ObjectiveTo elucidate the critical role of rehabilitation medical records (including electronic records) in rehabilitation medicine's clinical practice and management, comprehensively analyzed the structure, core content and data standards of rehabilitation medical records, to develop a standardized medical record data architecture and core dataset suitable for rehabilitation medicine and to explore the application of rehabilitation data in performance evaluation and payment. MethodsBased on the regulatory documents Basic Specifications for Medical Record Writing and Basic Specifications for Electronic Medical Records (Trial) issued by National Health Commission of China, and referencing the World Health Organization (WHO) Family of International Classifications (WHO-FICs) classifications, International Classification of Diseases (ICD-10/ICD-11), International Classification of Functioning, Disability and Health (ICF), and International Classification of Health Interventions (ICHI Beta-3), this study constructed the data architecture, core content and data standards for rehabilitation medical records. Furthermore, it explored the application of rehabilitation record summary sheets (home page) data in rehabilitation medical statistics and payment methods, including Diagnosis-related Groups (DRG), Diagnosis-Intervention Packet (DIP) and Case Mix Index. ResultsThis study proposed a systematic standard framework for rehabilitation medical records, covering key components such as patient demographics, rehabilitation diagnosis, functional assessment, rehabilitation treatment prescriptions, progress evaluations and discharge summaries. The research analyzed the systematic application methods and data standards of ICD-10/ICD-11, ICF and ICHI Beta-3 in the fields of medical record terminology, coding and assessment. Constructing a standardized data structure and data standards for rehabilitation medical records can significantly improve the quality of data reporting based on the medical record summary sheet, thereby enhancing the quality control of rehabilitation services, effectively supporting the optimization of rehabilitation medical insurance payment mechanisms, and contributing to the establishment of rehabilitation medical performance evaluation and payment based on DRG and DIP. ConclusionStructured rehabilitation records and data standardization are crucial tools for quality control in rehabilitation. Systematically applying the three reference classifications of the WHO-FICs, and aligning with national medical record and electronic health record specifications, facilitate the development of a standardized rehabilitation record architecture and core dataset. Standardizing rehabilitation care pathways based on the ICF methodology, and developing ICF- and ICD-11-based rehabilitation assessment tools, auxiliary diagnostic and therapeutic systems, and supporting terminology and coding systems, can effectively enhance the quality of rehabilitation records and enable interoperability and sharing of rehabilitation data with other medical data, ultimately improving the quality and safety of rehabilitation services.

Objective To assess the accuracy of pN staging prediction in papillary thyroid carcinoma (PTC) using ultrasound radiomics and deep neural networks (DNN). Methods A retrospective analysis was conducted on 375 patients with pathologically confirmed PTC, comprising 261 cases in the training set and 114 in the test set. Staging was categorized as pN0 (no cervical lymph node metastasis), pN1a (central neck lymph node metastasis), and pN1b (lateral neck lymph node metastasis). An ultrasound physician manually segmented the regions of interest (ROIs) for PTC, extracting 1899 radiomic features. Dimensionality reduction was performed using the least absolute shrinkage and selection operator (LASSO) regression. A DNN model for predicting PTC pN staging was developed using the H2O deep learning platform, trained on the training set, and validated on the test set to assess the accuracy of the optimal model. Results A total of 153 patients were in the pN0 stage, 131 patients in the pN1a stage, and 91 patients in the pN1b stage. LASSO regression selected 15 radiomic features for each PTC. The optimal DNN model, constructed using these 15 features, achieved accuracies of 85.82% on the training set and 81.57% on the test set. Conclusion Ultrasound radiomics of PTC demonstrates high accuracy in predicting pN staging and shows potential for automating N staging in patients.

