Artificial Intelligence Devices Research Articles

Accuracy of an artificial intelligence-enabled diagnostic assistance device in recognizing normal chest radiographs: a service evaluation.

Artificial intelligence (AI) enabled devices may be able to optimize radiologists' productivity by identifying normal and abnormal chest X-rays (CXRs) for triaging. In this service evaluation, we investigated the accuracy of one such AI device (qXR). A randomly sampled subset of general practice and outpatient-referred frontal CXRs from a National Health Service Trust was collected retrospectively from examinations conducted during November 2022 to January 2023. Ground truth was established by consensus between 2 radiologists. The main objective was to estimate negative predictive value (NPV) of AI. A total of 522 CXRs (458 [87.74%] normal CXRs) from 522 patients (median age, 64 years [IQR, 49-77]; 305 [58.43%] female) were analysed. AI predicted 348 CXRs as normal, of which 346 were truly normal (NPV: 99.43% [95% CI, 97.94-99.93]). The sensitivity, specificity, positive predictive value, and area under the ROC curve of AI were found to be 96.88% (95% CI, 89.16-99.62), 75.55% (95% CI, 71.34-79.42), 35.63% (95% CI, 28.53-43.23), and 91.92% (95% CI, 89.38-94.45), respectively. A sensitivity analysis was conducted to estimate NPV by varying assumptions of the prevalence of normal CXRs. The NPV ranged from 88.96% to 99.54% as prevalence increased. The AI device recognized normal CXRs with high NPV and has the potential to increase radiologists' productivity. There is a need for more evidence on the utility of AI-enabled devices in identifying normal CXRs. This work adds to such limited evidence and enables researchers to plan studies to further evaluate the impact of such devices.

A study on the application of artificial intelligence in the design of intelligent medical robots

Abstract With the development of artificial intelligence and robotics technology, the combination of artificial intelligence and medical device research and development has been promoted, which is an important product of the development of artificial intelligence. In this paper, the general structure of the intelligent medical robot is designed by combining artificial intelligence technology and robotics-related technology. Then, the binocular vision function of the robot was realized by visually acquiring the image of the target object, 3D reconstruction of the target object, and combining the SIFT image recognition algorithm and target tracking algorithm. Then, a new speech recognition algorithm was constructed to realize the human-robot interaction function with the medical robot based on the deep learning Transforme network after the construction of the human acoustic model. Finally, the designed intelligent medical robot was tested, and its overall performance was evaluated. The results show that the recognition errors of the intelligent medical robot on the features of the items are all within 0.05, the recognition errors on the features of the human body are within 0.2, and the speed of the target tracking is between 6km/h and 16km/h. The average recognition accuracy of the medical robot for voice commands is about 0.9, the recognition time is about 0.7s, the normal working rate of each function is more than 0.99, and the test speed is within 2s.

Regulating Artificial Intelligence and Machine Learning-Enabled Medical Devices in Europe and the United Kingdom

Recent achievements in respect of Artificial Intelligence (AI) open up opportunities for new tools to assist medical diagnosis and care delivery. However, the typical process for the development of AI is through repeated cycles of learning and implementation, something that poses challenges to our existing system of regulating medical devices. Product developers face tensions between the benefits of continuous improvement/deployment of algorithms and keeping products unchanged. The latter more easily facilitates collecting evidence for safety assurance processes but sacrifices optimisation of performance and adaptation to user needs gained through learning-implementation cycles. The challenge is how to balance potential benefits with the need to assure their safety. Governance and assurance processes are needed that can accommodate real-time or near-real-time machine learning. Such an approach is of great importance in healthcare and other fields of application. AI has stimulated an intense process of learning as this new technology embeds in application contexts. The process is not only about the application of AI in the real world but also about the institutional arrangements for its safe and dependable deployment, including regulatory experimentation involving new market pathways, monitoring and surveillance, and sandbox schemes. We review the key themes, challenges and potential solutions raised at two stakeholder workshops and highlight recent attempts to adapt the laws for AI-enabled medical devices (AIeMD) with a special focus on the regulatory proposals in the UK and internationally. The UK regulatory trajectory shows signs of alignment with the US thinking, and yet the European Union model is still the most closely aligned framework.

