TY - JOUR AU - Tan, Jiaxing AU - Yang, Rongxin AU - Xiao, Liyin AU - Dong, Lingqiu AU - Zhong, Zhengxia AU - Zhou, Ling AU - Qin, Wei PY - 2025/3/10 TI - Risk Stratification in Immunoglobulin A Nephropathy Using Network Biomarkers: Development and Validation Study JO - J Med Internet Res SP - e65563 VL - 27 KW - IgA nephropathy KW - unsupervised learning KW - network biomarker KW - metabolomics KW - gut microbiota KW - biomarkers KW - risk stratification KW - IgA KW - immunoglobulin A KW - renal biopsy KW - renal KW - prospective cohort KW - Berger disease KW - synpharyngitic glomerulonephritis KW - kidney KW - immune system KW - glomerulonephritis KW - kidney inflammation KW - chronic kidney disease KW - renal disease KW - nephropathy KW - nephritis N2 - Background: Traditional risk models for immunoglobulin A nephropathy (IgAN), which primarily rely on renal indicators, lack comprehensive assessment and therapeutic guidance, necessitating more refined and integrative approaches. Objective: This study integrated network biomarkers with unsupervised learning clustering (k-means clustering based on network biomarkers [KMN]) to refine risk stratification in IgAN and explore its clinical value. Methods: Involving a multicenter prospective cohort, we analyzed 1460 patients and validated the approach externally with 200 additional patients. Deeper metabolic and microbiomic insights were gained from 2 distinct cohorts: 63 patients underwent ultraperformance liquid chromatography?mass spectrometry, while another 45 underwent fecal 16S RNA sequencing. Our approach used hierarchical clustering and k-means methods, using 3 sets of indicators: demographic and renal indicators, renal and extrarenal indicators, and network biomarkers derived from all indicators. Results: Among 6 clustering methods tested, the KMN scheme was the most effective, accurately reflecting patient severity and prognosis with a prognostic accuracy area under the curve (AUC) of 0.77, achieved solely through cluster grouping without additional indicators. The KMN stratification significantly outperformed the existing International IgA Nephropathy Prediction Tool (AUC of 0.72) and renal function-renal histology grading schemes (AUC of 0.69). Clinically, this stratification facilitated personalized treatment, recommending angiotensin-converting enzyme inhibitors or angiotensin receptor blockers for lower-risk groups and considering immunosuppressive therapy for higher-risk groups. Preliminary findings also indicated a correlation between IgAN progression and alterations in serum metabolites and gut microbiota, although further research is needed to establish causality. Conclusions: The effectiveness and applicability of the KMN scheme indicate its substantial potential for clinical application in IgAN management. UR - https://www.jmir.org/2025/1/e65563 UR - http://dx.doi.org/10.2196/65563 UR - http://www.ncbi.nlm.nih.gov/pubmed/40063072 ID - info:doi/10.2196/65563 ER - TY - JOUR AU - Li, Yanong AU - He, Yixuan AU - Liu, Yawei AU - Wang, Bingchen AU - Li, Bo AU - Qiu, Xiaoguang PY - 2025/1/30 TI - Identification of Intracranial Germ Cell Tumors Based on Facial Photos: Exploratory Study on the Use of Deep Learning for Software Development JO - J Med Internet Res SP - e58760 VL - 27 KW - deep learning KW - facial recognition KW - intracranial germ cell tumors KW - endocrine indicators KW - software development KW - artificial intelligence KW - machine learning models KW - software engineering KW - neural networks KW - algorithms KW - cohort studies N2 - Background: Primary intracranial germ cell tumors (iGCTs) are highly malignant brain tumors that predominantly occur in children and adolescents, with an incidence rate ranking third among primary brain tumors in East Asia (8%-15%). Due to their insidious onset and impact on critical functional areas of the brain, these tumors often result in irreversible abnormalities in growth and development, as well as cognitive and motor impairments in affected children. Therefore, early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life. Objective: This study aimed to investigate the application of facial recognition technology in the early detection of iGCTs in children and adolescents. Early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life. Methods: A multicenter, phased approach was adopted for the development and validation of a deep learning model, GVisageNet, dedicated to the screening of midline brain tumors from normal controls (NCs) and iGCTs from other midline brain tumors. The study comprised the collection and division of datasets into training (n=847, iGCTs=358, NCs=300, other midline brain tumors=189) and testing (n=212, iGCTs=79, NCs=70, other midline brain tumors=63), with an additional independent validation dataset (n=336, iGCTs=130, NCs=100, other midline brain tumors=106) sourced from 4 medical institutions. A regression model using clinically relevant, statistically significant data was developed and combined with GVisageNet outputs to create a hybrid model. This integration sought to assess the incremental value of clinical data. The model?s predictive mechanisms were explored through correlation analyses with endocrine indicators and stratified evaluations based on the degree of hypothalamic-pituitary-target axis damage. Performance metrics included area under the curve (AUC), accuracy, sensitivity, and specificity. Results: On the independent validation dataset, GVisageNet achieved an AUC of 0.938 (P<.01) in distinguishing midline brain tumors from NCs. Further, GVisageNet demonstrated significant diagnostic capability in distinguishing iGCTs from the other midline brain tumors, achieving an AUC of 0.739, which is superior to the regression model alone (AUC=0.632, P<.001) but less than the hybrid model (AUC=0.789, P=.04). Significant correlations were found between the GVisageNet?s outputs and 7 endocrine indicators. Performance varied with hypothalamic-pituitary-target axis damage, indicating a further understanding of the working mechanism of GVisageNet. Conclusions: GVisageNet, capable of high accuracy both independently and with clinical data, shows substantial potential for early iGCTs detection, highlighting the importance of combining deep learning with clinical insights for personalized health care. UR - https://www.jmir.org/2025/1/e58760 UR - http://dx.doi.org/10.2196/58760 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/58760 ER -