Depression and anxiety are prevalent mental health conditions among individuals with type 2 diabetes mellitus (T2DM), who exhibit unique vulnerabilities and etiologies. However, existing approaches fail to fully utilize regional heterogeneous electronic health record (EHR) data. Integrating this data can provide a more comprehensive understanding of depression and anxiety in T2DM patients, leading to more personalized treatment strategies. This study aims to develop and validate a deep learning model, the Regional EHR for Depression and Anxiety Prediction Model (REDAPM), using regional EHR data to predict depression and anxiety in patients with T2DM. A case-control development and validation study was conducted using regional EHR data from the Nanjing Health Information Center (NHIC). Two retrospective, matched (1:3) datasets were constructed from the full cohort for the model's internal and external validation. These two datasets were selected from the NHIC data of 2020 and 2022, respectively. The REDAPM incorporates both structured and unstructured EHR data, capturing the temporal dependency of clinical events. The performance of REDAPM was compared to a set of baseline models, evaluated using the area under the receiver operating characteristic curve (ROC-AUC) and the area under the precision-recall curve (PR-AUC). Subgroup, ablation, and interpretation analyses were conducted to identify relevant clinical features available from EHRs. The internal and external validation datasets comprised 24,724 and 34,340 patients, respectively. The REDAPM outperformed baseline models in both datasets, achieving ROC-AUC scores of 0.9029±0.008 and 0.7360±0.005, and PR-AUC scores of 0.8124±0.011 and 0.5504±0.009. Ablation and subgroup experiments confirmed the significant contribution of patients' medical history text to the model's performance. Integrated gradient score analysis identified the predictive importance of other mental disorders. The REDAPM effectively leverages the heterogeneous characteristics of regional EHR data, demonstrating strong predictive performance for depression onset in diabetic patients. It also shows potential for discovering significant clinical features, indicating considerable promise for clinical utility.

Objective: Due to heterogeneity and limited medical data in primary healthcare services (PHS), assessing the psychological risk of type 2 diabetes mellitus (T2DM) patients in PHS is difficult. Using unsupervised contrastive pre-training, we proposed a deep learning framework named depression and anxiety prediction (DAP) to predict depression and anxiety in T2DM patients. Materials and Methods: The DAP model consists of two sub-models. Firstly, the pre-trained model of DAP used unlabeled discharge records of 85 085 T2DM patients from the First Affiliated Hospital of Nanjing Medical University for unsupervised contrastive learning on heterogeneous electronic health records (EHRs). Secondly, the fine-tuned model of DAP used case–control cohorts (17 491 patients) selected from 149 596 T2DM patients’ EHRs in the Nanjing Health Information Platform (NHIP). The DAP model was validated in 1028 patients from PHS in NHIP. Evaluation included receiver operating characteristic area under the curve (ROC-AUC) and precision-recall area under the curve (PR-AUC), and decision curve analysis (DCA). Results: The pre-training step allowed the DAP model to converge at a faster rate. The fine-tuned DAP model significantly outperformed the baseline models (logistic regression, extreme gradient boosting, and random forest) with ROC-AUC of 0.91±0.028 and PR-AUC of 0.80±0.067 in 10-fold internal validation, and with ROC-AUC of 0.75 ± 0.045 and PR-AUC of 0.47 ± 0.081 in external validation. The DCA indicate the clinical potential of the DAP model. Conclusion: The DAP model effectively predicted post-discharge depression and anxiety in T2DM patients from PHS, reducing data fragmentation and limitations. This study highlights the DAP model’s potential for early detection and intervention in depression and anxiety, improving outcomes for diabetes patients.