Lightweight, porous, stretchable nanocomposite foams with sandwich-like and bimodal cell structure by supercritical fluids-assisted processing for flexible strain sensor

Developing strain sensors with wide detection range and high sensitivity at a low conductive nanofillers content still faces challenges. Herein, thermoplastic polyurethane (TPU)/multi-walled carbon nanotubes (MWCNTs) nanocomposite foams with a multilayer alternating and bimodal cell structure is prepared by stacking hot pressing and supercritical carbon dioxide batch foaming process. Consequently, the synergistic effect of sandwich-like and bimodal cell structure endows the foam sensor of FTPU-C3-L10 T80P10 (TPU/3wt.%MWCNTs nanocomposite foams with ten layers alternating structure foamed at 80℃ and 10MPa) 0.34 vol.% MWCNTs loading, broad response range of 0~150%, high sensitivity with a gauge factor (GF) of 101, fast response speed of 180 ms, as well as cyclic reproducibility and durability of 1000 cycles. Furthermore, the fabricated foam sensor can effectively monitor basic human motion from tiny to large. This work provides a facile strategy for designing and producing strain sensors applied in various fields, including human motion detection, artificial intelligence devices, and medical diagnosis.

Self-sustained and self-wakeup wireless vibration sensors by electromagnetic-piezoelectric-triboelectric hybrid energy harvesting

Self-sustained wireless sensing nodes (WSN) with energy harvesting, low power consumption, and intelligent sensing are the key devices in artificial intelligence of things (AIoT) area. This paper designs a tri-hybrid generator with electromagnetic-piezoelectric-triboelectric units integrated into one vibration energy harvesting structure. The tri-hybrid generator has three functions with electromagnetic unit for power supply with 13.1 mW, two piezoelectric units as the accelerometer for amplitude and frequency sensing with broadband decoupling function, triboelectric unit for triggering the self-wakeup WSN. The tri-hybrid generator structure is simulated and optimized by theory and finite element modeling, and the performance is tested in a vibration platform. To achieve self-sustained WSN, this study designs the power management circuit with maximum power point tracking and undervoltage lock function, combining periodic wake-up with overload self-wakeup to decrease 94.2% WSN power consumption. Self-sustained WSN is realized in the laboratory and verified on the vehicle engine. Finally, the application of wireless vibration sensing is verified on the vehicle engine. This work has a wide range of applications in vibration scenarios and hopefully promotes the development of AIoT.

AI-powered medical devices for practical clinicians including the diagnosis of colorectal polyps

Background: The integration of medical devices with artificial intelligence (AI) software is rapidly advancing as technology progresses. AI machine learning can be used in commercial medical services to generate practical data; there is evidence that it can be integrated into newly developed devices. However, such devices must undergo approval, regulation, and supervision. The Food and Drug Administration approves regulations for numerous machine-learning medical devices and shares open lists with the public. In this article, we examine recent medical AI devices in different fields, including the diagnosis of colorectal polyps.Current Concepts: Currently, in the field of gastroenterology, there has been a significant amount of research aimed at enhancing adenoma detection rates using tools powered by AI, such as the EndoScreener and GI Genius. Various such devices have also been developed for other fields; examples include the 23andMe Personal Genome Service for DNA detection, Spectral MD’s DeepView platform for wound imaging in surgery, Gili Pro BioSensor for monitoring vital signs, DreaMed Advisor Pro for diabetes, Minuteful for urinary analysis, BrainScope TBI for cerebral diagnosis, Compumedics Sleep Monitoring System for sleep disorders, Idx-DR v2.3 for ophthalmology, and EarliPoint system for pediatrics.Discussion and Conclusion: By the time this article is published, it is likely that even more AI medical devices will have been approved and commercialized. The development of such devices should be strongly encouraged. Additionally, we anticipate greater involvement from practitioners in the development and validation of diverse medical AI devices in Korea.