ObjectiveTo establish the specific chromatogram and quantitative analysis of multi-components by single-marker（QAMS） based on linear calibration using two reference substances（LCTRS）， explore the consistency between Hedyotis Herba dispensing granules and standard decoction， and evaluate the quality of the dispensing granules. MethodsHigh performance liquid chromatography（HPLC） specific chromatogram was established based on 15 batches of Hedyotis Herba standard decoction and 10 batches of the dispensing granules， and LCTRS was used to locate chromatographic peaks. The actual retention times of 7 characteristic peaks in the specific chromatogram was measured on 24 different types of C₁₈ columns， taking deacetyl asperulosidic acid and asperulosidic acid as the dual standard compounds， the retention times of the other 5 characteristic peaks were predicted and validated. Based on this， QAMS was developed to determine the contents of four components（deacetyl asperulosidic acid， deacetyl asperulosidic acid methyl ester， asperulosidic acid， and p-coumaric acid）. Then， the relative correction factors of deacetyl asperulosidic acid， deacetyl asperulosidic acid methyl ester and p-coumaric acid were calculated using the reference peak of asperulosidic acid in the dual standard compounds， and each component was quantified accordingly. Finally， the consistency between the dispensing granules and standard decoction was assessed by taking extract rate of the standard decoction， consistency of the specific chromatograms， contents and transfer rates of the indicator components as indexes， and the quality of the dispensing granules was evaluated. ResultsThere were 7 common peaks in the characteristic chromatogram of samples of Hedyotis Herba standard decoction and the dispensing granules， and four of them were identified by reference standards， namely deacetyl asperulosidic acid（peak 1）， deacetyl asperulosidic acid methyl ester（peak 3）， asperulosidic acid（peak 6） and p-coumaric acid（peak 7）. The similarity between the dispensing granules and the standard decoction was >0.9. The absolute deviation in the predicted retention time for each component by LCTRS was lower than that of the relative retention time method. The extract rate of the 15 batches of Hedyotis Herba standard decoction ranged from 7.89% to 14.60%， the contents of deacetyl asperulosidic acid， deacetyl asperulosidic acid methyl ester， asperulosidic acid and p-coumaric acid were 6.62-19.70， 3.83-17.99， 1.57-6.69， 1.62-4.52 mg·g^-1， and the transfer rates of these components from decoction pieces to the standard decoction were 22.89%-39.60%， 34.03%-62.24%， 24.25%-43.70%， and 40.58%-73.71%， respectively. The extract rate， index component contents and transfer rates from decoction pieces to the three batches of Hedyotis Herba dispensing granules（P1-P3）， produced by manufacturer A， were similar to those of the standard decoction prepared from the same batch of decoction pieces， and all fell within the specified range. The contents of the 4 indicator components in 7 batches of the dispensing granules（P4-P10） from manufacturers B-E were all within the range of the content converted from the standard decoction based on the quantity of the dispensing granules. ConclusionThe established specific chromatogram and QAMS based on LCTRS are reasonable and reliable. Based on the evaluation indicators of standard decoction yield， consistency of specific chromatograms， contents and transfer rates of the four index components， the 10 batches of Hedyotis Herba dispensing granules from various manufacturers have exhibited good consistency with the standard decoction， indicating that the current production process is relatively reasonable.

