Device Description Research Articles

Medical device similarity analysis: a promising approach to medical device equivalence regulation

ABSTRACT Background This study aims to facilitate the identification of similar devices for both, the European Medical Device Regulation (MDR) and the US 510(k) equivalence pathway by leveraging existing data. Both are related to the regulatory pathway of read across for chemicals, where toxicological data from a known substance is transferred to one under investigation, as they aim to streamline the accreditation process for new devices and chemicals. Research design and methods This study employs latent semantic analysis to generate similarity values, harnessing the US Food and Drug Administration 510k-database, utilizing their ‘Device Descriptions’ and ‘Intended Use’ statements. Results For the representative inhaler cluster, similarity values up to 0.999 were generated for devices within a 510(k)-predicate tree, whereas values up to 0.124 were gathered for devices outside this group. Conclusion Traditionally, MDR equivalence involves manual review of many devices, which is laborious. However, our results suggest that the automated calculation of similarity coefficients streamlines this process, thus reducing regulatory effort, which can be beneficial for patients needing medical devices. Although this study is focused on the European perspective, it can find application within 510(k) equivalence regulation. The conceptual approach is reminiscent of chemical fingerprint similarity analysis employed in read-across.

Assessment of COVID-19-related medical device regulator policies on entry to market for prioritised devices: a case study

Background/Aims In response to the COVID-19 pandemic, medical devices were given exceptional use authorisations. Medical device regulators around the world modified their administrative approach to medical device approval to ensure that relevant devices and personal protection equipment would be available to healthcare professionals and patients. Using data from medical device regulators in the US and Australia, this study assessed the impact of COVID-19-related regulatory modifications implemented to allow quick market entry of relevant equipment, and how data science techniques can help to inform future policy. Methods Data from the US Food and Drug Administration's Global Unique Device Identification Database and the Australian Therapeutic Goods Administration's Australian Register of Therapeutic Goods were used as case studies to explore the effects of policy changes. All COVID-19-related devices and personal protective equipment were identified in the data using the Global Medical Device Nomenclature system and device descriptions. A 10-day and 20-day moving average was applied to assess how many of these devices reached the market between 30 July 2019 and 24 June 2020. Results In both the US and Australian datasets, the number of market entries increased after the pandemic began. However, the impact of the Australian policy appeared to be greater than that of the US, as there was a considerable increase in the number of personal protective equipment and COVID-19-related device registrations following the declaration of the pandemic in Australia, while the impact on the US data was relatively minimal. Conclusions In general, market entry of relevant equipment increased during the COVID-19 pandemic, indicating the possible impact of policy changes. The kind of data captured in national databases greatly influences the ability to accurately track performance of regulatory policy changes. This work shows the potential of using data science in a regulatory context to assess if a policy change creates the desired effect.

Classification of broadband network devices using text mining technique

The Broadband Internet industry is highly competitive, with service providers investing heavily in network development to meet customer demands and competing on pricing. Effective cost management is crucial for profitability in this market. This work proposes a model for classifying broadband network devices based on text mining techniques applied to a device list from a leading broadband network company in Thailand. The device descriptions are used to generate a feature vector, which is then employed by a classification algorithm to categorize devices into core, access, and last mile hierarchies. Various algorithms including decision tree, naïve Bayes, Bayesian network, k-nearest neighbor, support vector machine, and deep neural network are compared, with support vector machine achieving the highest accuracy of 90.35%. The results are visualized to provide insights into network hierarchy, device replacement dates, and budget requirements, enabling support for cost management, budget planning, maintenance, and investment decision-making. The methodology outline includes,•Obtaining a device list from a major broadband network company and extracting device descriptions through text mining and generating a feature vector.•Using a support vector machine for classification and comparing algorithm performances.•Visualizing the results for actionable insights in cost management, budget planning, and investment decisions.

Ultrasonic bone scalpel for long bone resections in limb reconstruction: Device description and case series

