In the treatment of cervical cancer, painless brachytherapy is crucial for enhancing the quality of life for patients. Painless strategies include preoperative pharmacological and non-pharmacological interventions to alleviate anxiety, intraoperative anesthesia selection to ensure comfort, and postoperative pain control to reduce suffering. This article reviews the research and application of painless brachytherapy, highlighting the importance of pain management during the treatment process.

Objective At present, there is no daily quality control standard for CZT cardiac specific camera at home and abroad. This paper verifies the system stability of the cadmium zinc telluride (CZT) specific cardiac camera by retrospectively analyzing its daily QC data, and explores its influencing factors and solutions.Methods According to the user manual, the daily QC data and the temperature and humidity of operation room of D-SPECT from 2017 to 2023 were collected. Nonparametric Spearman rank correlation test and multiple linear regression analysis were performed between the quality control indicators and the temperature and humidity of the operation room, and the activity of the quality control rod source to explore their influencing factors. The nonparametric binary classification Mann-Whitney U test was used to explore the impact of replacing the rod source.Results The daily QC results within six years were all qualified. The operation room temperature and rod source activity are related to daily QC indicators, and humidity is related to some indicators. (P<0.05) The rod source activity and temperature and humidity have influence on some daily QC indexes. Replacing the rod source has a significant impact on the quality control index. (P<0.05)Conclusion The system performance of the D-SPECT CZT cardiac specific camera remains stable over six years of use, and the stability of clinical application can be guaranteed under strict compliance with operating specifications. During daily use, it is necessary to pay close attention to changes in the operation room environment and the use status of the rod source to ensure that machine can run normally.

Objective To design a complex disease research platform based on microservices architecture and explore its application value in precision medicine.Methods The study employed the Spring Cloud Alibaba microservices framework, encapsulating complex disease-related data and analytical workflows into public and private microservices, including modules for transcriptomic data analysis, epigenetics data analysis, and others.Results After platform implementation, project initiation time was reduced by 52.6% compared to traditional methods, with statistically significant differences (P < 0.001). Project completion rate increased from 70% (14/20) to 90% (16/18).Conclusion The microservices-based research platform can be effectively applied to clinical and fundamental studies of complex diseases, demonstrating significant value for precision medicine and offering insights for broader adoption.

With the continuous development of communication technology, the rapid progress of Internet of Things technology is profoundly affecting the medical field, especially in the interconnection of medical equipment, which shows great potential. By building the Internet of Things for medical equipment, it can significantly improve the efficiency of information flow and integration within hospitals, achieve real-time collection of patient health data and medical environment parameters, provide scientific basis for clinical practice through deep analysis of data, optimize diagnosis and treatment processes, and improve the quality and efficiency of medical services. The interconnection of medical equipment based on IoT technology is conducive to the refined management of medical equipment, realizing real-time monitoring, intelligent scheduling, and efficient utilization of equipment, thereby significantly reducing the operating costs of hospitals. The interconnection of medical devices based on the Internet of Things plays an important role in the construction of smart hospitals. Therefore, this article will elaborate on the value of building the Internet of Things for medical devices, analyze and compare the value and current situation of medical device interconnection models based on the Internet of Things, explore the development direction of medical device interconnection under the Internet of Things technology, in order to provide forward-looking thinking and strategic suggestions for the development of smart healthcare, and promote the widespread application and deep integration of medical device Internet of Things technology in the medical industry.

Objective To explore the intelligent management indicator parameters corresponding to the key links in the entire life cycle management process of emergency life support equipment and determine the key indicator parameters for the intelligent management of the entire life cycle of emergency life support equipment. Methods In this study, an intelligent management model for emergency life support equipment was determined by integrating the methods of literature review, field visits and investigations, and brainstorming. The key indicator parameters in this model were identified through the Delphi expert consultation method and questionnaire survey method. Results From the five first-level indicator dimensions of tendering and procurement management, equipment benefit analysis, equipment operation analysis and management, equipment quality control, maintenance management, and clinical use evaluation of the equipment, an intelligent management model for emergency life support equipment with 32 important indicators was ultimately formed. Five indicators, namely plan demonstration, tender parameters, measurement plans for the equipment, maintenance management of the equipment, equipment optimization configuration, and operation training, were commonly familiar to experts and unanimously regarded as highly important indicator parameters. Conclusion The results of this study provide a powerful reference basis for colleagues to carry out intelligent management work for emergency life support equipment and will further advance the intelligent management process of emergency life support equipment.

Objective To conduct an in-depth analysis of the causes of the "system overheating" alarm malfunction of the CARDIOSAVE Hybrid intra-aortic balloon pump (IABP) of the MAQUET brand, summarize maintenance experience, and put forward improvement measures for equipment management to enhance the operational efficiency and reliability of the equipment. Methods Retrospectively analyze the maintenance processes of 6 cases of the "system overheating" alarm malfunction of this model of IABP pump. Analyze the malfunction mechanism in detail by combining the equipment system structure and working process. Meanwhile, count the usage status of the existing IABP equipment in the hospital, including information such as the using departments, cumulative usage time, service life and number of malfunctions. Results Six malfunction causes and corresponding maintenance solutions were summarized. It was found that the failure rate of the high-temperature alarm caused by problems with the negative and positive pressure filters was relatively high. There were significant differences in the usage frequencies of IABP equipment among different departments, and there was still room for optimization in the equipment configuration of the whole hospital. The service life of the equipment was positively correlated with the number of malfunctions, which conformed to the law of the equipment failure curve. Conclusion Equipment manufacturers should optimize equipment design, expand monitoring scope and add monitoring indicators. Medical institutions should manage equipment scientifically, including setting maintenance cycles and exploring sharing models, etc. so as to reduce the failure rate and improve the comprehensive benefits of IABP equipment.

