Device Software Research Articles

PHSOR07 Presentation Time: 9:30 AM: In-House Developed Medical Device Software BiCycle for Automated BT Treatment Planning, Compliant with the European Medical Device Regulation (MDR)

PHSOR07 Presentation Time: 9:30 AM: In-House Developed Medical Device Software BiCycle for Automated BT Treatment Planning, Compliant with the European Medical Device Regulation (MDR)

Engineering and Technological Advancements in Repetitive Transcranial Magnetic Stimulation (rTMS): A Five-Year Review

In the past five years, repetitive transcranial magnetic stimulation (rTMS) has evolved significantly, driven by advancements in device design, treatment protocols, software integration, and brain-computer interfaces (BCIs). This review evaluates how these innovations enhance the safety, efficacy, and accessibility of rTMS while identifying key challenges such as protocol standardization and ethical considerations. A structured review of peer-reviewed studies from 2019 to 2024 focused on technological and clinical advancements in rTMS, including AI-driven personalized treatments, portable devices, and integrated BCIs. AI algorithms have optimized patient-specific protocols, while portable devices have expanded access. Enhanced coil designs and BCI integration offer more precise and adaptive neuromodulation. However, challenges remain in standardizing protocols, addressing device complexity, and ensuring equitable access. While recent innovations improve rTMS’s clinical utility, gaps in long-term efficacy and ethical concerns persist. Future research must prioritize standardization, accessibility, and robust ethical frameworks to ensure rTMS’s sustainable impact.

Artificial intelligence-supported clear aligner orthodontic technology

With the advancement of digital healthcare and artificial intelligence (AI) technologies, the full automation of clear aligner orthodontic technology has become feasible. Significant research findings and commercial applications have emerged in areas such as intelligent diagnosis of multimodal orthodontic data, orthodontic treatment decision-making, automated generation of digital treatment plans, and remote intelligent monitoring. However, in the development and application of AI software, it is imperative to address issues related to clinical risks, target populations, and compliance with medical device software regulations. This article analyzes and summarizes the applications and challenges of AI in clear aligner orthodontic diagnosis, treatment, and production processes. Furthermore, it explores potential future trends in this field, providing valuable insights for clinical reference.

Double edged tech: navigating the public health and legal challenges of digital twin technology

Abstract This research addresses the legal challenges posed by the implementation of digital twin technology in public health. Digital twins are advanced computational models which aim to replicate human organ functions and biological processes. Their goal is to enable the simulation of the entire human body and to personalize the outputs with individual patient’s health data. Digital twin technology promises to bridge gap between personalized medicine and precision public health. This research is based on a comprehensive review of the current European and Swiss legal frameworks for medical devices and data protection that apply to digital twin technology. Within these frameworks, digital twins are in a grey area, as they are only considered as medical device software when applied to individuals. They also incorporate artificial intelligence, machine learning, and data analytics, which are already a source of legal concern in a healthcare setting, but their effective use in public health raises additional issues. Preliminary findings suggest significant shortcomings in the legal frameworks regarding data privacy, and the potential for increased surveillance by health insurance systems, which could lead to human rights violations. The public health application of digital twins would require global data analysis of sensitive personal information, raising further questions about the secure storage, transmission, and processing of this data. The study concludes that current legal frameworks must be future proofed to manage the complexities introduced by digital twins in public health. In particular, it suggests that regulatory oversight of medical devices needs to be significantly improved in order to safely harness the potential of digital twin technologies for public health. Finally, the new European Union health data space and the forthcoming EU AI act will also play important roles in the implementation of digital twin technologies. Key messages • Applying digital twin technology in public health faces considerable challenges, particularly the issues around data privacy, potential discrimination, and increased surveillance. • We need to adapt and strengthen existing legal frameworks to effectively manage the complexities introduced by digital twins, ensuring that these technologies can be safely used for public health.