IntroductionWhile the ultrasonic bone scalpel (UBS) has shown benefits, including decreased surgical duration, blood loss, and local tissue thermal injury, its implementation has been limited to skull base and spinal surgery. This case series sought to determine the safety and advantages of the UBS for bony resections in limb reconstructive procedures. MethodsA retrospective review of four patients with a median age of 42 ± 13.38 at the time of resection and bone segment transport (BST) surgery was performed with UBS. Patients with prior history of lower extremity trauma with sequelae including non-union (2), osteomyelitis (1), or both (1). Intraoperative and post-operative courses and complications were documented. ResultsEach patient underwent tibial resection with UBS with a median bone resection size of 6.6 ± 2.85. Three patients underwent BST using cables and external fixator and one underwent plate-assisted BST with an intramedullary device. All patients had proximal corticotomies and antegrade transport, with a formal docking procedure at the end of transport. Complications included fixator cable tensioning device failure, frame readjustment, and pin tract infections. Two patients required subsequent grafting for docking site nonunion. One patient terminated bone transport early. No neurovascular injuries, hematomas, or dead space infections were reported. ConclusionThe UBS offers a safe mechanism for long bone resections in lower extremity limb reconstruction. Neurovascular structures within the resection zone were preserved and uninjured, demonstrating major advantages in using this technology. Further study is needed to assess the risk for docking site nonunion with UBS.

A Market Assessment of Introducer Technology to Aid With Endotracheal Intubation.

Endotracheal intubation is a potentially lifesaving procedure. Previously, data demonstrated that intubation remains the most performed airway intervention in the Role 1 setting. Additionally, deployed data demonstrate that casualties intubated in the prehospital setting have worse survival than those intubated in the emergency department setting. Technological solutions may improve intubation success in this setting. Certain intubation practices, including the use of endotracheal tube introducer bougies, facilitate intubation success especially in patients with difficult airways. We sought to determine the current state of the market for introducer devices. This market review utilized Google searches to find products for intubation. The search criteria aimed to identify any device ideal for intubation in the emergency setting. Device data retrieved included manufacturer, device, cost, and design descriptions. We identified 12 introducer-variants on the market. Devices varied with regards to composition (latex, silicone, polyethylene, combination of several materials, etc.), tip shape, special features for ease of intubation (markings for depth and visibility, size, etc.), disposability/reuse capability, measurements, and prices. The cost of each device ranged from approximately $5 to $100. We identified 12 introducer-variants on the market. Clinical studies are necessary to determine which devices may improve patient outcomes in the Role 1 setting.

0462 CPAP-Experienced Patient Perceptions of CPAP & Novel Nasopharyngeal Airway Device as CPAP Alternative for Obstructive Sleep Apnea

Abstract Introduction Untreated obstructive sleep apnea (OSA) can impact numerous critical organ systems with drastic health ramifications while decreasing daily quality of life of individuals and their family. While Continuous Positive Airway Pressure (CPAP) can be highly effective, adherence is remarkably low. This is a preliminary initiative to gauge patient perceptions of a new non-surgical nasopharyngeal airway (NPA) device in development for OSA. Methods An IRB-approved single-site study surveyed 10 patients with polysomnography-confirmed OSA and at least 3 months’ experience using CPAP therapy. An independent expert in patient-reported outcomes helped develop the instrument to understand perceptions and attitudes towards CPAP and gauge initial reactions to the NPA-OSA device. This was reviewed by three Sleep Medicine experts for content validity. An NPA-OSA device description and insertion training video were provided to elicit feedback. Sixty-minute telephone interviews were conducted with OSA patients and transcribed by the independent expert. Results Ten patients (4 male), participated with an age range from 31 to 82 years. Nine used CPAP nightly, although described situations when they would not. All participants described significant dissatisfaction with some aspect of their CPAP treatment (e.g., restrictions on sleep position, difficulty cleaning and traveling, reliance on electricity), though most cope and appreciate therapeutic benefit. Respondents were motivated to find new treatment options for OSA, but were not actively seeking new options. Surgical treatment was considered by most, but with fear of unsuccessful outcomes/complications. A few of the respondents had previously used oral appliances with limited success. When introduced to the NPA device, most participants were interested in trying it. Positive attributes were non-invasive, portable and not requiring electricity. Ultimately, participants believed that the device had the potential to improve sleep. Primary concerns were the potential of pain during insertion, discomfort during use, and treatment effectiveness. All those interviewed were interested in participating in a clinical trial using the device. Conclusion Patients successfully using CPAP may still be dissatisfied and motivated to explore new options. The NPA-OSA device was considered a compelling option. Support (if any) This work was funded by the University of Michigan Coulter program.

PO-04-178 E-COMMERCE DIRECT-TO-CONSUMER RHYTHM MONITORING DEVICES: CLEARED FOR LANDING OR CLEAR AS MUD?

