Current Issue : October-December Volume : 2026 Issue Number : 4 Articles : 5 Articles
Accurately classifying gait abnormalities is crucial for the effective monitoring and rehabilitation of stroke patients. This study proposed a lightweight machine learning framework for distinguishing healthy from abnormal gait paerns using statistical features extracted from wearable gyroscope data. Statistical z-axis angular velocity values from both limbs were derived and used to evaluate the performance of multiple classifiers, including logistic regression, support vector machines, and ensemble methods. A leave-one-out cross-validation strategy was employed to enhance generalizability across subjects. The results indicated that several classifiers achieve accuracy and area under the curve (AUC) values exceeding 0.95, with random forest and support vector machine-based models demonstrating near-perfect class separability, with an AUC of 0.98. These findings highlighted the effectiveness of using minimal set of biomechanically relevant gyroscope features for gait classification in real-world healthcare applications. The proposed pipeline is computationally efficient, making it well suited for implementing in wearable and remote monitoring systems....
Different from isothermal amplification, for polymerase chain reaction (PCR), highly reliable valving for PCR chamber, significantly shortened thermal cycling time, and concise multiplexed detection are always challenges for microfluidic-based devices. Here, we present a real-time, centrifugal, plastic microfluidic chip for multiplexed PCR detection specifically based on the mechanism of cooperating valving. To achieve consistent amplification, a concise dual-valving strategy was developed. Instantly melted wax is centrifuged and completely filled into the narrow channel and hole to act as the compact wax valve. Meanwhile, an elastic and sticky membrane is depressed to seal the hole to act as the membrane valve. The wax valve is protected by the membrane valve from being damaged by both mechanical deformation and thermal corroding caused by the hot vapor with high pressure from the PCR chamber. A double-sided heating strategy is adopted to reduce the thermal cycling time; meanwhile, a balanced mechanism is used to achieve real-time amplification by rotating the centrifugal chip between the heating and detection positions in turn. As a proof-of-concept, the performance of the centrifugal chip with four parallel units is demonstrated by successfully detecting purified DNA templates or the extracted DNA templates from cells as well within 20 min....
Magnetizing living cells with superparamagnetic iron oxide nanoparticles (SPIONs) enables their remote manipulation using external magnetic field. This lays the foundation for magnetically assembling tissue precursors within cell-friendly, proliferation-permissive environments and holds considerable promise for biomedical applications, particularly in the development of complex single- and multicellular tissue constructs for bone and organ reconstruction. However, progress in this field is limited by the lack of robust mathematical tools for accurate control of ensembles of magnetic nano- and micro-objects. In practical printing scenarios, collective behavior and unavoidable statistical heterogeneity— such as variations in SPION size and shape or deviations in cell magnetization—render traditional equation-based modeling inadequate. We developed a hybrid modeling framework integrating conventional physics-based simulations with artificial intelligence- driven image analysis. Dynamic parameters were extracted from video recordings of magnetized cells moving within model microfluidic devices exposed to well-defined magnetic fields and gradients. The AI-based analysis enabled quantitative characterization of ensemble behavior under heterogeneous conditions. The proposed framework successfully captured the collective dynamics of magnetized cell ensembles and enabled accurate control of their spatial organization under external magnetic actuation. The integration of simulation and data-driven analysis provided robust parameter identification despite statistical heterogeneity within the system. This integrated modeling approach provides a practical and effective tool for controlling the three-dimensional magnetic assembly of living cells, with strong potential for applications in tissue engineering....
Extracellular vesicles (EVs) hold significant potential in cardiovascular diagnosis and treatment. However, their clinical applications are limited by challenges such as isolation efficiency, subpopulation heterogeneity, analytical standardization, and manufacturing scalability. Artificial intelligence (AI) and machine learning (ML) offer a computational framework to address these constraints through data-driven platform engineering. This review examines AI-assisted strategies in three interconnected EV platform pillars in cardiovascular medicine. These include: (i) isolation and processing platforms where ML algorithms optimize microfluidic separation and improve signal accuracy; (ii) analytical and diagnostic platforms where deep learning supports single vesicle phenotyping, multi-omics biomarker engineering, and biosensor interpretation; and (iii) therapeutic and manufacturing platforms where AI guides cargo loading, biodistribution estimation, and process control. We also assess key translational challenges, including MISEV2023 compliance, dataset bias, reproducibility, and regulatory alignment. This review positions artificial intelligence as the fundamental layer of the EV bioengineering process, providing a structured framework for advancing EV-based cardiovascular platforms from laboratory research to clinical application....
This preliminary study explored circadian variations in meridian-associated skin temperature using infrared thermal imaging (IRTI). Four healthy adults receive a two-hour IRTI measurement alternately over a 24 h period, with thermal images acquired every 15 min. Within the 24 h monitoring period, two-hour intervals corresponding to the predicted peak activity of each meridian according to the ziwu-liuzhu theory were selected for detailed analysis. Specifically, jing-well acupoints exhibited an early increase in temperature at the onset of their predicted active intervals, whereas terminal acupoints showed a decline in temperature, suggesting the initiation and completion of meridian activity. A progressive increase followed by a decrease was observed along both the spleen meridian (9:00–11:00 a.m.) and heart meridian (11:00–1:00 p.m.), suggesting a temporal trend that may be consistent with traditional Chinese medicine (TCM) predictions. These preliminary results indicate that IRTI may provide a non-invasive approach for visualizing circadian features of meridian function, offering potential to bridge TCM concepts with modern biomedical approaches....
Loading....