Objective This study aims to explore the development and practice of a quality control management model based on distributed quality control devices. Methods By analyzing the challenges in medical equipment quality control, a distributed quality control device was specifically developed using infant incubators as an example. Subsequently, a three-tier quality control management model was established based on this device. The model was piloted in the pediatric department of the China-Japan Friendship Hospital and compared with traditional quality control devices and management models through a Comparative Effectiveness Research (CER). Results The quality control management model utilizing the distributed device for infant incubators improved quality control efficiency by over 71%, achieved 100% equipment coverage and 7×24-hour real-time daily quality control monitoring, reduced costs by nearly 50%, and standardized quality control processes and criteria. Conclusion The innovative model systematically addresses four major pain points of traditional quality control—low efficiency, narrow coverage, high cost, and inconsistent standards—providing a more efficient, economical, and reliable solution for medical equipment quality control.

Objective To address the current issues of fragmented performance assessments and weak quality regulation due to the lack of a standardized evaluation system for electroacupuncture therapy devices, this study aims to establish a scientifically robust and universally applicable evaluation index system to provide theoretical support for industry standardization.Methods The Delphi method and Analytic Hierarchy Process (AHP) were adopted to construct the evaluation index system. A preliminary framework was developed through literature analysis and expert consultations, followed by two rounds of Delphi surveys and quantitative analysis using AHP.Results A comprehensive evaluation index system was finalized, comprising 3 primary indicators, 7 secondary indicators, and 26 tertiary indicators. This system was applied to conduct systematic testing and comparative analysis of 286 electrotherapy devices (13 models from 8 manufacturers) in clinical practice.Conclusion The evaluation index system developed in this study demonstrates strong scientific validity and broad applicability, serving as standardized criteria for performance assessment, product development, and quality regulation of electroacupuncture therapy devices.

The SPD management model for medical consumables has significantly improved the efficiency and quality of the management of medical consumables. Its management model has developed rapidly in China, but there is a lack of unified standards for the management model. The SPD models applied in the management of medical consumables mainly include the self-operated and self-built model of hospitals, the operation outsourcing model led by hospitals, the centralized distribution service model, etc., and the management models are still constantly innovating. For large general hospitals, due to the large volume and diverse types of medical consumables involved and the high complexity of consumable management, more attention should be paid to the impact of the SPD management model on the consumable management, exploring the advantages and disadvantages of the SPD management model and forming relevant standards.

Objective This study aims to enhance the refined management of medical consumables through the reform of the Supply, Processing and Distribution (SPD) service model in hospitals. By integrating data across departments, the reform strengthens precision management practices throughout the entire circulation process of medical consumables. Methods Connect data interfaces to link with HIS, HRP, EMR, and other information systems. A medical consumables supply management system was established, incorporating functions including standardized coding, inventory management, clinical traceability, intelligent replenishment, and financial settlement integration. Through logistics data monitoring and analysis at each usage stage, full lifecycle traceability management of medical consumables was achieved. Results Through the reform of SPD service and supported by big data evidence, achieved rationalized supervision of medical consumables and promoted their clinically appropriate application. Conclusion The results demonstrate that the in-hospital reform of medical consumables supply chain services meets the practical needs of refined management for hospital consumables management departments.

Objective To design a multi-supplier SPD (Supply, Processing, and Distribution) management platform to solve the problem of multi-supplier management in hospital consumables management and optimize the full-process management. Methods Adopt the model of "self-built platform and connection with supplier systems", through multi-level system architecture design, build a unified management process, data standards and assessment system, achieve seamless connection with the hospital system, cover the links of access, distribution, use and settlement, and be equipped with intelligent devices and analysis tools. Results As of August 2024, the platform has completed the construction of main archives for 108,000 items of materials, launched 5,540 types of consumables, accumulated 61,248 orders, with a delivery amount of 364 million yuan, a settlement amount of 571 million yuan, and invoice verification of 299 million yuan. This has effectively prevented errors and omissions in accounting, facilitated "0 inventory" management, reduced inventory costs, and improved delivery efficiency. Optimize supply chain management to enhance the satisfaction of medical staff and patients. Conclusion The SPD platform has enhanced the refined level of consumable management, formed a management closed loop, and significantly improved the operational efficiency and medical quality of the hospital. In the future, the system will continue to be optimized, the application of RFID technology will be expanded, and the management accuracy and efficiency will be enhanced.

Objective To address the current management of non-sterile orthopedic consumables, the process is restructured to achieve full-process supervision, effective traceability, and unified usage and billing of consumables. Improve billing accuracy and efficiency, reduce non sterile consumables disinfection costs.Methods Digital technology is utilized to build a digital platform for orthopedic management, creating a "one-item-one-code" management model for non-sterile orthopedic consumables, and introducing an advanced image recognition system to reshape the management process. This extends regulatory work to in-hospital warehousing, enabling precise acceptance of each implant, in-hospital traceability, and accurate billing. Conclusion Through the trial operation of the new model, the management of non sterile orthopedic consumables has been optimized, resulting in a 62.5% increase in billing efficiency and accuracy. This has achieved 100% traceability of non sterile consumables, reduced sterilization frequency, lowered disinfection costs by 87.5%, and saved overall costs.