Direct-to-consumer (DTC) digital health products, especially personal ECG monitoring devices, have grown exponentially. Marketing studies show that ∼70% of consumers never click beyond the 1st search engine results page (SERP) of an online e-commerce (e-comm) site and frequently purchase from the 1st few products listed. Whether the majority of personal ECG devices available on e-comm platforms in the United States are FDA cleared or validated is unknown. To characterize DTC personal ECG monitoring devices on a popular e-commerce website. The most popular U.S. e-commerce website, Amazon.com (Amazon.com, Inc., Seattle, WA), was searched for “personal ECG.” Results on the 1st SERP were ranked in order of position on the webpage. Non-heart monitoring devices & duplicates were excluded. Devices were analyzed for name, type of analysis offered, presence of an external website, presence of non-medical use disclaimers, and for FDA clearance statement in the e-comm device description or on an external website. Results were cross-referenced to the FDA 510(k) clearance database and to PubMed for validation studies. A total of 61 devices were listed on the 1st SERP, of which 21 (43%) were excluded. The remaining 40 devices were: 23 (58%) ECG-capable, 7 (18%) PPG-rhythm capable, and 10 (25%) heart-rate only. Seven (70%) of the 1st ten devices on the SERP could not be found in the FDA 510(k) database. Of the 30 ECG or PPG-rhythm capable devices, 14 (47%) were not listed in the FDA 510(k) database: 2 advertised FDA clearance on an external webpage but were not listed in the FDA 510(k) database, 11 (79%) offered rhythm analysis with 2 (14%) also offering automatic QTc, 6 (43%) had a clearly stated non-medical use disclaimer in the e-comm description. Of the 16 (53%) devices confirmed to have FDA 510(k) clearance, 4 (25%) stated this clearly in the e-comm description. Validation studies were found for 13 (81%) of FDA-cleared vs 1 (7%) of non-FDA-cleared devices. Nearly half of DTC “personal ECG” devices on the 1st SERP of a popular e-commerce site may not be FDA cleared, do not have non-medical use disclaimers and the majority do not have validation studies. Also, few FDA-cleared devices are clearly labeled as such on the site. This can be potentially confusing and misleading for patients and consumers. Education to increase awareness and health policies for regulation are needed for this issue.

New Device of Neonatal Ostomy: To Effectively Reduce the Postoperative Complications of Neonatal Ostomy.

Background need. Complications frequently occur after neonatal enterostomy. Enterostomy formation is a common outcome following emergency neonatal laparotomy. We introduce a new method for improving proximal enterostomy in newborns.Methodlogy and device description. We added a simple drainage device on the proximal enterostomy.The simple drainage device consists of several materials: a foreskin cerclage staple (Chong Qing BORN Biological Technology Co. Ltd., Sichuan, China), a condom,and 0- Mersilk Silk braided nonabsorbable suture (ETHICON 15 × 60cm).Preliminary results. A total of 20 cases participated in the study. All surgeries were performed by a single surgeon. The cases only occurred one case of prolapse of the intestinal, one case of premature surgery due to excessive orifice flow, and one case of periostomy dermatitis, Other patients not experienced intraoperative or postoperative complications.Current status. Based on our preliminary observations, the simple drainage device is a safe and effective operation device that can reduce the risk of stoma-related complications.

Static and Small-Signal Modeling of Radiofrequency Hexagonal Boron Nitride Switches

A first modeling approximation of the general performance of radiofrequency (RF) switches based on hexagonal boron nitride (hBN), a two-dimensional (2D) dielectric material is presented. The I-V characteristics intrinsic and extrinsic impedance parameters, the return loss, insertion loss and isolation of RF 2D switches fabricated with hBN are described here by a equivalent circuit models. Straightforward analytical expressions are obtained. In contrast to conventional switches, the unique RF performance of the hBN switch, at ON-state, i.e., a direct improvement with frequency of the insertion loss, is accurately described by considering a capacitor in the intrinsic part of the model. The latter is suggested to be related to storaged charge during the resistive switching mechanism. The highest mean relative error obtained between modeling and measurements of the return loss is of 7.6% with the approach presented here which overcomes the 42.5% of difference obtained with a previous model with an incomplete intrinsic device description.

An Alternative Airway Intervention to Preserve the Surgical Field in Oral and Maxillofacial Surgery.

