中国医疗器械杂志最新文献

Biodegradable heart occluder uses a biodegradable medical polymer material to replace or completely replace the metal material. After completing the repair function of the heart defect, the device is gradually degraded and safely absorbed by the human tissue. So it may minimize the risk of long-term complications that traditional metal heart occluder causing in the body after implantation. Based on the quality management concept of the entire lifecycle of medical device, this article briefly introduces design and development, as well as the product realization of biodegradable heart occluder. It analyzes the main risk points in design and production, and corresponding suggestions have been put forward. These suggestions are combined with the medical device good manufacturing practice and the appendix of implantable medical equipment to provide a reference for regulators and industry professionals.

This study aims at developing a dataset for determining the presence of carotid artery plaques in ultrasound images, composed of 1761 ultrasound images from 1165 participants. A deep learning architecture that combines bilinear convolutional neural networks with residual neural networks, known as the single-input BCNN-ResNet model, was utilized to aid clinical doctors in diagnosing plaques using carotid ultrasound images. Following training, internal validation, and external validation, the model yielded an ROC AUC of 0.99 (95% confidence interval: 0.91 to 0.84) in internal validation and 0.95 (95% confidence interval: 0.96 to 0.94) in external validation, surpassing the ResNet-34 network model, which achieved an AUC of 0.98 (95% confidence interval: 0.99 to 0.95) in internal validation and 0.94 (95% confidence interval: 0.95 to 0.92) in external validation. Consequently, the single-input BCNN-ResNet network model has shown remarkable diagnostic capabilities and offers an innovative solution for the automatic detection of carotid artery plaques.

Objective: Photoelectric volumetric tracing (PPG) exhibits high sensitivity and specificity in flap monitoring. Deep learning (DL) is capable of automatically and robustly extracting features from raw data. In this study, we propose combining PPG with 1D convolutional neural networks (1D-CNN) to preliminarily explore the method's ability to distinguish the degree of embolism and to localize the embolic site in skin flap arteries.

Methods: Data were collected under normal conditions and various embolic scenarios by creating vascular emboli in a dermatome artery model and a rabbit dermatome model. These datasets were then trained, validated, and tested using 1D-CNN.

Results: As the degree of arterial embolization increased, the PPG amplitude upstream of the embolization site progressively increased, while the downstream amplitude progressively decreased, and the gap between the upstream and downstream amplitudes at the embolization site progressively widened. 1D-CNN was evaluated in the skin flap arterial model and rabbit skin flap model, achieving average accuracies of 98.36% and 95.90%, respectively.

Conclusion: The combined monitoring approach of DL and PPG can effectively identify the degree of embolism and locate the embolic site within the skin flap artery.

Sleep disordered breathing (SDB) is a common sleep disorder with an increasing prevalence. The current gold standard for diagnosing SDB is polysomnography (PSG), but existing PSG techniques have some limitations, such as long manual interpretation times, a lack of data quality control, and insufficient monitoring of gas metabolism and hemodynamics. Therefore, there is an urgent need in China's sleep clinical applications to develop a new intelligent PSG system with data quality control, gas metabolism assessment, and hemodynamic monitoring capabilities. The new system, in terms of hardware, detects traditional parameters like nasal airflow, blood oxygen levels, electrocardiography (ECG), electroencephalography (EEG), electromyography (EMG), electrooculogram (EOG), and includes additional modules for gas metabolism assessment via end-tidal CO ₂ and O ₂ concentration, and hemodynamic function assessment through impedance cardiography. On the software side, deep learning methods are being employed to develop intelligent data quality control and diagnostic techniques. The goal is to provide detailed sleep quality assessments that effectively assist doctors in evaluating the sleep quality of SDB patients.

Objective: The prediction of RR intervals in hypertensive patients can help clinicians to analyze and warn patients' heart condition.

Methods: Using 8 patients' data as samples, the RR intervals of patients were predicted by long short-term memory network (LSTM) and gradient lift tree (XGBoost), and the prediction results of the two models were combined by the inverse variance method to overcome the disadvantage of single model prediction.

Results: Compared with the single model, the proposed combined model had a different degree of improvement in the prediction of RR intervals in 8 patients.

Conclusion: LSTM-XGBoost model provides a method for predicting RR intervals in hypertensive patients, which has potential clinical feasibility.

With the continuous advancement of artificial intelligence in the field of prostate cancer research, numerous studies have shown that AI performance can rival that of physicians. This review examines the recent applications and developments of AI in the early, accurate, and non-invasive diagnosis of prostate cancer, subsequently elucidating its importance, benefits, and limitations. The review emphasizes the exploration of the potential integration of AI with multi-omics and other cutting-edge technologies. Considering the current status of AI in prostate cancer diagnosis, the review summarizes the challenges faced in the clinical adoption of AI technologies and looks forward to improved and enhanced AI-based prostate cancer diagnostic techniques. The goal is to offer a reference for the integration of artificial intelligence into clinical practice.

In order to achieve precise risk control of medical devices, it is necessary to establish a scientific evaluation system throughout the entire life cycle of medical devices that focuses on risk identification and risk control. This study summarizes the medical device adverse event monitoring system of the US on regulatory agencies and regulatory law, adverse events reporting forms and time limits, adverse event database, adverse event report analysis and evaluation, as well as adverse event feedback and control. Furthermore, some examples are provided to illustrate the application of the MAUDE database in risk analysis, physical and mechanical performance research, and clinical evaluation of medical device registration and application materials.

To comprehensively assess the true visual function of clinical dry eye patients and the comprehensive impact of blinking characteristics on functional vision of the human eye, an intelligent vision measurement system has been designed and developed to detect and analyze blinks from the side. The system employs deep learning keypoint recognition technology to analyze eyelid features from a lateral perspective. It presents the data of identified key points for the upper and lower eyelids in a line chart format and annotates the trough of each blink. By setting benchmark values, the system automatically calculates the proportion of complete and incomplete blinks in the tested individuals. The results indicate that the system is stable in performance and accurate in measurement, successfully achieving the anticipated design objectives. It thereby provides reliable technical support for future clinical applications.

As the direct microenvironment of assisted reproductive technology, the evaluation of culture medium for human assisted reproduction technology is particularly important. This paper discussed the classification management, technical review points, clinical evaluation and review thinking, focusing on the basic requirements, raw material control, biological evaluation, sterilization process of culture medium for human assisted reproduction technology, combined with some material limit, new added material and quality system control to thoroughly assess management risk of the whole life cycle of culture medium for human assisted reproduction technology.

This paper describes the design of an innovative linear accelerator image-guided radiosurgery (IGRS) device, which is based on a composite twofold rotary gantry structure. The paper discusses five aspects of the innovative device: its overall composition, the safety net space created by the accelerator radiation head as it rotates around the patient's longitudinal axis, the non-coplanar spherical coverage in the direction of the incidence angle for quasi-4π delivery, the structural features of the composite twofold rotary gantry, and the processes of treatment planning and implementation. It elaborates on the device's manufacturing feasibility, safety, effectiveness, accuracy, and efficiency. The conclusion is that this innovative device design holds significant development value and market promotion potential.