From Code to Care: The Impact of Software Engineering and QA on Healthcare Delivery Systems

The rapid digitalization of healthcare has led to an unprecedented reliance on software systems to improve patient care, streamline operations, and ensure regulatory compliance. This article presents a comprehensive analysis of the critical role that software engineering and quality assurance (QA) play in three key areas of modern healthcare: Electronic Health Records (EHRs), telemedicine platforms, and medical device software. Through an examination of current practices, challenges, and case studies, we demonstrate how robust software engineering methodologies and rigorous QA processes contribute to the development of reliable, secure, and efficient healthcare applications. Our findings highlight the importance of data integrity, interoperability, user experience, and regulatory compliance in healthcare software development. Furthermore, we explore emerging trends such as artificial intelligence, blockchain, and the Internet of Medical Things (IoMT), discussing their implications for future software engineering and QA practices in healthcare. This article provides valuable insights for healthcare organizations, software developers, and policymakers, offering recommendations to enhance the quality and safety of software-driven healthcare solutions.

Research on Medical Device Software Based on Artificial Intelligence and Machine Learning Technologies

With the rapid development of Artificial Intelligence (AI) and Machine Learning (ML) technologies, new opportunities for innovation and application in medical device software have emerged. This paper explores the current research on medical device software based on AI and ML, analyzing the practical applications and outcomes of these technologies in the medical field. First, the basic concepts of AI and ML and their significance in medical devices are introduced. Then, an in-depth analysis of the functional requirements of medical device software, user experience, and relevant regulations is provided. Next, the paper discusses the specific applications of AI and ML in data processing, model training, and software implementation, showcasing their practical effects through case studies. Finally, the paper summarizes the current technical challenges and future opportunities, hoping to provide insights for further development in the medical device industry.

Integrating toyota production system for sustainability and competitive advantage in medical device software design

This research explores the integration of the Toyota Production System (TPS) and sustainability into the software design and development processes of a medium-sized medical device company dealing with resource constraints and evolving customer requirements. Through an analysis of TPS principles and how they relate to manufacturing and software development challenges, the research seeks to strengthen efficiency and competitiveness. It provides an adaptable implementation plan that fosters a competitive strategy and promotes sustainability through efficient software practices. The paper presents a roadmap for systematically integrating TPS and sustainability in alignment with international best practices, positioning the company to thrive in the expanding medical software market. This framework addresses immediate operational issues while laying the groundwork for long-term success and compliance with industry standards.

A - 91 Nocturnal Motor Activity and Wake after Sleep Onset and Neuropsychological Health in Veterans with Gulf War Illness

Abstract Objective To examine the association between actigraphy-based sleep parameters and neuropsychological health in Veterans with Gulf War Illness (GWI). Methods Objective sleep data was obtained from 85 GW Veterans (Mage = 54.2, 79% Male) using an actigraphy monitor (Phillips Respironics Actiwatch-2) worn for 24 hours/day for seven consecutive days. Actigraphy data was manually scored to define time in bed (TIB), and total sleep time (TST), wake after sleep onset (WASO), number of awakenings (NWAK), and motor activity counts (MAC) during sleep were derived using the device software. Participants completed a battery of questionnaires: Patient Health Questionnaire (PHQ-9), Posttraumatic Symptom Checklist (PCL-5), and Pittsburgh Sleep Quality Index (PSQI). Cognitive function was assessed using the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS). Correlation analysis was conducted to discover associations between sleep parameters, self-reported measures, and cognitive function. Results MAC was positively correlated with elevated scores on PSQI (r = 0.35, p < 0.01), PHQ-9 (r = 0.26, p < 0.05), and PCL-5 (r = 0.26, p < 0.05), and negatively correlated with RBANS Total Index score (r = −0.27, p < 0.05). WASO was also positively correlated with PSQI scores (r = 0.29, p < 0.01). TIB and TST were positively correlated with age (r = 0.25, r = 0.28; all p < 0.05). Conclusion Objective parameters of disrupted sleep – nocturnal MAC and WASO – were associated with greater self-reported sleep disturbance. MAC was additionally correlated with increased self-reported symptoms of depression and PTSD, as well as lower performance on a measure of objective cognitive function. This study identifies aspects of sleep disruption as potential sleep intervention targets related to both mood and cognitive symptoms.

