With the development of the internet, applications have become complicated, and the relevant technology has diversified. Compared with medical applications, the significance of information technology has been expanding to include clinical auxiliary functions of medical information. This includes electronic medical records, electronic prescriptions, medical information systems, etc. Although research on the data processing structure and format of various related systems is becoming mature, the integration is insufficient. An integrated medical information system with security policy and privacy protection, which combines e-patient records, e-prescriptions, modified smart cards, and fingerprint identification systems, and applies proxy signature and group signature, is proposed in this study. This system effectively applies and saves medical resources—satisfying the mobility of medical records, presenting the function, and security of medicine collection, and avoiding medical conflicts and profiteering to further acquire the maximum effectiveness with the least resources. In this way, this medical information system may be developed into a comprehensive function that eliminates the transmission of manual documents and maintains the safety of patient medical information. It can improve the quality of medical care and indispensable infrastructure for medical management.

Magnetic resonance imaging (MRI), with its high resolution and radiation-free characteristics, has become a crucial tool for brain tumor diagnosis. We classified brain tumors into non-tumors, glioma, meningioma, and pituitary tumors by integrating public image datasets with preprocessing and data augmentation techniques and employing four deep learning models, such as a convolutional neural network (CNN), visual geometry group network 19 (VGGNet 9), residual network 101 version 2 (ResNet101V2), and efficient network version 2 b2 (EfficientNetV2B2). VGGNet19 and CNNs excelled in accuracy and stability, while EfficientNetV2B2 was efficient yet required refinement for specific categories, and ResNet101V2 benefited from further optimization. Deep learning significantly enhances diagnostic efficiency and accuracy, assisting clinical decision-making and improving patient survival rates.

Background/Objectives: Altered lumbar sagittal alignment is associated with degenerative and mechanical musculoskeletal disorders. However, conventional angle-based measurements, such as the Cobb angle, may not fully reflect the overall curvature pattern of the lumbar spine. This pilot study investigated whether curvature distribution profiling on sagittal lumbar radiographs is associated with clinically confirmed lumbar musculoskeletal disorders. Methods: This retrospective pilot study included 50 adults who underwent standing sagittal lumbar radiography. Patients were classified as disease-positive or disease-negative according to radiographic findings, short-term clinical follow-up, and chart review. Vertebral body centroids from T12 to S1 were manually identified to construct continuous lumbar curvature profiles. Curvature height was normalized to a standardized baseline for cross-case comparison. Distribution patterns of curvature deviation were analyzed between groups. Total curvature was also calculated as a quantitative descriptor of overall lumbar bending, and group-wise comparisons were performed using the Kruskal–Wallis test. Results: The disease-negative group showed a predominantly unimodal and symmetric curvature distribution, whereas the disease-positive group showed greater dispersion at both hypo-lordotic and hyper-lordotic extremes. The hypo-lordosis subgroup demonstrated a more consistent deviation pattern, whereas the hyper-lordosis subgroup partially overlapped with the disease-negative distribution. These pattern-based findings suggest that deviation from a central curvature profile, rather than lordosis magnitude alone, may be associated with lumbar musculoskeletal disorders. In exploratory quantitative analysis, total curvature showed a distributional shift in the disease-positive group, although the overall between-group difference did not reach statistical significance (p = 0.096). Conclusions: Curvature distribution profiling may provide complementary morphological information in conjunction with conventional angle-based assessment. Both reduced and exaggerated lumbar curvature patterns were observed in association with lumbar musculoskeletal disorders. Larger studies are needed to validate these preliminary findings and to determine the clinical relevance of this approach.