Objective To track the changes in tissue properties during the operation of the ultrasonic scalpel and to monitor the dynamic changes in tissue characteristics during the cutting process of the ultrasonic scalpel in real time, with the aim of providing a more optimized energy regulation output algorithm. Methods In accordance with the principle of bioimpedance, the impedance matching algorithm of ultrasonic transducers was employed to measure the tissue impedance of the contact portion of the knife head. Signal acquisition and processing were conducted to fit the tissue parameters and generate a tissue model. During the three stages of "start - denaturation - separation" in the cutting process of the ultrasonic scalpel, the load impedance data of the knife head was collected in real time by using the impedance matching algorithm of the ultrasonic transducer (with a sampling frequency of 2000 times per second). The impedance curves were fitted through in vitro pig tissue experiments (n = 100 cuts per setting), and tissue-specific characteristics were extracted by integrating signal smoothing, peak analysis, and other methods. The experimental design encompassed five current output settings (170 - 350 mA) to systematically explore the coupling mechanism of energy - impedance - tissue type. Results The curves of tissue impedance changes during the cutting process of some pig tissues were fitted, validating the feasibility of this method. The changes in impedance recovery of pig stomach and small intestine throughout the cutting cycle were significantly different (p < 0.05), indicating that there were differences in impedance changes among different tissue parts. The consistency of impedance recovery changes in the same tissue part was mainly manifested in the insignificant differences in the period of peak appearance, peak size, and data change trend after peak appearance (p > 0.05), suggesting that the impedance recovery data changes of the same tissue part in different individuals exhibited a high degree of convergence. As the energy output of the ultrasonic scalpel host increased, the trends of impedance recovery data changes in pig stomach and small intestine tissues tended to be gentle, and the peaks decreased, indicating that the tissue load of the knife head would vary under different energy output settings of the ultrasonic scalpel. By extracting this change characteristic, the ultrasonic scalpel host could identify the type of tissue being cut at each output setting, thereby enabling the setting of the energy output adjustment module of the ultrasonic scalpel host for different tissue types for each setting. Conclusion The tissue impedance curve can provide a basis for the host of ultrasonic scalpel to identify tissue type and adjust the energy output of the host. This study can provide effective data support for improving the performance of domestic ultrasonic scalpel and optimizing the clinical effect of ultrasonic scalpel.

Hepatocellular carcinoma (HCC) is the main subtype of primary liver cancer, and due to its insidious early symptoms and rapid progression, the five-year survival rate of patients is only 18%. Currently, it remains a major challenge in the global cancer treatment field. In recent years, spectral CT has shown great potential as an emerging medical imaging method in oncology, with great potential for accurate diagnosis, treatment guidance, and prognosis evaluation of tumor diseases. In the context of precision medicine, the deep integration of artificial intelligence and radiomics, combined with multi parameter quantitative analysis of spectral CT, provides new technical support for early screening, dynamic evaluation of therapeutic efficacy, and accurate prognosis prediction of HCC. This article aims to systematically explain the basic principles of spectral CT imaging and its clinical applications in hepatocellular carcinoma, while also reviewing the rapidly developing fields of radiomics and artificial intelligence in recent years.

Objective To explore the SPD management strategy for operating room consumables based on the integration of medical and engineering perspectives, and to evaluate its practical effects in a tertiary hospital in Jiangsu Province.Methods Guided by the concepts of medical-engineering integration and SPD lean management, an SPD management strategy for operating room consumables was developed and implemented. The management effectiveness was assessed by comparing indicators such as consumables management efficiency per surgery, abnormal situations in barcode-controlled consumables management, and satisfaction of operating room medical staff before and after the application of the SPD model.Results After implementing the SPD model, the preparation time, delivery time, response time for temporary requisitions, and return time of consumables per surgery in the operating room of the tertiary hospital in Jiangsu were significantly reduced (P<0.001).The implementation of daily clearance management for barcode-controlled consumables has effectively reduced losses, missed charges, and incorrect charges(P<0.05).The satisfaction of medical staff significantly improved (Χ2=26.825,P< 0.001).Conclusion The SPD management strategy based on the medical-engineering perspective significantly optimizes the operating room consumables management process, reduces operational costs, improves management efficiency, and enhances the quality and efficiency of medical institutions. It holds broad potential for promotion.

Objective To compare and analyze the results of composite field and large field in dose verification of Portal Dosimetry (PD) for fixed-field intensity modulated radiotherapy (IMRT) plans of cervical cancer, and to provide reference and guidance for medical physicists to carry out dose verification work. Methods A total of 21 fixed-field IMRT plans from 21 cervical cancer patients were selected for this study. Each treatment plan included 7 large fields, and each large field consisted of a pair of split fields. The Eclipse was used to create two kinds of PD dose verification plans from treatment plans, one kind containing only split fields and the other kind containing only large fields. And then the above two kinds of verification plans were carried out using a Clinac iX linac. Data of gamma passing rate were directly obtained for large fields by using the PD software module. And data of gamma passing rate for each composite field was obtained from corresponding pair of split fields by using the composite field menu tool. Value of G was used to represent data of gamma passing rate. Parameter settings of 3mm/3% and a threshold of 10% were used in gamma analysis. Statistical analysis and comparative study were used for G values of composite fields, large fields, and split fields. The rank-sum test was used to compare G values of the two types of composite field and large field. Results A total of G values of 147 composite fields and 147 large fields were obtained, with median values of 99.2% and 98.3%, respectively. The rank-sum test of G values of the two types of fields showed that, the difference was statistically significant (P<0.05). The median difference in G values between composite field and large field is 0.9%. The median values of G values for split field 1 (SF1), split field 2 (SF2), and all split fields (SF) are 99.7%, 99.9%, and 99.8%, respectively. The G values of SF1, SF2 and SF are generally higher than corresponding values of the composite field and the large field. Conclusion By and large, values of gamma passing rate of the composite field are bigger than corresponding values of the large filed. It could be considered to use the composite filed to obtain better dose verification results.

Objective The purpose of this study was to achieve the goal of comprehensive management of high-value consumables in the oral clinic through fine management. Methods The characteristics of high-value consumables in the oral clinic were sorted out, and the personalized information needs of the SPD system were formulated to achieve the goal of scanning all high-value consumables in the outpatient department. A three-level inventory management system was established, and it was linked to the performance system. An RBRVS (Resource-Based Relative Value Scale) model was established to distribute the performance of the oral clinic specialty, and the cost and benefits were refined. Results The time for medical staff to claim consumables and the time for warehouse inventory were significantly shortened (P < 0.05), the errors in registering high-value consumables and the differences in billing were significantly smaller than before implementation (P < 0.05), and the satisfaction of medical staff was significantly higher than before implementation (P < 0.05). The material ratio of the department from January to July 2024 was reduced from 15.07% of the previous year to 14.18%. It saved hospital costs, reduced the risk of consumable management, motivated doctors, and achieved comprehensive management of high-value consumables in the oral clinic. Conclusion By sorting out the "life nodes" of high-value consumables according to their entire life cycle and using the SPD model for fine management of high-value consumables in the oral clinic, high-value consumables in the oral clinic can truly achieve comprehensive management, improving the efficiency and level of hospital management, reducing consumable costs, and thus reducing the economic burden on patients. It is worthwhile for peers to learn from it.