Digitalization of Analysis of a Concrete Block Layer Using Machine Learning as a Sustainable Approach

The concrete block pavement (CBP) system has a surface layer consisting of concrete block pavers and joint sand over a bedding sand layer. The non-homogeneous nature of the surface course of CBP, along with different laying patterns and shapes of block pavers, makes the analysis of CBP cumbersome. In this study, the surface course of CBP was modeled based on the slab action of the block pavers and joint sand, which are connected together in full contact. Four different laying patterns, including herringbone, stretcher, parquet, and square, were modeled using a finite element model. The elastic moduli of the block pavers varied from 2500 MPa to 45,000 MPa, with thicknesses ranging from 60 mm to 120 mm. As a result, modeling of CBP based on slab action can be considered a realistic strategy. In addition, a dataset was created based on quantitative inputs, e.g., elastic modulus and thickness of the block pavers, and qualitative input, i.e., block laying patterns. The approaches of machine learning adopted were support vector regression, Gaussian process regression, single-layer and deep artificial neural networks, and least squares boosting to implement prediction approach based on input and output. The analyses of statistical accuracy of all five machine learning methods showed high accuracy; however, the Gaussian process and deep artificial neural network methods resulted in the most accurate outputs and are recommended for further studies. Based on the machine learning models, digitalization is achieved through the development of simple, user-friendly software for electronic devices in order to perform a preliminary analysis of different laying patterns of CBP. Such a platform may result in less laboratory work and boosts the level of sustainability in concrete block pavement technology.

Evaluation of high altitude training camps with heart rate recovery and heart rate variability analysis: beneficial effect in elite swimmers.

The available evidence on the impact of altitude training on sports performance is inconclusive. Heart rate variability (HRV) and heart rate recovery (HRR) are among the most frequently used parameters in athletic performance analysis and monitoring. Our study aims to investigate the effect of high altitude training on HRR and HRV, which are reliable predictors of athletic performance. Elite national swimmers were included in the study. Time domain and frequency domain analyzes were performed with the Polar Verity Sense device and Kubios HRV software. HRR were measured at one-minute intervals for the first 15 minutes after peak heart rate, and then recorded at the 20th, 25th and 30th minutes. A significant difference is observed from the beginning to the 11th minute. The P value at 1, 3, 5, 7 and 11 minutes is 0.001, 0.023, 0.032, 0.019 and 0.020, respectively. Similarly, a significant change was observed in delta HRR. Among the HRV parameters, RMSSD, SDNN, Poincaré SD1 and PNS are statistically significant. P values are 0.004, 0.018, 0.024 and 0.013 respectively. High altitude training program has a positive effect on HRV and CRV in elite swimmers. This condition is associated with increased cardiac parasympathetic activity. Time domain analyses have proven to be more beneficial for HRV. HRR and HRV are effective, reliable and inexpensive methods of performance monitoring of elite athletes.

A comprehensive engineering design analysis of Apple Watch as a smart wearable device

This paper presents a comprehensive engineering design analysis of the Apple Watch, a pioneering smart wearable device by Apple Inc. The analysis covers the device's hardware and software components, design principles, manufacturing processes, impact on user experience, and its influence on the wearable technology market. The Apple Watch integrates advanced technologies into a sleek and functional design, enhancing user interaction through its intuitive interface and robust health monitoring capabilities. By examining its engineering intricacies and market impact, this study highlights the Apple Watch's role in shaping the future of wearable technology.

Establishment and Evaluation of a Noninvasive Metabolism-Related Fatty Liver Screening and Dynamic Monitoring Model: Cross-Sectional Study.