Background/need. Office-based sedation has become increasingly commonplace in dental offices in recent years, allowing for practitioners to provide broader scope of care for their patients. Maintaining high standards of safety is of utmost importance when sedation is utilized in the office-based setting, especially for patients deemed at a higher-risk for intraoperative airway obstruction. This demographic includes but is not limited to individuals with a medical history significant for obstructive sleep apnea, chronic obstructive pulmonary disease, and morbid obesity. Presently, a wide variety of airway devices exist for use in the event of airway obstruction. However, in the context of oral and maxillofacial surgery, placement of these devices can encroach upon the surgical field, extending the perioperative period and putting the patient at greater long-term risk for maintaining adequate oxygenation. Methodology. The authors describe a preliminary technique trialed in our offices which utilizes a size 5.0 endotracheal tube (5OET) as an adjunct supraglottic airway to help mitigate the issue of oxygen saturation maintenance, as well as unimpeded access to the oral cavity. Implementation of the device requires identifying appropriate candidates during preoperative screening and placing the device through the nare and securing it above the glottis. Device Description. The 'tube kit' is comprised of a standard size straight 5.0 cuffed oral ETT, a 5-mL syringe for inflation of the cuff post insertion, lubricant, flex extension tubing, end tidal sampling line for capnography, tape for securement of the 5OET, and an anesthesia breathing circuit. Optional equipment pieces include an elbow connecter and a foam piece for comfort. Results/Current Status. Preliminary results have demonstrated oxygen saturations maintained above 98% when the 5OET is placed preoperatively. Continued use of the trial device will inform the development of a tube by our clinicians, and its efficacy will be studied in our offices. The next steps will be to start developing a pilot cuff that will be submitted for patent approval after its use in IRB-approved clinical studies.

A Point-of-Care Device for Fully Automated, Fast and Sensitive Protein Quantification via qPCR.

This paper presents a fully automated point-of-care device for protein quantification using short-DNA aptamers, where no manual sample preparation is needed. The device is based on our novel aptamer-based methodology combined with real-time polymerase chain reaction (qPCR), which we employ for very sensitive protein quantification. DNA amplification through qPCR, sensing and real-time data processing are seamlessly integrated into a point-of-care device equipped with a disposable cartridge for automated sample preparation. The system’s modular nature allows for easy assembly, adjustment and expansion towards a variety of biomarkers for applications in disease diagnostics and personalised medicine. Alongside the device description, we also present a new algorithm, which we named PeakFluo, to perform automated and real-time quantification of proteins. PeakFluo achieves better linearity than proprietary software from a commercially available qPCR machine, and it allows for early detection of the amplification signal. Additionally, we propose an alternative way to use the proposed device beyond the quantitative reading, which can provide clinically relevant advice. We demonstrate how a convolutional neural network algorithm trained on qPCR images can classify samples into high/low concentration classes. This method can help classify obese patients from their leptin values to optimise weight loss therapies in clinical settings.

Pulse oximeters market analysis during the COVID-19 pandemic: Kyiv pharmacies’ offers and survey of pharmacy faculty students

Abstract Objectives The objective of this study was to study the market of pulse oximeters to select the optimal choice for monitoring health status during the COVID-19 pandemic. Methods Pulse oximeter data, presented on the Tabletki.ua website (2021) in Kyiv (Ukraine), were summarized and discussed. A survey about the history of the device purchase among 170 students of the Faculty of Pharmacy (Zaporizhzhia State Medical University, Ukraine) was statistically analysed by Kolmogorov–Smirnov, Shapiro–Wilk, Levene’s, Scheffe tests, one-sample t-test, Spearman’s correlation and one-way ANOVA. Key findings The largest part of the Kyiv (Ukraine) pulse oximeter market is occupied by the People’s Republic of China (70.97%). The price ranged from UAH 171.50 to UAH 1799.00. The models S6 and Linke LK88 are found to be the best choices according to the fullest provided data, the lowest minimum price and emphasis on the oxygen saturation and pulse rate accuracies. Medical students statistically significant would buy a pulse oximeter for less than UAH 563.40 (t(76) = −2.884; P = 0.005). The price did not depend on age (F = 1.104, P = 0.372) or gender (F = 2.466, P = 0.121), but there was a correlation between price and year of purchase (F = 2.712, P = 0.051). Students are primarily interested in country of origin, guarantees and pharmacist recommendations. A significantly weak Spearman’s correlation was found between price and friend advice (ρ = 0.275, Sig. = 0.015). Conclusions The same models differ in price by up to 4.2 times and in between them – up to 10. Less than half of the responders bought devices, and even a quarter of them did not use them at all, although they were from a health field. The detailed notifications about accuracy for different patient skin types are required in the device description. More people should be aware of pulse oximeter importance to maintaining health after COVID-19.

Barcodes as Optical Marks for an Objective Assessment of Laparoscopic Skills in a Box Trainer.