Objective To study the variation patterns of cortical functional connectivity property in mental workload tasks with different types of visual information. Methods Working memory tasks with different information types and various mental loads were designed based on N-Back paradigm. EEG signals from 18 normal adults were acquired when tasks were being performed. EEG source localization based on sLORETA were carried out and the cortical EEG functional networks in the Theta and Alpha frequency bands based on the Pearson correlation were constructed. The network node and global indices were calculated and analyzed by statistic methods. Results Six nodes and four groups of functional connections in the two frequency bands network showed significant changes with cognitive load in the four tasks (p<0.05). With the increment of task loads, the average characteristic path length of the theta-band network significantly decreased from 2.8427 ± 0.0083 to 2.7751 ± 0.0051, while the average clustering coefficient and global efficiency significantly increased from 0.3384 ± 0.0018, 0.4232 ± 0.0015 to 0.3620 ± 0.0020, 0.4432 ± 0.0017, respectively. Conclusion The cortical functional connectivity indices can effectively represent the changes of mental workload in working memory tasks with different information types.

Objective To investigate the efficacy of DCE-MRI texture parameters combined with conventional MRI signs in predicting the nature of breast nodular lesions.Methods One hundred and twenty-two female patients with BI-RADS category 4 who presented to our hospital from January 2022 - December 2024 with breast nodules detected by ultrasound physical examination, with 78 benign and 44 malignant nodules confirmed by histopathological diagnosis, were selected. General patient data and MRI imaging manifestations were compared separately.A self-help sampling method was used to divide 90 samples as the training set and 32 samples as the test set, and the Random Forest algorithm was applied to establish a prediction model for conventional MRI imaging. For DCE-MRI images, the region of interest (ROI) was manually outlined by two physicians, and 13 texture parameters were extracted using the texture analysis module provided by Philips IntelliSpace Portal workstation.Nine texture features with significant differences were screened out by single-factor analysis, and inputted into the random forest algorithm to construct the texture feature prediction model. The binary logistic regression analysis was performed to construct a joint prediction model by combining the significant features of conventional MRI imaging with the texture parameters; the diagnostic efficacy of each model was evaluated by plotting the ROC curves.Results Compared with benign nodules, malignant nodules were more irregularly shaped morphologically, more likely to have lobulated or burr edges, more heterogeneous internal signals, with a higher proportion of calcifications, inhomogeneous enhancement, and larger nodules, and the differences were all statistically significant (P<0.05).Univariate analysis of texture features extracted from DCE-MRI images of breast lesions showed that among the 13 texture features, GLCM_Energy, GLCM_Entropy, GLCM_Contrast, GLCM_Correlation, GLCM_InverseDifferenceMoment, GLRLM_GrayLevelNonuniformity, GLRLM_ RunPercentage, GLSZM_LargeAreaEmphasis and GLDM_DependenceEnergy were significantly different between benign and malignant nodules (P<0.05).The AUC (95%CI) of ROC curve of conventional MRI imaging prediction model, texture feature prediction model and combined prediction model were 0.811 (0.753-0.828), 0.838 (0.796-0.871) and 0.893 (0.855-0.921), respectively. The accuracy, sensitivity and specificity were 82.22%, 85.60% and 94.47%, 80.41%, 81.24% and 92.36%, 78.63%, 79.92% and 90.15%, respectively.Conclusion DCE-MRI texture parameters combined with conventional MRI sign prediction model can effectively predict the nature of breast nodular lesions, which is expected to provide a reference basis for clinical diagnosis and treatment.

Objective To design and implement an intelligent stethoscope that can be widely used in medical environments with insufficient network coverage or cost sensitivity, in order to mitigate the digital divide caused by resource endowment. Methods Machine learning is deployed on smartphones using TensorFlow Lite to achieve on-site collection, preprocessing, feature extraction, and operation of a heart sound classification and quantification model for heart sound data. The ResNet50 model is introduced as a reference to compare and evaluate the accuracy, sensitivity, specificity, precision, and F1 score of the designed prototype. Results The results of the algorithm model show that the prototype has an accuracy of 0.881, sensitivity of 0.903, specificity of 0.825, F1 score of 0.915, and an area under the curve (AUC) of 0.95. The quantized model has an accuracy of 0.865, sensitivity of 0.893, specificity of 0.815, and an F1 score of 0.915, maintaining performance that meets the requirements for heart sound binary classification. The intelligent stethoscope app meets medical standards in terms of time consumption, stability, memory usage, latency, and signal-to-noise ratio, and provides a good user experience.Conclusion The intelligent stethoscope designed based on edge computing technology can adapt to environments with unstable network connections or limited resources while ensuring the reliability and efficiency of the system. It reduces the cost of use and improves the fairness of digital and intelligent medical services.