Highly Stretchable and Conductive MXene‐Encapsulated Liquid Metal Hydrogels for Bioinspired Self‐Sensing Soft Actuators

AbstractAdvanced sensation and actuation abilities of various living organisms in nature have inspired researchers to design bioinspired self‐sensing soft actuators. However, the majority of conventional soft actuators primarily possess actuation capabilities while lacking a real‐time sensing signal feedback. Here, a promising strategy is reported to develop highly stretchable and conductive hydrogels for bioinspired self‐sensing soft actuators, which integrate actuation and strain‐sensing functions into a single materials system. The conductive hydrogels are designed and fabricated by in situ copolymerization of amino‐functionalized MXene‐encapsulated liquid metal nanodroplets (LM@A‐MXene) and poly(N‐isopropylacrylamide) hydrogels with controllable activated nanogels as nano‐cross‐linkers. The resulting hydrogel presents a compacted conducting network and highly porous microstructure, giving rise to robust integration of high conductivity, excellent strain sensitivity, broad stretchability, high stability, and fast response speed. Interestingly, the gradient network structure, formed by self‐precipitation of LM@A‐MXene, endows the hydrogel with shape‐programmable actuation, light‐driven remote control, and self‐sensing function. As a proof‐of‐concept application, the soft gripper based on the self‐sensing hydrogel actuators is developed, which can not only grasp, lift, and release objects, but also perceive every movement state by monitoring resistance changes. The proposed self‐sensing soft actuator can offer new insights for developing smart soft robotics and other artificial intelligent devices.

حكم تولي أجهزة الذكاء الاصطناعي كتابة خطبة الجمعة وإلقائها

This research talks about an expected future calamity, which is that artificial intelligence devices will undertake the work of the Friday preacher, such as writing and delivering the sermon. The aim of the research is to show the jurisprudential ruling on this calamity, and it was followed in it according to the inductive purposeful analytical approach, and the result of the research was that the jurisprudential ruling on this issue There are many options between artificial intelligence devices writing the sermon themselves and receiving it, and this is not permissible from a legal standpoint. Because the robot is obligated to perform the Friday prayers, if he himself preaches, but if the imam stumbles in writing a disciplined Friday sermon, it is permissible for him to use these devices to write the sermon, on the condition that he reviews it after writing. Because there is no clear evidence that prevents it from being written solely by devices, this research contributes greatly to the jurisprudence of calamities because it laid the foundation for starting to look into t This is the future calamity

Humor type and service context shape AI service recovery

While artificial intelligence (AI) service failure is inevitable in tourism and hospitality, scholarly attention to it is limited. This study investigated how the type of humor (self-deprecating or self-enhancing) that AI agents adopt interacted with the service context (hedonic-dominant or utilitarian-dominant) in influencing customers' intentions to continue using AI devices. Findings indicate that in hedonic-dominant service contexts, self-deprecating and self-enhancing humor increase continuous usage intention; in utilitarian-dominant service contexts, only self-deprecating humor boosts continuous usage intention. Results also reveal the mediating roles of positive emotion and inferred negative motives along with the moderating effect of anthropomorphism. This study enriches theories on AI service recovery and offers tourism firms suggestions on how to use humor to resolve AI service failures.