Background: Primary hypertension (PH) poses significant risks to children and adolescents. Few prediction models for the risk of PH in children and adolescents currently exist, posing a challenge for doctors in making informed clinical decisions. Objective: This study aimed to investigate the incidence and risk factors of PH in Chinese children and adolescents. It also aimed to establish and validate a nomogram-based model for predicting the next year’s PH risk. Methods: A training cohort (n=3938, between January 1, 2008, and December 31, 2020) and a validation cohort (n=1269, between January 1, 2021, and July 1, 2023) were established for model training and validation. An independent cohort of 576 individuals was established for external validation of the model. The result of the least absolute shrinkage and selection operator regression technique was used to select the optimal predictive features, and multivariate logistic regression to construct the nomogram. The performance of the nomogram underwent assessment and validation through the area under the receiver operating characteristic curve, concordance index, calibration curves, decision curve analysis, clinical impact curves, and sensitivity analysis. Results: The PH risk factors that we have ultimately identified include gender (odds ratio [OR] 3.34, 95% CI 2.88 to 3.86; P<.001), age (OR 1.11, 95% CI 1.08 to 1.14; P<.001), family history of hypertension (OR 42.74, 95% CI 23.07 to 79.19; P<.001), fasting blood glucose (OR 6.07, 95% CI 4.74 to 7.78; P<.001), low-density lipoprotein cholesterol (OR 2.03, 95% CI 1.60 to 2.57; P<.001), and uric acid (OR 1.01, 95% CI 1.01 to 1.01; P<.001), while factor breastfeeding (OR 0.04, 95% CI 0.03 to 0.05; P<.001) has been identified as a protective factor. Subsequently, a nomogram has been constructed incorporating these factors. Areas under the receiver operating characteristic curves of the nomogram were 0.892 in the training cohort, 0.808 in the validation cohort, and 0.790 in the external validation cohort. Concordance indexes of the nomogram were 0.892 in the training cohort, 0.808 in the validation cohort, and 0.790 in the external validation cohort. The nomogram has been proven to have good clinical benefits and stability in calibration curves, decision curve analysis, clinical impact curves, and sensitivity analysis. Finally, we observed noteworthy differences in uric acid levels and family history of hypertension among various subgroups, demonstrating a high correlation with PH. Moreover, the web-based calculator of the nomogram was built online. Conclusions: We have developed and validated a stable and reliable nomogram that can accurately predict PH risk within the next year among children and adolescents in primary care and offer effective and cost-efficient support for clinical decisions for the risk prediction of PH.

Purpose To study epidemiology, complications, risk factors, clinical course and treatment patterns of diabetes, the Nanjing Diabetes Cohort (NDC) was established using anonymised electronic health records from 650 hospitals and primary care since 2020. This cohort provides valuable data for researchers and policy-makers focused on diabetes management and public health strategies. Participants Diabetes was defined as having inpatient or outpatient encounters with a diagnosis of diabetes International Classification of Diseases-9/10 codes, any use of insulin or oral hypoglycaemic drugs, or one encounter with haemoglobin A1C >4.8 mmol/mol or 6.5%. Patients with diabetes have been continuously enrolled on hospitals and primary care in Nanjing since 2020. Demographic, medications and comorbidities data were extracted from clinical notes, diagnostic codes, labs, prescriptions and vital signs among different types of diabetes. Findings to date The NDC consisted of 1 033 904 patients from 1 January 2020 to 31 December 2022, the majority were male (50.62%) and from the Gulou district (30.79%). The clinical characteristics and medication usage of patients with type 1 diabetes, type 2 diabetes, gestational diabetes and other diabetes were assessed. The prevalences of hypertension, ischemic heart disease, and cerebrovascular disease were 49.72%, 17.85% and 24.90%, respectively. Future plans NDC will annually enrol eligible patients and include socioeconomic data in future updates. The data of NDC are maintained by the Department of Medical Informatics at Nanjing Medical University.