Sepsis remains a significant global public health challenge, with its high mortality and marked pathological heterogeneity continuing to hinder improvements in clinical outcomes. Despite the standardization of anti-infection treatments and organ support technologies, the decline in patient mortality rates has plateaued in recent years, underscoring the urgent need for novel therapeutic strategies. Precision medicine and individualized management have gained attention as promising approaches to address the complexity and rapid progression of sepsis. However, the sheer volume of complex data and the necessity for dynamic treatment adjustments often exceed the capacity of attending physicians alone. Artificial intelligence (AI) emerges as a powerful tool capable of addressing these challenges by integrating multimodal data, optimizing treatment decisions, and streamlining the diagnostic and therapeutic processes. This review systematically evaluates the latest advancements, potential roles, and limitations of AI in the precise management of sepsis, clarifies future research directions, and aims to provide a robust theoretical foundation and practical guidance for clinicians and researchers. Ultimately, this work seeks to promote the development of individualized precision therapies, reduce mortality, and enhance patient outcomes.

Objective To investigate the efficacy of deep learning technology in enhancing multi-modal ultrasound diagnosis of cervical lymph node metastasis in thyroid cancer. Methods A retrospective analysis was conducted on 283 patients who underwent thyroid multi-modal ultrasound in our hospital from June 2024 to March 2025. Patients were divided into a disease group (n=126) and a control group (n=157) based on the presence of thyroid cancer, and further classified into a metastasis group (n=50) and a non-metastasis group (n=76) according to cervical lymph node metastasis status. Sonographic features of each group were collected and analyzed. ACE-Net was adopted as the deep learning network architecture to construct a DL (deep learning) model for disease diagnosis. The model was optimized using a training set of 22,946 sheets and its diagnostic efficacy was validated using a validation set of 2,550 sheets. Results Multivariate logistic regression analysis showed significant differences in sonographic features between the diseased and control groups, and between the metastatic and non-metastatic groups. The DL model's detection sensitivities for non-diseased and diseased cases were 0.943 and 0.959 respectively. Compared to physicians reading films alone, the DL model's mAP increased by 6.24%, Params decreased by 19.32 million, FLOPs decreased by 17.83 billion, and FPS increased by 18.01 frames per second. The model size was notably reduced with performance improved to some extent. After combining with the DL model, physicians' diagnostic sensitivity and accuracy increased significantly, and the false positive rate decreased. For cervical lymph node metastasis of thyroid cancer, the combined diagnosis had the best efficacy compared to conventional ultrasound [AUC (95%CI)=0.928 (0.887-0.976), sensitivity=83.33%, specificity=85.71%, accuracy=84.13%]. Conclusion The DL model constructed in this study significantly improved the diagnostic sensitivity for thyroid cancer and the accuracy in assessing cervical lymph node metastasis, demonstrating potential clinical application value.

In recent years, with the continuous advancement of medical informatics, artificial intelligence (AI) has made significant progress in disease diagnosis and treatment. Machine learning, deep learning, and multimodal technologies can process and analyze large amounts of complex data, improving disease progression prediction and treatment effectiveness. These advancements offer new insights and methods for the diagnosis and management of chronic obstructive pulmonary disease (COPD). This paper compares and synthesizes the latest literature on commonly used AI algorithms and techniques in the field of respiratory diseases, with a particular focus on their applications in COPD prognosis assessment. Key topics include the prediction of acute exacerbation risk and prognosis, real-time monitoring and early warning, and integration of biosignature analysis and disease health management. For the first time, multidimensional biosignature analysis of imaging, biomarkers and respiratory microbiome was systematically integrated, which in turn suggested a more economical and effective direction of clinical validation, with a view to providing a theoretical basis for the application of AI in COPD prognosis assessment and standardized management.

Lung cancer has one of the highest global incidence and mortality rates among all cancers, with overall five-year survival rates relatively low compared to other malignancies. Therefore, early diagnosis and precise treatment are imperative. Artificial intelligence (AI) technologies, particularly deep learning (DL) algorithms, have the capacity to process extensive medical image data for enhanced early detection of lung cancer and optimization of treatment. AI technology based on DL algorithms has exhibited substantial potential in the medical domain, especially in the realm of diagnosing and treating lung cancer. This paper systematically delineates the application status of various AI algorithms in the sphere of lung cancer diagnosis and treatment while summarizing research progress on AI technology for diagnosing, treating, and prognosticating lung cancer outcomes. The aim is to provide a reference point for early diagnostic methods and tailored treatment programs for lung cancer.

Objective To assess the maturity of core sub-technologies in current invasive ventilators, providing decision-making references for healthcare institution administrators, procurement teams, and biomedical engineers, about the selection，procurement and maintenance of invasive ventilators. Methods Based on technology evolution theory, a hybrid methodology integrating Delphi expert consultation, Technology Readiness Level (TRL) scale evaluation, literature analysis, and expert scoring was applied to evaluate the maturity of each core sub-technology in invasive ventilators. Results Through two rounds of email surveys, 25 core sub-technologies were identified. Invited experts attending scoring sessions to yield maturity values for each technology, which were quantitatively mapped onto an S-curve model of technological development to complete the maturity assessment. Conclusion The technology maturity assessment based on evolutionary theory and visualized through the S-curve model, scientifically and visually reflects the current lifecycle status and future trends of core sub-technologies. Providing practical technical references for decision-makers related to the device in its full lifecycle management.

Objective To explore and analyze the individual influencing factors of the size-specific dose estimate based on water equivalent diameter (SSDEWED) of the adults who underwent non-contrast chest computed tomography (CT) examine, and to construct a regression prediction model of SSDEWED. Methods A prospective study was conducted involving 205 adult patients who underwent non-contrast chest CT examine. Cross-sectional images at the central level of the chest CT were selected, and the region of interest (ROI) was delineated. The cross-sectional area of the ROI (AROI) and the mean CT value (CTROI) were recorded. Subsequently, the SSDEWED was calculated. The relationship between SSDEWED and individual influencing factors was analyzed by correlation and stepwise multiple linear regression analysis, and the prediction model of SSDEWED was established. Results The results of the correlation analysis indicated that AROI, lateral diameter (DLAT), body weight, fat volume, Anterior-posterior diameter (DAP), muscle volume, average CT value of fat, gender, height, body mass index (BMI), fat content, and CTROI were significantly positively correlated with SSDEWED (P<0.05). The prediction model of SSDEWED was established using multiple linear stepwise regression，on the basis of following independent risk factors (P<0.05): gender, height, DLAT, AROI, and CTROI. Conclusion The prediction model of SSDEWED, which established based on five independent influencing factors including gender, height, DLAT, AROI, and CTROI, is helpful for assessing the actual radiation dose received by adults undergoing chest CT examinations in a personalized manner.

