as prediction labels for inclusion in the study. Within 30 days after surgery, 453 patients (29.2%) developed one or more complications. Considering overall accuracy, precision, recall, and F1-score, the random forest model [AUC=0.930, 95% CI (0.910, 0.950)] and the extreme gradient boosting model [AUC=0.909, 95% CI (0.880, 0.938)] demonstrated the best predictive performance. SHAP analysis revealed that anti-cyclic citrullinated peptide antibody, C-reactive protein, rheumatoid factor, interleukin-6, body mass index, age, and smoking status made significant contributions to the overall prediction of postoperative complications. CONCLUSION Machine learning-based models enable accurate prediction of postoperative complication risks among RA patients undergoing TKA. Inflammatory and immune-related blood biomarkers, such as anti-cyclic citrullinated peptide antibody, C-reactive protein, and rheumatoid factor, interleukin-6, play key predictive roles, highlighting their potential value in perioperative risk stratification and individualized management.
Humans ; Arthroplasty, Replacement, Knee/adverse effects* ; Arthritis, Rheumatoid/blood* ; Machine Learning ; Postoperative Complications/blood* ; Female ; Male ; Retrospective Studies ; Middle Aged ; Aged ; Risk Factors ; Preoperative Period ; C-Reactive Protein/analysis* ; Risk Assessment

Corticotomy is a clinical procedure to accelerate orthodontic tooth movement characterized by the regional acceleratory phenomenon (RAP). Despite its therapeutic effects, the surgical risk and unclear mechanism hamper the clinical application. Numerous evidences support macrophages as the key immune cells during bone remodeling. Our study discovered that the monocyte-derived macrophages primarily exhibited a pro-inflammatory phenotype that dominated bone remodeling in corticotomy by CX3CR1^CreERT2; R26^GFP lineage tracing system. Fluorescence staining, flow cytometry analysis, and western blot determined the significantly enhanced expression of binding immunoglobulin protein (BiP) and emphasized the activation of sensor activating transcription factor 6 (ATF6) in macrophages. Then, we verified that macrophage specific ATF6 deletion (ATF6^f/f; CX3CR1^CreERT2 mice) decreased the proportion of pro-inflammatory macrophages and therefore blocked the acceleration effect of corticotomy. In contrast, macrophage ATF6 overexpression exaggerated the acceleration of orthodontic tooth movement. In vitro experiments also proved that higher proportion of pro-inflammatory macrophages was positively correlated with higher expression of ATF6. At the mechanism level, RNA-seq and CUT&Tag analysis demonstrated that ATF6 modulated the macrophage-orchestrated inflammation through interacting with Tnfα promotor and augmenting its transcription. Additionally, molecular docking simulation and dual-luciferase reporter system indicated the possible binding sites outside of the traditional endoplasmic reticulum-stress response element (ERSE). Taken together, ATF6 may aggravate orthodontic bone remodeling by promoting Tnfα transcription in macrophages, suggesting that ATF6 may represent a promising therapeutic target for non-invasive accelerated orthodontics.
Animals ; Mice ; Macrophages/metabolism* ; Tumor Necrosis Factor-alpha/genetics* ; Tooth Movement Techniques/methods* ; Activating Transcription Factor 6/metabolism* ; Bone Remodeling ; Flow Cytometry ; Blotting, Western

Objective To predict the invasion degree of subsolid nodule(SSN)lung adenocarcinoma using a combined model incorporating artificial intelligence(AI)quantitative parameters and imaging signs,and to validate the predictive efficacy of this model.Methods A total of 281 SSN lung adenocarcinoma CT images in 243 patients were retrospectively collected and randomly divided into training set(224 cases)and validation set(57 cases)in an 8∶2 ratio,with atypical adenomatous hyperplasia(A AH)+adenocarcinoma in situ(AIS)+minimally invasive adenocarcinoma(MIA)(191 cases)as the non-invasive adenocarcinoma(I AC)group and I AC(90 cases)as the IAC group.Multivariate logistic regression analysis was performed based on the AI quantitative parameters and CT signs in the training set to obtain independent predictors of IAC.A combined model and nomogram were then constructed and validated.The diagnostic efficacy and clinical applicability of the model were evaluated by the receiver operating characteristic(ROC)curve,calibration curve,and clinical decision curve analysis(DCA).Results Multivariate logistic regression analysis of the training set showed nodule type,spicule sign,vascular abnormality,long diameter＞11.5 mm,median CT value＞—426.25 HU,and mass＞391.5 mg were independent predictors of IAC(P＜0.05).The area under the curve(AUC)of the training set model,based on these independent predictive factors,was 0.915[95％confidence interval(CI)0.875-0.954],and the AUC of the validation set model was 0.903(95％CI 0.824-0.982),indicating both the training set and validation set models had high efficacy in distinguishing IAC.The nomogram model,which quantified these independent factors,demonstrated enhanced predictive power for IAC.The calibration curve indicated good fit of the prediction model,and the clinical DCA showed the model had good clinical applicability.Conclusion The model combining AI quantitative parameters and imaging signs has a higher ability to predict the risk of IAC,compared to a single indicator.It helps clinicians in determining the appropriate surgical timing,formulating surgical methods,and reducing overtreatment.

