Electrosurgery is widely applied for precise tissue cutting and coagulation through high-frequency electrical energy, yet it carries the risk of collateral thermal injury. This review examines emerging strategies to mitigate such  damage, including cooling systems, real-time temperature monitoring, pulsed cutting, and laser- or ultrasoundassisted techniques. By improving temperature regulation, enhancing feedback accuracy, and enabling adaptive power control, these innovations reduce heat diffusion and tissue charring, thereby enhancing surgical safety and outcomes.

Protecting the recurrent laryngeal nerve (RLN) and superior laryngeal nerve during thyroid and parathyroid surgery remains a significant challenge. Traditional methods primarily rely on visual identification and regional protection techniques to minimize nerve injury. However, these approaches often face challenges such as limited working space, high procedural difficulty, and incomplete tissue removal. Intraoperative nerve monitoring uses neuro physiological techniques to assess the functional integrity of nerves, aiming to prevent or reduce nerve damage. Intraoperative nerve monitoring for laryngeal nerve protection during thyroid and parathyroid surgery provides an effective means of evaluating RLN damage. For successful RLN monitoring, both monitoring personnel and surgeons need a solid understanding of nerve monitoring principles, follow of standardized surgical procedures, and be able to troubleshoot abnormal signals during surgery. With ongoing advancements in technology, nerve monitoring devices are expected to become more sensitive, offering rapid and precise waveform analysis, and enhancing user-friendliness. Additionally, minimally invasive thyroidectomy and robot-assisted surgical systems hold promising potential for the future of thyroid surgery. This paper reviews the use of Intraoperative nerve monitoring and RLN monitoring, incorporating the latest research from both domestic and international studies. It discusses the importance of RLN monitoring, the principles of monitoring technologies, current research on RLN monitoring technology, guidelines for nerve monitoring, and strategies for managing and analyzing abnormal monitoring signals.

In the field of bioanalysis, the integration of magnetic beads and biosensors provides a protein detection platform with high separation efficiency and sensitivity. The superparamagnetism of magnetic beads, combined with surface functional modifications, forms the basis for selectively capturing and effectively separating target proteins. Additionally, the high sensitivity and specificity of biosensors ensure precise quantitative analysis of captured proteins. This article systematically reviews the synthesis strategies of functionalized magnetic beads, detection methods for proteins and nucleic acids, as well as the current technical challenges and future development directions.

Objective: To construct a prediction model for fatty liver disease (FLD) among elderly residents in community using machine learning (ML) algorithms and evaluate its effectiveness. Methods: The physical examination data of 4989 elderly people (aged over 60 years) in a street of Shanghai from 2019 to 2023 were collected. The subjects were divided into a training set and a testing set in a 7:3 ratio. Using feature selection and importance sorting methods, eight indicators were selected, including high-density lipoprotein cholesterol, body mass index, uric acid, triglycerides, albumin, red blood cell, white blood cell, and alanine aminotransferase. Six ML models, including Categorical Features Gradient Boosting, eXtreme Gradient Boosting, Light Gradient Boosting Machine, Random Forest, Decision Tree, and Logistic Regression, were constricted, and their predictive performances were compared via accuracy, precision, recall, F1 score, and Area Under Receiver Operating Characteristic Curve. Results: Among the six ML models, the Categorical Features Gradient Boosting model demonstrated the highest prediction accuracy of 0.74 for FLD in elderly community population, along with a precision of 0.70, a recall of 0.73, a F1 score of 0.71, and an area under the curve of 0.74. Conclusions: In the context of rapid development of artificial intelligence, a community-based elderly FLD prediction model constructed using ML algorithms aid family general practitioners in the early diagnosis, early treatment, and health management of local FLD patients.

Recently, vibration sensors, initially confined to industrial use, have emerged as pivotal tools in medical practice. This article delves into their myriad applications within healthcare, underscoring their potential to reshape patient care paradigms. From wearable gadgets to cutting-edge medical equipment, the incorporation of vibration sensors holds promises to redefine patient monitoring, diagnostics, and therapeutic strategies. By integrating these sensors, healthcare professionals gain novel insights into physiological dynamics, ultimately improving patient outcomes. The integration of vibration sensors into medical practice not only enhances the accuracy and efficiency of health monitoring and diagnostics but also opens up new avenues for personalized medicine. As these technologies continue to evolve, they hold the promise of transforming healthcare delivery, making it more responsive, proactive, and patient-centric.

Since the 1960s, anastomosis instruments have become integral in gastrointestinal procedures, employing Titanium (Ti) alloy staples. These staples, however, remain permanently in the body, potentially inciting inflammatory reactions, compromising computed tomography scans, and causing diagnostic inaccuracies. This scenario underscores the imperative for biodegradable surgical staples, spurring research into materials that exhibit both superior biodegradability and mechanical integrity. Current investigations are focused on Magnesium (Mg), Zinc (Zn), and their alloys for their exemplary biodegradability, mechanical strength, and biocompatibility, making them promising candidates for gastrointestinal anastomosis. This review encapsulates the latest advancements in biodegradable surgical staples, emphasizing material and structural enhancements. It details the mechanical attributes of wires intended for staple fabrication, the corrosion dynamics across varied environments such as in vitro immersion solutions and in vivo implantation sites and the impact of structural refinements on staple biodegradability. Additionally, it contrasts the benefits and limitations of Mg-based and Zn-based staples and offers insights into the potential and hurdles in developing biodegradable surgical staples, thereby fostering further exploration in this field.