BACKGROUND With the development of the Internet, online medical community can help patient access to medical information and relevant decisions more conveniently, and meet the needs of patients for their own healthcare management. Mining these Q&A (Question and Answer) data, we can help doctors give more targeted feedback which improve the efficiency of question-and-answer, and patient satisfaction. OBJECTIVE This study aimed to (1) analysis frequency and position of diabetes related diseases or symptoms in Q&A website and (2) find out the differences of disease terms in gender and age using in the questions. METHODS We collected 5766 Q&A diabetes related data on the website of Chunyuyisheng from June 2012 to April 2020. In 38176 combined sentences, a vocabulary contains 3 categories of 3851 word and 2094 ICD (International Classification of Diseases) matching terms were obtained by calculating the similarity using word vectors. Proportion of the frequency of words and Mann-Whitney U test on word position were used to quantify the difference in patient’s gender and age group. RESULTS The vocabulary of the disease category accounts for 70%. We analyzed the word frequency and position in questions for different gender and age group. For gender, women participate in question answering more, accounting for 53% of total questions. They pay more attention to pregnancy, sleep and thyroid gland related vocabulary compared to men. Men focus more on circulation system, kidney failure related vocabulary. For different age group, pregnancy, glucose regulation, digestive and respiratory system related vocabulary have a higher proportion for patients under 40 years old. Patients over 40 years old pay more attention on kidney failure, cerebral ischaemia, infectious and circulation system. CONCLUSIONS This study provides a new insight into frequency and position of diabetes related diseases or symptoms in online medical services. It can show patients’ different attention by comparing disease or symptom categories for gender and age with ICD disease codes. The frequency and position of disease category words in patients’ conversation can be used for further risk evaluation for chronic diseases research.

BACKGROUND Online health communities (OHCs) are important channels for families of children with autism spectrum disorder to obtain health information and psychosocial support. Differences between an open forum platform and the physician-patient consultation platforms may shape caregiver decisions, yet comparative evidence from China remains limited. A large language model (LLM) provides a scalable approach for systematic content annotation in large OHC datasets. OBJECTIVE This study proposes and validates a standardized LLM-assisted annotation framework under a unified classification schema and compares topic distributions and poster identities across an open forum platform (Baidu Tieba) and physician-patient consultation platforms (Chunyu Doctor and Haodf). METHODS We implemented an LLM-assisted annotation framework. A unified taxonomy of topics and poster identities was first developed through human open coding. Poster identities in Baidu Tieba were annotated through a double-blind manual procedure. For topic classification, interannotator and human-LLM agreement were evaluated on a manually labeled subset to benchmark models of varying sizes. The best-performing LLM was selected for full-dataset topic annotation, followed by statistical and cross-platform analysis. RESULTS When metrics were arithmetically averaged across all annotation tasks, the best-performing LLM achieved agreement levels comparable to human annotation (accuracy=79.18%, SD 0.20%; κ=0.736, SD 0.003; F1-score=0.727, SD 0.006), approaching interannotator agreement (accuracy=81.65%; κ=0.767; F1-score=0.758), demonstrating strong stability and scalability. Full-dataset analysis yielded 3 main findings. First, model performance increased with parameter scale but plateaued beyond 14B, indicating diminishing marginal returns from further scaling. Second, clear cross-platform differences in poster identity were observed: the open forum platform was dominated by family members of patients (caregivers: 2377/3516, 67.61%), with substantial participation from commercial rehabilitation practitioners (commercial posters: 427/3516, 12.14%), resulting in a more heterogeneous participation structure. Third, topic distributions reflected both shared high demand for resource-related information and differentiated help-seeking pathways: both platform types demonstrated consistently high demand for resource recommendation and evaluation; the open forum platform was primarily characterized by diagnosis-related discussions (1183/7535, 15.70%), whereas the physician-patient consultation platforms were centered on intervention-related consultation (2864/7687, 37.26%). CONCLUSIONS The LLM-assisted annotation framework proposed in this study enables reliable large-scale annotation of OHC data while maintaining high human-LLM agreement and operational stability. Midsized models (eg, 14B) demonstrated favorable cost-performance efficiency. The findings reveal 2 key aspects: the open forum platform exhibits a complex participation structure, and the influence of commercially affiliated actors should not be overlooked; users on both platform types show sustained demand for resource-related information but follow different help-seeking pathways, emphasizing diagnostic exploration and professional intervention, respectively. These results suggest that platform structure and governance mechanisms may shape caregivers’ information access and decision-making. The framework provides a transparent, reproducible, and cost-effective approach for OHC research. All data were deidentified and handled in accordance with relevant platform policies and ethical standards. CLINICALTRIAL