Alzheimer's disease (AD) is a degenerative disease of the central nervous system. With the intensification of global population aging, the social and economic burden it brings is becoming increasingly heavy. At present, clinical analysis based on magnetic resonance imaging (MRI) of the brain is the main method for diagnosing AD. In recent years, deep learning methods have made breakthrough progress in the field of early diagnosis of Alzheimer's disease. However, existing literature lacks a systematic review of the neural network models used by different researchers. To systematically summarize the current application status of neural network models in AD classification and diagnosis, this paper conducted a systematic review of research in this field by searching relevant literature in databases such as PubMed and CNKI in recent years. Firstly, the commonly used AD image datasets were introduced; Secondly, based on the temporal context of the emergence and application of the model, the application principles and performance of LeNet-5, AlexNet, VGGNet, GoogLeNet, ResNet, DenseNet, and 3D-CNN in AD classification and diagnosis were analyzed in detail. By comparing and analyzing the classification and diagnostic performance of these models on public datasets, the existing problems in current research were summarized, and future research directions were discussed. This review aims to help beginners quickly grasp the research trends in this field and provide references for subsequent related research.

Objective Through the accurate analysis of the data collected by the wearable vital signs mobile monitoring system, to explore the rehabilitation care activities application effect of wearable devices in postoperative patients, so as to assist postoperative patients to carry out rehabilitation activities as soon as possible to promote patient recovery. Methods We designed a wearable vital signs mobile monitoring system, which used the vital signs signal acquisition tool, the bedside and wearable monitoring equipment are connected to the central monitoring system, and after the received vital signs data are in storage, standardization and intelligent processed, they displayed on the different terminals. Through the evaluation of the patient's index of getting out of the bed and rehabilitation status, health care workers adjust the walking up time of getting out of bed in timely. The time to first ambulation of the postoperative patient, average time of vital signs data collection are selected as the evaluation index to analyze the application effect of the wearable device. Results After the application of the wearable vital signs mobile monitoring system, the average time to first ambulation for postoperative patients in the pilot department was significantly reduced by 12.7 hours compared to before the system was used, with an average saving of 1.33 hours of input time per person per day. Conclusion The application of wearable vital signs mobile monitoring system realizes the data of vital signs monitoring and collection automatically and mobility, which shortened the rehabilitation cycle of postoperative patients and improved the work efficiency and satisfaction.

Objective By constructing a collaborative preparation management model for surgical medical apparatus on an information technology platform and implementing the application in a large public Grade-III Class-A hospital, its application practice and specific effects will be discussed in this article. Methods The construction of a multi-party collaborative packaging management model for surgical medical consumables based on the SPD information platform was analyzed in terms of the total time for preoperative consumable preparation, error rate in preoperative consumable preparation, time to obtain consumables during surgery, consumable billing time per surgery, postoperative inventory time per surgery, and surgical billing error rate before and after the application of the model. Results After the application of the multi-party collaborative packaging management model for surgical medical consumables based on the SPD information platform in a tertiary public hospital, there was a significant reduction in the total time for preoperative consumable preparation, error rate in preoperative consumable preparation, time to obtain consumables during surgery, consumable billing time per surgery, postoperative inventory time per surgery, and surgical billing error rate, with statistically significant differences (P < 0.05).Conclusion The collaborative preparation management mode of surgical medical apparatus based on SPD information platform is a high-efficiency, high-accuracy, and high-management effectiveness management mode of surgical medical apparatus, which could bring a revolution on this industry and refine management level of public surgical medical apparatus.

Conventional MRI mainly relies on the contrast between lesions and surrounding tissues for clinical diagnosis. Scanning sequences, scanning parameters, and hardware conditions all have an impact on it. Moreover, conventional contrast images cannot provide quantitative analysis data, which limits its further clinical application. Synthetic MRI (syMRI) can obtain quantitative data of tissues in a short time. It can not only quickly reconstruct contrast images but also conduct quantitative assessment. It has played an important role in the evaluation of various central nervous system diseases, especially for children with poor cooperation. Currently, syMRI has achieved good results in the measurement of relaxation time in children's central nervous system, brain volume segmentation and measurement, assessment of myelin development, and evaluation and prediction of brain development disorders. However, syMRI still has problems such as poor quality of synthetic FLAIR images, heavy phase encoding and liquid pulsation artifacts in synthetic T2WI, and overall data acquisition time is still too long. This article reviews the application of syMRI in children's central nervous system aimed to promote its further clinical promotion.

This paper presents a review around the application of wearable sleep breathing monitoring devices (WSMDs) in sleep disordered breathing (SDB). It elaborates that WSMDs are based on optoelectronic volumetric pulse wave, piezoelectric sensor and microphone to monitor physiological signals, and use filtering and machine learning algorithms to process the data, which are classified into wrist, finger-ring, and head-worn according to the wearing parts. Its sensitivity to moderate-to-severe obstructive sleep apnoea hypoventilation syndrome in SDB diagnosis is high, but consumer-grade devices have bias and are prone to miss diagnosis of mild OSA, and it has significant advantages in the diagnosis and monitoring of treatment effects in children. However, WSMDs face challenges in monitoring accuracy, comfort and wearer compliance. The aim of this paper is to provide reference for the technological innovation, clinical application and standardised development in this field, to promote multidisciplinary integration, and to help realise the accurate and universal management of SDB.