To address the problem of data silos in dental specialties caused by equipment heterogeneity, this study developed an Intelligent Internet of Things (IoT)-enabled dental chair platform (hereinafter referred to as the intelligent platform) based on the concept of medical-engineering integration. The platform adopts a three-tier chair-domain interconnection architecture: the bottom tier integrates multi-source sensors and standardized interfaces for automated data acquisition and linkage with hospital information systems; the middle tier provides clinic-level management and remote teaching collaboration; and the top tier employs a blockchain-based secure cloud database for resource allocation and data management. Clinical validation at The Affiliated Stomatological Hospital of Nanjing Medical University demonstrated that, compared with a control group from the same period in 2023, the trial group achieved a 38.0% increase in average daily patient visits (80.6±6.8 vs. 58.4±5.2, t=15.16, P<0.001), a 24.6% reduction in average treatment time [(36.1±6.3) min vs. (47.9±8.5) min, t=7.72, P<0.001], a 39.2% reduction in waiting time [23.3 (16.5, 30.1) min vs. 38.3 (28.3, 48.3) min, U=32.00, P<0.001], a 30.4% reduction in equipment idle rate [8.7% (5.1%, 12.3%) vs. 12.5% (7.4%, 17.6%), U=251.00, P=0.003], and an increase in patient satisfaction from 88.2% (1 519/1 723) to 94.3% (2 186/2 318) ( t=7.26, P<0.001). User research confirmed that the functions most favored by clinicians and patients were "dental chair parameter updating and clinical data integration" [74.7% (80/107)] and "chairside display of diagnostic images" [76.8% (119/155)], respectively. Looking forward, the intelligent platform has the potential to integrate artificial intelligence-assisted diagnosis and 5G-enabled multicenter collaboration to further expand its clinical applications and accelerate the digital transformation of dental healthcare.

Objective To predict the invasion degree of subsolid nodule(SSN)lung adenocarcinoma using a combined model incorporating artificial intelligence(AI)quantitative parameters and imaging signs,and to validate the predictive efficacy of this model.Methods A total of 281 SSN lung adenocarcinoma CT images in 243 patients were retrospectively collected and randomly divided into training set(224 cases)and validation set(57 cases)in an 8∶2 ratio,with atypical adenomatous hyperplasia(A AH)+adenocarcinoma in situ(AIS)+minimally invasive adenocarcinoma(MIA)(191 cases)as the non-invasive adenocarcinoma(I AC)group and I AC(90 cases)as the IAC group.Multivariate logistic regression analysis was performed based on the AI quantitative parameters and CT signs in the training set to obtain independent predictors of IAC.A combined model and nomogram were then constructed and validated.The diagnostic efficacy and clinical applicability of the model were evaluated by the receiver operating characteristic(ROC)curve,calibration curve,and clinical decision curve analysis(DCA).Results Multivariate logistic regression analysis of the training set showed nodule type,spicule sign,vascular abnormality,long diameter＞11.5 mm,median CT value＞—426.25 HU,and mass＞391.5 mg were independent predictors of IAC(P＜0.05).The area under the curve(AUC)of the training set model,based on these independent predictive factors,was 0.915[95％confidence interval(CI)0.875-0.954],and the AUC of the validation set model was 0.903(95％CI 0.824-0.982),indicating both the training set and validation set models had high efficacy in distinguishing IAC.The nomogram model,which quantified these independent factors,demonstrated enhanced predictive power for IAC.The calibration curve indicated good fit of the prediction model,and the clinical DCA showed the model had good clinical applicability.Conclusion The model combining AI quantitative parameters and imaging signs has a higher ability to predict the risk of IAC,compared to a single indicator.It helps clinicians in determining the appropriate surgical timing,formulating surgical methods,and reducing overtreatment.

