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: Synthetic electronic health records (EHRs) generated by large language models (LLMs) offer potential for clinical education and model training while addressing privacy concerns. However, performance variations and demographic biases in these models remain underexplored, posing risks to equitable health care. Objective: This study aimed to systematically assess the performance of various LLMs in generating synthetic EHRs and to critically evaluate the presence of gender and racial biases in the generated outputs. We focused on assessing the completeness and representativeness of these EHRs across 20 diseases with varying demographic prevalence. Methods: A framework was developed to generate 140,000 synthetic EHRs using 10 standardized prompts across 7 LLMs. The electronic health record performance score (EPS) was introduced to quantify completeness, while the statistical parity difference (SPD) was proposed to assess the degree and direction of demographic bias. Chi-square tests were used to evaluate the presence of bias across demographic groups. Results: Larger models exhibited superior performance but heightened biases. The Yi-34B achieved the highest EPS (96.8), while smaller models (Qwen-1.8B: EPS=63.35) underperformed. Sex polarization emerged: female-dominated diseases (eg, multiple sclerosis) saw amplified female representation in outputs (Qwen-14B: 973/1000, 97.3% female vs 564,424/744,778, 75.78% real; SPD=+21.50%), while balanced diseases and male-dominated diseases skewed the male group (eg, hypertension Llama 2-13 B: 957/1000, 95.7% male vs 79,540,040/152,466,669, 52.17% real; SPD=+43.50%). Racial bias patterns revealed that some models overestimated the representation of White (eg, Yi-6B: mean SPD +14.40%, SD 16.22%) or Black groups (eg, Yi-34B: mean SPD +14.90%, SD 27.16%), while most models systematically underestimated the representation of Hispanic (average SPD across 7 models is –11.93%, SD 8.36%) and Asian groups (average SPD across 7 models is –0.77%, SD 11.99%). Conclusions: Larger models, such as Yi-34B, Qwen-14B, and Llama 2 to 13 B, showed improved performance in generating more comprehensive EHRs, as reflected in higher EPS values. However, this increased performance was accompanied by a notable escalation in both gender and racial biases, highlighting a performance-bias trade-off. The study identified 4 key findings as follows: (1) as model size increased, EHR generation improved, but demographic biases also became more pronounced; (2) biases were observed across all models, not just the larger ones; (3) gender bias closely aligned with real-world disease prevalence, while racial bias was evident in only a subset of diseases; and (4) racial biases varied, with some diseases showing overrepresentation of White or Black populations and underrepresentation of Hispanic and Asian groups. These findings underline the need for effective bias mitigation strategies and the development of benchmarks to ensure fairness in artificial intelligence applications for health care.

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.