When Service Quality is Enhanced by Human–Artificial Intelligence Interaction: An Examination of Anthropomorphism, Responsiveness from the Perspectives of Employees and Customers

This article reports on two distinct studies conducted in the context of employees and customers, respectively. The aim of Study 1 is to investigate the influence of anthropomorphism and responsiveness of food delivery people using artificial intelligence (AI) devices on their psychological safety and AI empathy. This study also evaluated the mediating impact of psychological safety and AI empathy with relation to anthropomorphism and responsiveness on AI service quality. In addition, Study 2 examines the impact of perceptions of AI service quality on customer engagement and customer satisfaction. Furthermore, in Study 2, we tested the moderating influence of AI usability on the relationship between AI service quality and customer engagement and on the relationship between AI service quality and customer satisfaction. In Study 1, we collected data from 312 food delivery boys/girls who used AI-based applications to offer e-food restaurant services. This study used a cross-sectional research design. We expand the scope of Study 1 by collecting data from 363 customers of the companies surveyed in Study 1 from eastern and southern parts of China. Study 2 used a time-delayed approach and collected data in two waves three months apart. The overall results of Study 1 and Study 2 support the proposed hypotheses. The results showed the direct and indirect relationship between independent variables (anthropomorphism and responsiveness) and service quality, customer engagement and customer satisfaction. Furthermore, the results indicated a significant role of mediators (psychological safety and AI empathy) in Study 1 and moderators (AI usability) in Study 2. This article provided valuable insights for practitioners and researchers concerned with the use and application of AI in deal with the service sector.

Use of an elastic-scattering spectroscopy and artificial intelligence device in the assessment of lesions suggestive of skin cancer: A comparative effectiveness study

Skin cancer is the most common form of cancer worldwide. As artificial intelligence (AI) expands its scope within dermatology, leveraging technology may aid skin cancer detection. To assess the safety and effectiveness of an elastic-scattering spectroscopy (ESS) device in evaluating lesions suggestive of skin cancer. This prospective, multicenter clinical validation study was conducted at 4 US investigational sites. Patients with skin lesions suggestive of melanoma and nonmelanoma skin cancers were clinically assessed by expert dermatologists and evaluated by a device using AI algorithms comparing current ESS lesion readings with training data sets. Statistical analyses included sensitivity, specificity, AUROC, negative predictive value (NPV), and positive predictive value (PPV). Overall device sensitivity was 97.04%, with subgroup sensitivity of 96.67% for melanoma, 97.22% for basal cell carcinoma, and 97.01% for squamous cell carcinoma. No statistically significant difference was found between the device and dermatologist performance (P=.8203). Overall specificity of the device was 26.22%. Overall NPV of the device was 89.58% and PPV was 57.54%. The ESS device demonstrated high sensitivity in detecting skin cancer. Use of this device may assist primary care clinicians in assessing suspicious lesions, potentially reducing skin cancer morbidity and mortality through expedited and enhanced detection and intervention.

Potential Applications and Impact of ChatGPT in Radiology

Radiology has always gone hand-in-hand with technology and artificial intelligence (AI) is not new to the field. While various AI devices and algorithms have already been integrated in the daily clinical practice of radiology, with applications ranging from scheduling patient appointments to detecting and diagnosing certain clinical conditions on imaging, the use of natural language processingand large language modelbased software have been in discussion for a long time.Algorithms like ChatGPT can help in improving patient outcomes, increasing the efficiency of radiology interpretation, and aiding in the overall workflow of radiologists and here we discuss some of its potential applications.

S299 Implementation of Artificial Intelligence Device for Polyp Detection During Colonoscopy at an Academic County Hospital System

S299 Implementation of Artificial Intelligence Device for Polyp Detection During Colonoscopy at an Academic County Hospital System

Wearable Devices and Explainable Unsupervised Learning for COVID-19 Detection and Monitoring.