Background/Need. The sensor-equipped box trainers can objectively evaluate psychomotor skills similar to virtual simulators. However, such box models are least of all involved in curricula in minimally invasive surgery, probably because of their complexity or high cost. This discrepancy prompted us to find a simple solution that provides an objective assessment of laparoscopic skills on any box trainer. Methodology and Device Description. We used QR code, Code 128, and Circular Code 128 as optical marks in tasks on box trainers. These were marks of errors and positive actions. Polyvinylchloride and a nontransparent silicone sheet served as materials for the tasks. All barcode images were printed with black ink on office paper. In addition, we have developed an app that allows dealing with selected types of barcodes. Preliminary results. We designed 6 tasks based on our approach. Every task provides a precision registration of time, errors, and correct actions, comparable with virtual simulators. However, only 4 tasks showed satisfactory results during face validity's obtaining. We found that primitive barcode scanning technology can provide an objective assessment of trainees on box trainers. The proposed approach is well suited for both commercial and custom box trainers. Current status. The research is currently underway to establish construct validity for the developed tasks. Besides, we intend to study features of other types of barcodes, such as Aztec Code, EAN-8, DataMatrix, and annular barcodes.

Lost in Transit: Implications and Insights for Making Medical Task Trainer Prototypes with an Open Source Hardware Paradigm

AbstractThis paper presents an open-source novel intravenous cannulation task trainer developed during the Covid- 19 pandemic for unsupervised clinical skill practice. Multiple user errors were uncovered when observing 13 registered nurses using the task trainer during a two-hour unsupervised skill training session. These insights raise the question of how OSH needs to share more than just device descriptions and assembly instructions- as designs are being shared only in its current state of an ongoing project, sharing insights, user errors and test results should be encouraged and prioritized.

Internet-of-Things object model

Background: With the advancement of communication technology and advanced sensors, there are massive demands for Internet-of-Things (IoT) applications in buildings, communities, factories, parks, etc. Accessing IoT devices provides convenience for scene management and monitoring, ameliorating production and life intelligently. However, due to the lack of a unified model for IoT devices, data is often skipped over IoT platforms and transmitted to applications directly. This leads to the fact that each manufacturer needs to produce its devices and develop its customized software, which hugely increases the development cycle. On the other hand, it is difficult to convey information between different systems, limiting cross- system control. Moreover, digital twin relies on large amounts of heterogeneous data, and it is impracticable to provide enough data without a unified model for device description. Methods: First, we illustrate the motivation, design goals, and design principles for creating the Internet-of-Things Object Model (IoT-OM). Then we propose a unified description to define IoT devices. The proposed concept has been accepted by several companies, and we analyse one platform that adopts the model. To demonstrate the effectiveness of the model, we introduce two projects based on the platform. One project is an intelligent fire protection system, and another project is an intelligent air quality monitoring system. Results: We measured the time taken by five companies when developing IoT devices and their applications, including the development cycle duration without utilizing the proposed model and the duration using the model at China Mobile’s OneNET platform. The results prove that the proposed model can significantly shorten the development cycle. Conclusions: This paper proposes a model for IoT devices, which helps to unify heterogeneous data among different manufacturers and helps to shorten the development cycles for developers.

ECHONET Lite Framework Based on Embedded Component Systems

The large number and many types of electrical equipment in modern house-holds pose major challenges to developers. To increase the breadth of smart homes, improving the development e°ciency of electrical equipment in smart homes is essential. The present research proposes a development method based on embedded components for devices in smart homes. Besides improving the development e°ciency, this method of development reduces the developmental complexity and increases the scalability of elec-trical equipment. The smart home devices are developed and controlled in TOPPERS Embedded-Component System (TECS), a component description language that automatically generates template C ˝les when expand-ing new components or functions. Using the ECHONET Lite plugin, TECS then reads the parameters of the electrical device in the device description ˝le (JSON ˝), and outputs the function parameters for implementation by the developer. The evaluation shows that the code automatically gen-rated by the plugin slows down the software execution time by only 2%compared with the default, thus improving the software development efficiency.

IoT Device Integration and Payment via an Autonomic Blockchain-Based Service for IoT Device Sharing.