Wearable devices, integrating intelligent sensing technologies, enable real-time health monitoring, disease early warning, and rehabilitation assistance, driving the development of precision preventive medicine. This review focuses on the applications of wearable devices in the field of intelligent medicine, systematically expounding their current status in health monitoring, disease early warning, and rehabilitation assistance. It deeply analyzes the principles of sensor data collection and algorithm-based health assessment and disease early warning, demonstrates application effectiveness through practical cases, comprehensively analyzes the challenges in battery life, data accuracy, and user acceptance, and discusses corresponding strategies. Finally, the future development trends are prospected.

Coronary artery disease (CAD) is one of the major lethal factors worldwide, and pericoronary adipose tissue of whole coronary arteries, which is highly correlated with the progression of CAD, can be quantitatively assessed for inflammatory changes in coronary arteries based on coronary computed tomography angiography. However, pericoronary adipose tissue in whole coronary arteries has limited value in precise diagnosis, risk stratification, and therapeutic guidance because of the mismatch between its overall characteristics and the localized pathomechanisms of atherosclerosis. In contrast, pericoronary adipose tissue around coronary lesions, also known as lesion-specific pericoronary adipose tissue, may be more reliable and targeted in assessing predicting coronary inflammation and disease progression. With the breakthrough in medical imaging technology, lesion-specific pericoronary adipose tissue has been increasingly used in clinical research. Based on this, this article reviews the clinical studies of lesion-specific pericoronary adipose tissue in high-risk plaques, acute coronary syndromes, ischemic coronary stenosis, and major adverse cardiovascular events, with the aim of providing new ideas for the prevention and treatment of coronary artery disease.

This article explores the relevant standard requirements that need to be referenced when conducting hand-transmitted vibration tests on medical electrical equipment. It points out that the difficulties in conducting these tests arise from issues such as low integration, unclear applicability, and excessive lag in domestic method standards. The article also provides a detailed analysis of the testing equipment required for hand-transmitted vibration tests, sensor installation, and sample arrangement. It highlights that when conducting hand-transmitted vibration tests on medical electrical equipment according to current relevant national standards, the complexity and difficulty of achieving a suitable testing environment are due to the lack of compatibility among multiple method standards with significant time spans. Finally, the article proposes reasonable suggestions aimed at improving the inspection efficiency of medical device manufacturers and relevant inspection and testing institutions, and ensuring the accuracy of inspection and testing.

Objective To analyze and evaluate the application value of integrated management combined with reprocessing risk control in the handling of rigid endoscopic instruments within the hospital's Central Sterile Supply Department (CSSD). Methods Through integrated management combined with reprocessing risk control, 800 rigid endoscopic instruments collected from the central operating room and outpatient operating room of a tertiary hospital in Anhui Province from July 2024 to November 2024 were selected as the control group, and 895 rigid endoscopic instruments collected from December 2024 to April 2025 were selected as the observation group. The application effect of the integrated management combined with reprocessing risk control model was verified by comparing the disinfection management status, quality management adverse events, quality management quality, and surgeon satisfaction of rigid endoscopic instruments between the two groups. Results The cleaning qualification rate, packaging qualification rate, the observation group exhibited significantly superior performance in terms of distribution qualification rate compared with the control group, while the resterilization rate was lower than that of the control group. The incidence of quality management adverse events of rigid endoscopic instruments in he observation group exhibited a significantly lower rate compared to the control group. The quality management quality score of rigid endoscopic instruments in the observation group exhibited a significantly higher level compared to the control group. Conclusion Integrated management combined with reprocessing risk control can effectively improve the management efficiency and quality of rigid endoscopic instruments.

Prostate cancer, as the most prevalent cancer among men, poses a serious threat to male health. Compared with traditional open surgery, interventional therapy has the advantages of small incisions, fewer side effects, faster recovery and lower infection rates. To achieve precise, standardized and real-time dynamic prostate interventional treatment, the integration of robot technology with minimally invasive surgery and magnetic resonance imaging (MRI) technology is proposed, and the development of MRI-guided prostate interventional robots is initiated. Based on a review of the current research status of MRI-guided prostate interventional robots at home and abroad, the focus is on analyzing the magnetic resonance compatibility of the robots. Key technologies such as material selection, timing and spatial coordination of adjustment operations, multi-physical field coupling compatibility of drive control methods, and structural optimization are introduced and analyzed. These technologies make interventional diagnosis and treatment under MRI guidance possible for robots. The MRI-guided prostate interventional robot breaks through the limitations of the MRI environment, promotes the integration of multiple disciplines and the development of smart healthcare, and has broad application and development prospects. Finally, the development trends of MRI-guided prostate interventional robot technology are prospected.

Objective To evaluate the accuracy of a deep learning-based intelligent contouring system in delineating head and neck organs at risk (OAR) and to explore its potential application in clinical radiotherapy. Methods Forty-five cases of head and neck tumor patients' positioning CT images were randomly selected. The SmartContour.AI software was used to contour 12 important OARs in the head and neck region (brainstem, spinal cord, left and right optic nerves, optic chiasm, left and right eyeballs, left and right lenses, left and right parotid glands, thyroid gland), and compared with the manual contouring by senior physicians. The consistency between automatic and manual contouring was quantitatively analyzed using seven geometric evaluation metrics, including Hausdorff distance (HD), Dice similarity coefficient (DSC), Jaccard coefficient, centroid deviation (CMD), sensitivity coefficient (SI), inclusiveness coefficient (II), and volume difference (VD). Additionally, the clinical acceptance of the intelligent contouring system was assessed by subjective evaluation from senior physicians. Results In terms of geometric accuracy, the maximum mean Hausdorff distance was 10.73 mm for the right optic nerve, and the minimum was 1.03 mm for the left lens. The mean DSC index for the OARs ranged from a minimum of 0.68 for the right optic nerve to a maximum of 0.95 for the right eyeball. The mean Jaccard coefficient for the OARs was highest for the right eye at 0.91 and lowest for the right optic nerve at 0.57. The maximum mean centroid deviation (CMD) was 4.08 mm for the right optic nerve and the minimum was 0.48 mm for the left lens. The sensitivity coefficient (SI) was relatively low for the left and right optic nerves and optic chiasm, at 0.63, 0.59, and 0.67, respectively, The SI value of the right eyeball is the largest, approaching 1.00. The mean inclusiveness coefficient (II) for all organs was ≥0.84. In terms of volume difference (VD), the brainstem, spinal cord, left and right eyeballs, left and right lenses, and thyroid gland were close to 0, while the VD values for the parotid gland, optic chiasm, and optic nerve exceed 0.10. In terms of clinical acceptance, the parotid glands, optic nerves, and optic chiasm had lower clinical acceptance, while the acceptance for the other organs was relatively high. Conclusion Automatic contouring of the brainstem, spinal cord, eyeballs, lenses, and thyroid gland showed high geometric consistency with manual contouring and was well accepted clinically, while automatic contouring of the parotid glands, optic nerves, and optic chiasm required further physician review and substantial modification.