Despite the declining COVID-19 cases, global healthcare systems still face significant challenges due to ongoing infections, especially among fully vaccinated individuals, including adolescents and young adults (AYA). To tackle this issue, cost-effective alternatives utilizing technologies like Artificial Intelligence (AI) and wearable devices have emerged for disease screening, diagnosis, and monitoring. However, many AI solutions in this context heavily rely on supervised learning techniques, which pose challenges such as human labeling reliability and time-consuming data annotation. In this study, we propose an innovative unsupervised framework that leverages smartwatch data to detect and monitor COVID-19 infections. We utilize longitudinal data, including heart rate (HR), heart rate variability (HRV), and physical activity measured via step count, collected through the continuous monitoring of volunteers. Our goal is to offer effective and affordable solutions for COVID-19 detection and monitoring. Our unsupervised framework employs interpretable clusters of normal and abnormal measures, facilitating disease progression detection. Additionally, we enhance result interpretation by leveraging the language model Davinci GPT-3 to gain deeper insights into the underlying data patterns and relationships. Our results demonstrate the effectiveness of unsupervised learning, achieving a Silhouette score of 0.55. Furthermore, validation using supervised learning techniques yields high accuracy (0.884 ± 0.005), precision (0.80 ± 0.112), and recall (0.817 ± 0.037). These promising findings indicate the potential of unsupervised techniques for identifying inflammatory markers, contributing to the development of efficient and reliable COVID-19 detection and monitoring methods. Our study shows the capabilities of AI and wearables, reflecting the pursuit of low-cost, accessible solutions for addressing health challenges related to inflammatory diseases, thereby opening new avenues for scalable and widely applicable health monitoring solutions.

Validation of a real-time biliopancreatic endoscopic ultrasonography analytical device in China: a prospective, single-centre, randomised, controlled trial

Endoscopic ultrasonography (EUS) is a key procedure for the diagnosis of biliopancreatic diseases. However, the performance among EUS endoscopists varies greatly and leads to blind spots during the operation, which can impair the health outcomes of patients. We previously developed an artificial intelligence (AI) device that accurately identified EUS standard stations and significantly reduced the difficulty of ultrasonography image interpretation. In this study, we updated the device (named EUS-IREAD) and validated its performance in improving the quality of EUS procedures. In this single-centre, randomised, controlled trial, we updated EUS-IREAD so it consisted of five learning models to identify eight EUS stations and 24 anatomical structures. The trial was done at the Renmin Hospital of Wuhan University (Wuhan, China) and included patients aged 18 years or older with suspected biliopancreatic (pancreas and biliopancreatic duct) lesions due to clinical symptoms, radiological findings, or laboratory findings, and with a high risk of pancreatic cancer. Patients were randomly assigned (1:1) by a dedicated research assistant using a computer-generated random number series (with a block size of four) to undergo the EUS procedure with or without the assistance of EUS-IREAD. Endoscopists in the EUS-IREAD-assisted group were required to observe all standard stations and anatomical structures according to the prompts by the AI device. Data collectors, the independent data anaylsis team, and patients were masked to group allocation. The primary outcome was the missed scanning rate of standard stations between the two groups, which was assessed in patients who underwent EUS procedure in accordance with the assigned intervention (per protocol). This trial is registered with ClinicalTrials.gov, NCT05457101. Between July 9, 2022, and Feb 28, 2023, 290 patients (mean age 55·93 years [SD 14·06], 152 [52%] male, and 138 [48%] female) were randomly assigned and analysed, including 144 in the EUS-IREAD-assisted group and 146 in the control group. The EUS-IREAD-assisted group had a lower missed scanning rate of stations than the control group (4·5% [SD 0·8] vs 14·3% [1·0], -9·8% [95% CI -12·2 to -7·5]; odds ratio 3·6 [95% Cl 2·6 to 4·9]; p<0·0001). No significant adverse event was found during the study. Our study confirms the capability of EUS-IREAD to monitor the blind spots and reduce the missed rate of stations and structures during EUS procedures. The EUS-IREAD has the potential to play an essential part in EUS quality control. Innovation Team Project of Health Commission of Hubei Province and College-enterprise Deepening Reform Project of Wuhan University.