Objective To evaluate the performance of the artificial intelligence (AI)-enabled snail identification system for recognition of Oncomelania hupensis robertsoni and Tricula in schistosomiasis-endemic areas of Yunnan Province. Methods Fifty O. hupensis robertsoni and 50 Tricula samples were collected from Yongbei Township, Yongsheng County, Lijiang City, a schistosomiasis-endemic area in Yunnan Province in May 2024. A total of 100 snail sample images were captured with smartphones, including front-view images of 25 O. hupensis robertsoni and 25 Tricula samples (upward shell opening) and back-view images of 25 O. hupensis robertsoni and 25 Tricula samples (downward shell opening). Snail samples were identified as O. hupensis robertsoni or Tricula by schistosomiasis control experts with a deputy senior professional title and above according to image quality and morphological characteristics. A standard dataset for snail image classification was created, and served as a gold standard for recognition of snail samples. A total of 100 snail sample images were recognized with the AI-enabled intelligent snail identification system based on a WeChat mini program in smartphones. Schistosomiasis control professionals were randomly sampled from stations of schistosomisis prevention and control and centers for disease control and prevention in 18 schistosomiasis-endemic counties (districts, cities) of Yunnan Province, for artificial identification of 100 snail sample images. All professionals are assigned to two groups according the median years of snail survey experiences, and the effect of years of snail survey experiences on O. hupensis robertsoni sample image recognition was evaluated. A receiver operating characteristic (ROC) curve was plotted, and the sensitivity, specificity, accuracy, Youden’s index and the area under the curve (AUC) of the AI-enabled intelligent snail identification system and artificial identification were calculated for recognition of snail sample images. The snail sample image recognition results of AI-enabled intelligent snail identification system and artificial identification were compared with the gold standard, and the internal consistency of artificial identification results was evaluated with the Cronbach’s coefficient alpha. Results A total of 54 schistosomiasis control professionals were sampled for artificial identification of snail sample image recognition, with a response rate of 100% (54/54), and the accuracy, sensitivity, specificity, Youden’s index, and AUC of artificial identification were 90%, 86%, 94%, 0.80 and 0.90 for recognition of snail sample images, respectively. The overall Cronbach’s coefficient alpha of artificial identification was 0.768 for recognition of snail sample images, and the Cronbach’s coefficient alpha was 0.916 for recognition of O. hupensis robertsoni snail sample images and 0.925 for recognition of Tricula snail sample images. The overall accuracy of artificial identification was 90% for recognition of snail sample images, and there was no significant difference in the accuracy of artificial identification for recognition of O. hupensis robertsoni (86%) and Tricula snail sample images (94%) (χ² = 1.778, P > 0.05). There was no significant difference in the accuracy of artificial identification for recognition of snail sample images with upward (88%) and downward shell openings (92%) (χ² = 0.444, P > 0.05), and there was a significant difference in the accuracy of artificial identification for recognition of snail sample images between schistosomiasis control professionals with snail survey experiences of 6 years and less (75%) and more than 6 years (90%) (χ² = 7.792, P < 0.05). The accuracy, sensitivity, specificity and AUC of the AI-enabled intelligent snail identification system were 88%, 100%, 76% and 0.88 for recognition of O. hupensis robertsoni snail sample images, and there was no significant difference in the accuracy of recognition of O. hupensis robertsoni snail sample images between the AI-enabled intelligent snail identification system and artificial identification (χ² = 0.204, P > 0.05). In addition, there was no significant difference in the accuracy of artificial identification for recognition of snail sample images with upward (90%) and downward shell openings (86%) (χ² = 0.379, P > 0.05), and there was a significant difference in the accuracy of artificial identification for recognition of snail sample images between schistosomiasis control professionals with snail survey experiences of 6 years and less and more than 6 years (χ² = 5.604, P_adjusted < 0.025). Conclusions The accuracy of recognition of snail sample images is comparable between the AI-enabled intelligent snail identification system and artificial identification by schistosomiasis control professionals, and the AI-enabled intelligent snail identification system is feasible for recognition of O. hupensis robertsoni and Tricula in Yunnan Province.