The prefrontal cortex and hippocampus may support sequential working memory beyond episodic memory and spatial navigation. This stereoelectroencephalography (SEEG) study investigated how the dorsolateral prefrontal cortex (DLPFC) interacts with the hippocampus in the online processing of sequential information. Twenty patients with epilepsy (eight women, age 27.6 ± 8.2 years) completed a line ordering task with SEEG recordings over the DLPFC and the hippocampus. Participants showed longer thinking times and more recall errors when asked to arrange random lines clockwise (random trials) than to maintain ordered lines (ordered trials) before recalling the orientation of a particular line. First, the ordering-related increase in thinking time and recall error was associated with a transient theta power increase in the hippocampus and a sustained theta power increase in the DLPFC (3-10 Hz). In particular, the hippocampal theta power increase correlated with the memory precision of line orientation. Second, theta phase coherences between the DLPFC and hippocampus were enhanced for ordering, especially for more precisely memorized lines. Third, the theta band DLPFC → hippocampus influence was selectively enhanced for ordering, especially for more precisely memorized lines. This study suggests that theta oscillations may support DLPFC-hippocampal interactions in the online processing of sequential information.
Adult ; Female ; Humans ; Young Adult ; Epilepsy ; Hippocampus ; Memory, Short-Term ; Mental Recall ; Prefrontal Cortex ; Theta Rhythm ; Male

Objective:To explore the protective mechanism of tea polyphenols (TP) on mouse oral cancer.Methods:A total of 50 mice were divided into control group, model group, TP group, Selisistat group, TP+ Selisistat group, with 10 mice in each group. The control group was gavaged with physiological saline, while the model group, TP group, Selisistat group, and TP+ Selisistat group were gavaged with 300 mg/L 4-NQO to establish a mouse oral cancer model. Physiological saline, 200 mg/kg TP, 0.01 mg/kg Selisistat, and 200 mg/kg TP+ 0.01 mg/kg Selisistat were gavaged respectively. The weight changes of each group of mice were compared; HE staining was used to observe the morphology of mouse oral tumor tissue; Enzyme linked immunosorbent assay was used to detect the levels of malondialdehyde (MDA) and superoxide dismutase (SOD) in serum; Immunoblotting and immunohistochemistry were used to detect the expression of silencing information regulatory factor (Sirt1) and nuclear factor E2 related factor 2 (Nrf2) proteins in mouse oral tissues.Results:Compared with the control group, the model group mice had a decrease in body weight [(23.19±1.36)g], a decrease in serum SOD level [(91.64±8.75)U/ml], an increase in MDA level [(5.18±0.46)nmol/ml], a decrease in Sirt1 (0.38±0.05) and Nrf2 (0.36±0.05) protein expression in oral tissue, and an increase in Nrf2 acetylation level (0.84±0.11) (all P<0.05). Compared with the model group, the TP group mice had an increase in body weight [(25.28±1.25)g], elevated serum SOD levels [(121.24±10.68)U/ml], decreased MDA levels [(3.89±0.42)nmol/ml], increased expression of Sirt1 (0.61±0.09) and Nrf2 (0.58±0.06) proteins in oral tissue, and decreased Nrf2 protein acetylation levels (0.39±0.05); The Selisistat group mice showed a decrease in body weight [(21.41±1.07)g], a decrease in serum SOD levels [(72.16±7.43)U/ml], an increase in MDA levels [(5.87±0.41)nmol/ml], a decrease in Sirt1 (0.23±0.04) and Nrf2 protein (0.24±0.03) expression in oral tissue, and an increase in Nrf2 acetylation levels (1.12±0.14) ( P<0.05). The body weight [(23.32±1.27)g], serum SOD levels [(92.58±8.13)U/ml], and oral Sirt1 (0.41±0.06) and Nrf2 (0.38±0.05) protein expression in the TP+ Selisistat group mice were higher than those in the Selisistat group, while MDA [(5.11±0.38)nmol/ml] and Nrf2 acetylation levels (0.82±0.09) were lower than those in the Selisistat group (all P<0.05). Conclusions:Tea polyphenols can alleviate oral tissue damage and alleviate oxidative stress in mice with oral cancer, and their mechanism may be related to the upregulation of the Sirt1/Nrf2 pathway.