Metabolically associated fatty liver disease (MAFLD) insidiously affects people's health, and many models have been proposed for the evaluation of liver fibrosis. However, there is still a lack of noninvasive and sensitive models to screen MAFLD in high-risk populations. The purpose of this study was to explore a new method for early screening of the public and establish a home-based tool for regular self-assessment and monitoring of MAFLD. In this cross-sectional study, there were 1758 eligible participants in the training set and 200 eligible participants in the testing set. Routine blood, blood biochemistry, and FibroScan tests were performed, and body composition was analyzed using a body composition instrument. Additionally, we recorded multiple factors including disease-related risk factors, the Forns index score, the hepatic steatosis index (HSI), the triglyceride glucose index, total body water (TBW), body fat mass (BFM), visceral fat area, waist-height ratio (WHtR), and basal metabolic rate. Binary logistic regression analysis was performed to explore the potential anthropometric indicators that have a predictive ability to screen for MAFLD. A new model, named the MAFLD Screening Index (MFSI), was established using binary logistic regression analysis, and BFM, WHtR, and TBW were included. A simple rating table, named the MAFLD Rating Table (MRT), was also established using these indicators. The performance of the HSI (area under the curve [AUC]=0.873, specificity=76.8%, sensitivity=81.4%), WHtR (AUC=0.866, specificity=79.8%, sensitivity=80.8%), and BFM (AUC=0.842, specificity=76.9%, sensitivity=76.2%) in discriminating between the MAFLD group and non-fatty liver group was evaluated (P<.001). The AUC of the combined model including WHtR, HSI, and BFM values was 0.900 (specificity=81.8%, sensitivity=85.6%; P<.001). The MFSI was established based on better performance at screening MAFLD patients in the training set (AUC=0.896, specificity=83.8%, sensitivity=82.1%) and was confirmed in the testing set (AUC=0.917, specificity=89.8%, sensitivity=84.4%; P<.001). The novel MFSI model was built using WHtR, BFM, and TBW to screen for early MAFLD. These body parameters can be easily obtained using a body fat scale at home, and the mobile device software can record specific values and perform calculations. MFSI had better performance than other models for early MAFLD screening. The new model showed strong power and stability and shows promise in the area of MAFLD detection and self-assessment. The MRT was a practical tool to assess disease alterations in real time.

On the Application of Artificial Intelligence/Machine Learning (AI/ML) in Late-Stage Clinical Development.

Whereas AI/ML methods were considered experimental tools in clinical development for some time, nowadays they are widely available. However, stakeholders in the health care industry still need to answer the question which role these methods can realistically play and what standards should be adhered to. Clinical research in late-stage clinical development has particular requirements in terms of robustness, transparency and traceability. These standards should also be adhered to when applying AI/ML methods. Currently there is some formal regulatory guidance available, but this is more directed at settings where a device or medical software is investigated. Here we focus on the application of AI/ML methods in late-stage clinical drug development, i.e. in a setting where currently less guidance is available. This is done via first summarizing available regulatory guidance and work done by regulatory statisticians followed by the presentation of an industry application where the influence of extensive sets of baseline characteristics on the treatment effect can be investigated by applying ML-methods in a standardized manner with intuitive graphical displays leveraging explainable AI methods. The paper aims at stimulating discussions on the role such analyses can play in general rather than advocating for a particular AI/ML-method or indication where such methods could be meaningful.

Comparing methods for detection of gastro-oesophageal reflux in anaesthetized dogs

ObjectiveTo compare the sensitivity and specificity of pH with multichannel intraluminal impedance (pH-MII), pH-metry (pH) alone and MII alone to direct observation of GOR by endoscopy in anaesthetized dogs. Study designA prospective comparative trial in a live canine model. AnimalsA group of 35 (22 females, 13 males) dogs of various breeds. The mean (range) body weight and age were 31.9 (14–40) kg and 5.6 (0.75–12) years, respectively. MethodsAll dogs were premedicated with medetomidine and morphine, anaesthesia was induced with propofol and maintained on isoflurane in oxygen. A monitoring assembly consisting of an endoscopy camera, endotracheal tube and a disposable flexible pH-MII catheter was used to measure oesophageal pH, MII and directly visualize reflux. Visual reflux score was (0–3) and pH was recorded on a data capture sheet. Reflux was considered to have occurred whenever oesophageal pH was < 4.0 or > 7.5, device software analysing MII data detected fluid or a visual reflux score of 2 or 3 were assigned. Receiver operator curves (ROC) analysis was used to determine sensitivity and specificity for each monitoring method to detect GOR. ResultsEndoscopy identified GOR in 20 dogs (57%), pH-MII in 19 dogs (54%), pH alone in 13 dogs (37%) and MII alone in 12 dogs (24%). ROC analysis showed fair accuracy for pH-MII and pH alone, whereas MII demonstrated low accuracy. Conclusions and clinical relevanceIn conclusion, pH-MII is a reliable method for detecting GOR and emerges as a promising tool for future research. Endoscopy is reliable and provides the ability to subjectively quantify the volume of reflux; however, it lacks the ability to discern the pH of refluxate. pH alone misses reflux events with intermediate pH (4.1–7.4). Incorporation of impedance addresses some of the limitations associated with pH alone and enhances diagnostic accuracy.