ObjectiveTo construct a family-centered care model for children with tuberculosis based on the double ABC-X model, and to evaluate its clinical effects. MethodsFrom December 2022 to October 2023, 64 newly admitted children with tuberculosis who met the criteria and their caregivers were recruited from the tuberculosis department of Shanghai Public Health Clinical Center were randomly divided into an experimental group (32 cases) and a control group (32 cases).The control group was given a conventional health care, while the experimental group was given a family-centered health care intervention based on the double ABC-X model, in which a multidisciplinary care team provided personalized information and emotional support for the caregivers and their children. Medication adherence of the children, caregiver’s teading burden, and disease management competence were compared between the 2 groups. ResultsA total of 29 cases in the experimental group and 27 cases in the control group completed the intervention. At 12 weeks of intervention, the medication adherence score (7.72±0.45 vs 7.41±0.50, P<0.05) and disease management competence score (36.97±7.85 vs 31.56±7.30, P<0.05) were higher in the experimental group than that in the control group while the caregiving burden score (31.79±13.40 vs 40.04±9.01, P<0.05) and difficulty of disease management score (30.41±12.41 vs 38.56±9.48, P<0.05) were lower than that in the control group. At 24 weeks of intervention, the medication adherence score (7.34±0.97 vs 6.70±1.14, P<0.05) and disease management competence score (42.07±6.93 vs 35.63±7.32, P<0.05) were higher in the experimental group than that in the control group as well, but the caregiving burden score (31.62±11.72 vs 39.63±10.17, P<0.05) and difficulty of disease management score (30.59±10.87 vs 37.81±9.32, P<0.05) were lower than that in the control group. ConclusionFamily-centered care based on the double ABC-X model can effectively promote medication adherence among children with tuberculosis, reduce caregivers’ care burden and disease management difficulties, and improve caregiver’s disease management competence.

OBJECTIVE To provide suggestions for improving the path and system construction of patient engagement in drug regulation in China. METHODS By reviewing initiatives and experiences from the United States （U. S.）， European Union （EU）， and Japan in promoting patient engagement， this study summarizes the roles and contributions of patients in the entire drug regulatory process internationally. Combining China’s current progress and challenges in patient engagement， specific proposals are formulated to refine regulatory pathways and institutional systems. RESULTS & CONCLUSIONS With growing global emphasis on patient engagement as a regulatory strategy， countries or regions such as the U.S.， EU， and Japan have established clear policies， designated oversight agencies， and developed diversified pathways for patient engagement. Patients contribute to regulatory processes through advisory meetings， direct decision-making roles， and leveraging lived experiences and expertise to optimize drug evaluation and monitoring. In contrast， China’s patient engagement remains primarily limited to clinical value- oriented drug development， lacking formal policy guidance. It is recommended that China， based on its existing policy system， further strengthen the construction of a safeguard system for patient engagement， improve the capacity building and pathway models for patient participation in pharmaceutical regulation， and promote the continuous development of patient engagement in pharmaceutical regulation in our country.

OBJECTIVE To analyze and identify the metabolites of pirtobrutinib （PTN） in rats， and clarify the possible metabolic pathways of PTN in rats. METHODS Six rats were intragastrically administered with 10 mg/kg PTN suspension. Blood samples were collected from the rats 30 minutes before administration and at 0.25， 0.5， 1， 2， 4， 6， 8， 12， 24 hours after administration. Urine and feces samples were collected 12 hours before administration and 24 hours after administration. UHPLC- Orbitrap Exploris 240 system combined with Compound Discoverer 3.0 and Xcalibur 2.0 software were adopted for structural identification and metabolic pathway analysis of PTN metabolites in rat plasma， urine， and feces. RESULTS A total of 29 PTN metabolites were identified， including 17， 19 and 22 metabolites in plasma， urine and feces， respectively. The metabolic pathways of PTN mainly included oxidation， sulfation， glucuronidation， etc.， and its metabolites were mostly combination products of two or more different metabolic forms. In detail， a total of 26 metabolites were associated with phase Ⅰ metabolic reactions （14 oxidation metabolites， 9 reduction/dehydrogenation metabolites， 8 demethylation metabolites， and 5 hydrolysis metabolites）. Meanwhile， a total of 20 products were involved in phase Ⅱ metabolites （14 sulfation metabolites and 8 glucuronic acid binding metabolites）. CONCLUSIONS PTN exhibits a diverse range of metabolites in rat fecal samples， with the primary metabolic pathways being oxidation， sulfation， glucuronidation， and others.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.