Retracted: The Optimization of Civic Education with the Assistance of Artificial Intelligence Devices

Retracted: The Optimization of Civic Education with the Assistance of Artificial Intelligence Devices

Asymmetric and Flexible Ag-MXene/ANFs Composite Papers for Electromagnetic Shielding and Thermal Management.

Lightweight, flexible, and electrically conductive thin films with high electromagnetic interference (EMI) shielding effectiveness and excellent thermal management capability are ideal for portable and flexible electronic devices. Herein, the asymmetric and multilayered structure Ag-MXene/ANFs composite papers (AMAGM) were fabricated based on Ag-MXene hybrids and aramid nanofibers (ANFs) via a self-reduction and alternating vacuum-assisted filtration process. The resultant AMAGM composite papers exhibit high electrical conductivity of 248,120 S m-1, excellent mechanical properties with tensile strength of 124.21 MPa and fracture strain of 4.98%, superior EMI shielding effectiveness (62 dB), ultra-high EMI SE/t (11,923 dB cm2 g-1) and outstanding EMI SE reliability as high as 96.1% even after 5000 cycles of bending deformation benefiting from the unique structure and the 3D network at a thickness of 34 μm. Asymmetric structures play an important role in regulating reflection and absorption of electromagnetic waves. In addition, the multifunctional nanocomposite papers reveal outstanding thermal management performances such as ultrafast thermal response, high heating temperatures at low operation voltage, and high heating stability. The results indicate that the AMAGM composite papers have excellent potential for high-integration electromagnetic shielding, wearable electronics, artificial intelligence, and high-performance heating devices.

How to Safely Integrate Large Language Models Into Health Care

This JAMA Forum discusses categories of artificial intelligence devices such as clinical decision support tools and large language models that are increasing being used in health care and the improvements needed to ensure the accuracy and rigor of these tools for patient use.

Digital Democracy Political Participation Through Technology in the Modern Era

As a country that upholds democracy, Indonesia uses democracy in carrying out political participation. Along with technological developments, the integration of this technology appears in the way of politics. This research aims to explore the impact of digital technology on political participation in the modern era. In its implementation, this research was carried out using a descriptive qualitative approach. Using relevant data from previous research through literature studies, this research will produce a deeper understanding of the role of technology in shaping the way people engage in politics. The results of this research found that there is a lot of potential in digital democracy technological innovation. These various potentials such as artificial intelligence, blockchain, and mobile devices have the potential to increase the efficiency and quality of political participation. However, in its implementation, there are still several obstacles, such as regulations, ethics, and unequal access to technology. Through the right steps, a more inclusive, transparent, and democratic digital democracy in the digital era can be achieved.

Ultrastretchable and highly conductive hydrogels based on Fe3+- lignin nanoparticles for subzero wearable strain sensor

Conductive hydrogels have attracted considerable interest for potential applications in soft robotics, electronic skin and human monitoring. However, insufficient mechanical characteristics, low adhesion and unsatisfactory electrical conductivity severely restrict future application possibilities of hydrogels. Herein, lignin nanoparticles (LNPs)-Fe3+-ammonium persulfate (APS) catalytic system was introduced to assemble Poly(2-hydroxyethyl methacrylate)/LNPs/Ca2+ (PHEMA/LNPs/Ca) hydrogels. Due to the abundant metal coordination and hydrogen bonds, the composite hydrogel displayed ultrahigh stretchable capacity (3769 %), adhesion properties (248 kPa for skin) and self-healing performance. Importantly, hydrogel sensors possess with high durability, strain sensitivity (GF = 8.75), fast response time and freeze resistance (−20 °C) that could be employed to monitor motion signals in low-temperature regime. Therefore, the LNPs-Fe3+ catalytic system has great potential in preparing hydrogel for various applications such as human-computer interaction, artificial intelligence, personal healthcare and subzero wearable devices. At the same time, incorporation of natural macromolecules into polymer hydrogels is tremendous research significance for investigating high-value utilization of lignin.