The Internet of Things (IoT) incorporates billions of IoT devices (e.g., sensors, cameras, wearables, smart phones, as well as other internet-connected machines in homes, vehicles, and industrial plants), and the number of such connected IoT devices is currently growing rapidly. This paper proposes a novel Autonomic Global IoT Device Discovery and Integration Service (which we refer to as aGIDDI) that permits IoT applications to find IoT devices that are owned and managed by other parties in IoT (which we refer to as IoT device providers), integrate them, and pay for using their data observations. aGIDDI incorporates a suite of interacting sub-services supporting IoT device description, query, integration, payment (via a pay-as-you-go payment model), and access control that utilise a special-purpose blockchain to manage all information needed for IoT applications to find, pay and use the IoT devices they need. The paper describes aGIDDI’s novel protocol that allows any IoT application to discover and automatically integrate and pay for IoT devices and their data that are provided by other parties. The paper also presents aGIDDI’s architecture and proof-of-concept implementation, as well as an experimental evaluation of the performance and scalability of aGIDDI in variety of IoT device integration and payment scenarios.

Virtual Bronchoscopy-Guided Transbronchial Biopsy Simulation Using a Head-Mounted Display: A New Style of Flexible Bronchoscopy.

Background/need. The increases in reference images and information during bronchoscopy using virtual bronchoscopic navigation (VBN) and fluoroscopy has potentially created the need for support using a head-mounted display (HMD) because bronchoscopists feel difficulty to see displays that are at a distance from them and turn their head and body in various directions. Methodology and device description. The binocular see-through Moverio BT-35E Smart Glasses can be connected via a high-definition multimedia interface and have a 720p high-definition display. We developed a system that converts fluoroscopic (live and reference), VBN, and bronchoscopic image signals through a converter and references them using the Moverio BT-35E. Preliminary results. We performed a virtual bronchoscopy-guided transbronchial biopsy simulation using the system. Four experienced pulmonologists performed a simulated bronchoscopy of 5 cases each with the Moverio BT-35E glasses, using bronchoscopy training model. For all procedures, the bronchoscope was advanced successfully into the target bronchus according to the VBN image. None of the operators reported eye or body fatigue during or after the procedure. Current status. This small-scale simulation study suggests the feasibility of using a HMD during bronchoscopy. For clinical use, it is necessary to evaluate the safety and usefulness of the system in larger clinical trials in the future.

Toward a Digital Twin for Arthroscopic Knee Surgery: A Systematic Review

The use of digital twins to represent a product or process digitally is trending in many engineering disciplines. This term has also been recently introduced in the medical field. In arthroscopic surgery education, the paradigm shift from apprenticeship to simulation training has driven the need for better simulators, and the current focus is on improving simulators with respect to computational efficiency and system accuracy. However, expanding surgical simulations towards digital twins has not yet been explored. This paper introduces the digital twin concept for arthroscopic surgery, and explores its potential in light of the existing scientific literature. Thus, a systematic review was conducted to summarize and analyze the literature with respect to fast and robust design of an arthroscopic digital twin using patient-specific information, and methods for interactive surgical soft tissue simulation. The review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol with three reliable scientific search engines: IEEE Xplore, ScienceDirect and PubMed. Eighty papers were included in the review, and the extracted data included modeling methods, tissue types, constitutive behavior, computational efficiency or accuracy, hardware configuration, haptic device description, software tools, and system architectures. Considering the review, a novel macro-level conceptual arthroscopic digital twin system is presented, and the applicability of the review findings for the identified subsystems are discussed. The proposed system integrates patient-specific images, diagnostic data, intraoperative sensor data, and surgical practice as inputs, and conceptually enables surgical skills training, preoperative planning, and a database of virtual surgeries.

WND-Identifier: Automated and Efficient Identification of Wireless Network Devices

The widespread application of wireless communication technology brings great convenience to people, but security and privacy problems also arise. To assess and guarantee the security of wireless networks and user devices, discovering and identifying wireless devices become a foremost task. Currently, effective device identification is still a challenging issue, as device fingerprinting requires huge training datasets and is difficult to expand, and rule-based identification is not accurate and reliable enough. In this paper, we propose WND-Identifier, a universal and extensible framework for the identification of wireless devices, which can generate high-precision device labels (vendor, type, and product model) efficiently without user interaction. We first introduce the concept of device-info-related network protocols. WND-Identifier makes full use of the natural language features in such protocol messages and combines with the device description in the welcome page, thereby utilizing extraction rules to generate concrete device labels. Considering that the device information in the protocol messages may be incomplete or forged, we further take advantage of the application logic independence and stability of the device-info-related protocol, so as to build a multiprotocol text classification model, which maps the device to a known label. We conduct experiments in homes and public networks and present three application scenarios to verify the effectiveness of WND-Identifier.