Objective Under the background of the normalization of orthopedic medical consumables collection, an early warning mechanism for the use of medical consumables is established to help medical institutions better adapt to the collection policy, provide data basis for managers, facilitate the timely adoption of management measures, guide the rational use of medical consumables, and make the management of consumables more scientific, intelligent and refined. Methods Systematic method and induction method were used to analyze the difficulties and risk points in the management of orthopedic medical consumables after the collection and mining of orthopedic medical consumables became normal. Based on information technology, the early warning mechanism for the use of medical consumables was established. The use monitoring and analysis were only conducted for the indicators such as the use quantity, cost and benefit of medical consumables, and multi-dimensional comprehensive monitoring was adopted to fully reflect the use of various consumables. Use big data analysis to give early warning to abnormal data and unreasonable use. Results By establishing an early warning mechanism, the hospital has improved its management mechanism for the use of medical consumables, reducing the proportion of key monitoring consumables. The proportion of 18 key monitoring consumables has decreased by 10.46% compared to 2023. The joint procurement task for the new year has been 100% completed, improving the hospital's management efficiency and effectiveness, and achieving an overall improvement in the management level of orthopedic medical consumables. Conclusion The establishment of the early warning mechanism for medical consumables puts forward clear management ideas and scientific management methods for monitoring the use of medical consumables after collection of orthopedic consumables, which can be properly promoted to help managers of large public hospitals make more scientific decisions, conduct preventive monitoring of medical consumables in hospitals, prevent the accumulation of minor problems, and constantly strengthen the connotation construction of hospital consumables monitoring system. Detect suspected problems through monitoring, control the source and continuous improvement.

Objective This study aimed to construct a maintenance quality evaluation index system for continuous renal replacement therapy devices based on the "structure-process-outcome" three-dimensional quality evaluation model to guide clinical practice. Methods Through the evidence-based method and the theoretical framework of the "structure-process-result" model, the first draft of the correspondence was constructed, and two rounds of expert correspondence were conducted by the Delphi method to determine the items at each level of the evaluation index, and finally the evaluation index system of maintenance quality of continuous renal replacement therapy device was formed. Results A total of 24 experts were selected for consultation. The active coefficients of experts in the two rounds of consultation were 82.35% and 100.00%, and the authority coefficients were 0.871 and 0.900. The coordination degree of expert opinions was good. The Kendall's coefficients of concordance in the two rounds of consultation were 0.160 and 0.166, P < 0.001. A maintenance quality evaluation index system for continuous renal replacement therapy devices was formed, including 3 first-level indicators, 12 second-level indicators and 52 third-level indicators. Conclusion The quality evaluation index system for the maintenance of continuous renal replacement therapy devices constructed based on the three-dimensional quality evaluation model has good consistency and scientific nature, and can provide a basis for the management of the maintenance quality of continuous renal replacement therapy devices.

Objective The next-generation integrated design of Positron Emission Tomography/Magnetic Resonance (PET/MR) combines PET detectors into the MR device, enabling simultaneous data collection from both detectors in the same space. However, the stability of the PET component in this new device structure during daily clinical operations requires further investigation. This study tracks nearly 16 months of source quality control data from the digital integrated uPMR 790 PET/MR system, five years after installation, to explore the stability of the digital integrated PET/MR system in clinical use and the influencing factors between PET source quality control parameters. Methods Under clinical application conditions, source quality control of the uPMR 790 system was conducted based on the daily quality assurance (DQA) guidelines issued by the equipment manufacturer. Data from 72 weeks of source quality control system tests from January 2023 to May 2024 were collected, including system temperature and voltage, Look-Up Table (LUT), collection system (CMap), Time of Flight (TOF), and system energy state drift. Spearman correlation analysis and Mann-Whitney U tests were used to analyze the system quality control parameters. Multiple linear regression analysis was conducted to explore the influencing factors of TOF drift. Results The overall pass rate for 72 PET/MR source quality control tests was 100%. TOF state drift showed a positive correlation with LUT state drift (r = 0.614, P < 0.001) and a negative correlation with the system's maximum temperature (r = -0.736, P < 0.001). There were distributional differences between TOF state drift and changes in the system's acquisition CMap state (Z = 4.872, P < 0.001). Multiple linear regression analysis revealed that LUT drift (β = 0.705, P < 0.001) and system acquisition CMap (β = 0.131, P = 0.031) had positive effects on the degree of TOF drift, while the system's maximum temperature (β = -0.263, P < 0.001) had a negative effect on the degree of TOF drift. Conclusion After five years of clinical use, Over the past 16 months, the testing parameters for PET source quality control have remained within normal ranges, and the equipment has demonstrated stable performance in daily clinical applications. However, attention should be paid to potential drifts in parameters related to the PET detectors during source quality control. Regular monitoring, combined with risk alerts, is essential to ensure the long-term stability of the equipment and the reliability of diagnostic outcomes.