Objective: This study uses dual-modality signals, including phonocardiogram (PCG) and electrocardiogram (ECG), together with machine learning methods to distinguish cardiac function states in subjects. Methods: We developed a model based on time–frequency representations. The model includes data preprocessing, a time–frequency conversion module, a feature extraction module, and a feature-fusion classifier module. The system uses complete ensemble empirical mode decomposition with adaptive noise to remove noise from the PCG and applies filters to reduce noise in the ECG. The system extracts Mel-frequency cepstral coefficients from the PCG and uses Fourier synchrosqueezed transform for the ECG. This study also improves VGG16 and ResNet18 as feature extractors by inserting a variant attention mechanism into the feature extraction networks. Finally, the system feeds the feature vector into a support vector machine for classification. Results: The dual-modality time–frequency method achieves 95.4% accuracy and 97.4% sensitivity for positive cases on public datasets, demonstrating strong performance in cardiac function classification. Conclusion: This research shows that the approach improves both diagnostic accuracy and sensitivity. The system provides valuable support for the preliminary screening of cardiac dysfunction.

Acute respiratory distress syndrome (ARDS) is characterized by increased alveolar capillary permeability and hypoxemia, often leading to multi-organ failure. Early recognition and intervention, especially the optimization of mechanical ventilation, restricted volume control, treatment of anti-inflammation, and some new type of therapies, such as prone-position ventilation and ECMO, can significantly shorten ICU stays, reduce healthcare costs and improve patient survival. In order to optimize the diagnosis and treatment of ARDS, it is necessary to integrate research results, clinical guidelines and practical experience to build a systematic knowledge system. As a smart tool, GPT has shown great potential in the medical field. It can efficiently search medical databases, build knowledge graphs, develop online platforms, and provide personalized recommendations to help doctors quickly grasp the latest progress. At the same time, GPT can also generate high-quality education and training materials to meet the training needs of different medical staff. In the online training, GPT combines simulated cases and VR/AR technology to create an immersive learning environment and improve the diagnosis and treatment capabilities of grassroots doctors. GPT can also enable remote diagnosis and treatment, especially in low-resource settings, to accelerate the treatment process through remote diagnosis and assistance. In terms of clinical decision support, GPT can analyze electronic medical records, provide early warning and intervention recommendations, and customize personalized treatment plans. It also fosters multidisciplinary collaboration and technical exchange. In terms of resource allocation, GPT can analyze data and provide resource allocation suggestions for governments and medical institutions to optimize the allocation of medical resources. In remote areas, GPT serves as an online think tank, providing immediate guidance to grassroots doctors. However, the application of GPT also faces challenges such as data privacy, model accuracy, technical thresholds, imbalance of medical resources, and medical liability.

Key Words: generative pre-trained transformers; acute respiratory distress syndrome; extracorporeal membrane oxygenation

The Internet of Things, Metaverse and Medical GPT are used to empower the field of health care, and the quality and efficiency of health care are improved through high-tech means. IoT technology provides a scientific basis for developing personalized health plans by deploying sensors and monitoring devices to monitor individual health status in real-time and collect data. The metaverse builds a three-dimensional virtual space, allowing users to participate in a variety of health promotion activities as virtual identities and enjoy immersive health education experiences, such as exercise training and rehabilitation courses in virtual reality. Medical GPT uses natural language processing technology, combined with the user’s genetic, physiological indicators and other information, to provide personalized health consultation and prevention strategies, generate customized health management plans, assess health risks, and provide professional consultation and education. The combination of these technologies not only improves the personalized and intelligent level of health management, but also expands the accessibility of health education resources, so that residents in remote areas can also enjoy high-quality resources. In addition, they reduce reliance on traditional healthcare resources, reduce costs, improve service efficiency, and enhance user engagement and satisfaction with health promotion activities by providing interactive and fun virtual reality experiences. These technologies are conducive to promoting innovation in medical and health services, promoting the equitable distribution of health resources, and improving the health level of the whole people.

Key Words: virtual reality; augmented reality; Internet of Things; generative pretrained transformer

The interventional treatment of chronic total occlusion (CTO) in coronary arteries is a highly complex procedure that demands exceptional expertise, advanced technical skills and sophisticated intraoperative decision-making from operators. Traditional teaching methods, however, encounter significant limitations when it comes to training for such intricate interventions. As an emerging paradigm, metaverse—which integrates virtual reality (VR), augmented reality (AR) and artificial intelligence (AI)—provides an immersive and interactive platform for advancing CTO interventional training. This article explores the latest research advancements and discusses the future potential of metaverse in enhancing the education and training of CTO interventions.

Key Words: metaverse; chronic total occlusion; interventional treatment; teaching