A novel energy harvesting technology from the movements of air masses

The displacement of air masses caused by the movement of objects or vehicles is often characterized by considerable energy content, which, with appropriate technologies, can be partially recovered. In this sense, numerous scientific works consider rail transport as a possible context for application. However, the literature in the sector highlights how using existing wind technologies in these areas involves many difficulties, mainly related to the turbulent and impulsive nature of the airflows generated. This work presents the architecture and general aspects of an innovative technology for obtaining electrical energy from variable and impulsive airflows, such as those due to the rapid transit of railway trains in tunnels, without precluding its use in other similar fields. The innovative aspect mainly concerns the independent control of two distinct typologies of bladed elements, which can also have translational movement and drag-based and lift-based aerodynamic behavior to improve the adaptability of the embodiment to the site’s fluid dynamic and geometric characteristics. Furthermore, the structural simplification of the apparatus, shifting some of the technological complexity to the control systems, brings further advantages in terms of construction cost, robustness, maintenance, reuse, and transferability to different contexts. Of course, the counterpart of these benefits lies in the software and hardware of the control devices. Analytical models to determine the non-dimensional performance coefficients of the two basic types have been reported as has the architectural model of the control system. The technology shown in this work is protected by an EP and US Patent.

The Target Detection of Wear Particles in Ferrographic Images Based on the Improved YOLOv8

An enhanced YOLOv8 algorithm is proposed in the following paper to address challenging issues encountered in ferrographic image target detection, such as the identification of complex-shaped wear particles, overlapping and intersecting wear particles, and small and edge-wear particles. This aim is achieved by integrating the main body network with the improved Deformable Convolutional Network v3 to enhance feature extraction capabilities. Additionally, the Dysample method is employed to optimize the upsampling technique in the neck network, resulting in a clearer fused feature image and improved precision for detecting small and edge-wear particles. In the head network, parameter sharing simplifies the detection head while enhancing convergence speed and precision through improvements made to the loss function. The experimental results of the present study demonstrate that compared to the original algorithm, this enhanced approach achieves an average precision improvement of 5.6% without compromising the detection speed (111.6FPS), therefore providing valuable support for online monitoring device software foundations.

Digital endpoints in clinical trials: emerging themes from a multi-stakeholder Knowledge Exchange event

BackgroundDigital technologies, such as wearable devices and smartphone applications (apps), can enable the decentralisation of clinical trials by measuring endpoints in people’s chosen locations rather than in traditional clinical settings. Digital endpoints can allow high-frequency and sensitive measurements of health outcomes compared to visit-based endpoints which provide an episodic snapshot of a person’s health. However, there are underexplored challenges in this emerging space that require interdisciplinary and cross-sector collaboration. A multi-stakeholder Knowledge Exchange event was organised to facilitate conversations across silos within this research ecosystem.MethodsA survey was sent to an initial list of stakeholders to identify potential discussion topics. Additional stakeholders were identified through iterative discussions on perspectives that needed representation. Co-design meetings with attendees were held to discuss the scope, format and ethos of the event. The event itself featured a cross-disciplinary selection of talks, a panel discussion, small-group discussions facilitated via a rolling seating plan and audience participation via Slido. A transcript was generated from the day, which, together with the output from Slido, provided a record of the day’s discussions. Finally, meetings were held following the event to identify the key challenges for digital endpoints which emerged and reflections and recommendations for dissemination.ResultsSeveral challenges for digital endpoints were identified in the following areas: patient adherence and acceptability; algorithms and software for devices; design, analysis and conduct of clinical trials with digital endpoints; the environmental impact of digital endpoints; and the need for ongoing ethical support. Learnings taken for next generation events include the need to include additional stakeholder perspectives, such as those of funders and regulators, and the need for additional resources and facilitation to allow patient and public contributors to engage meaningfully during the event.ConclusionsThe event emphasised the importance of consortium building and highlighted the critical role that collaborative, multi-disciplinary, and cross-sector efforts play in driving innovation in research design and strategic partnership building moving forward. This necessitates enhanced recognition by funders to support multi-stakeholder projects with patient involvement, standardised terminology, and the utilisation of open-source software.

Connected to the cloud at time of death: a case report

BackgroundOur case report provides the first clinical evaluation of autopsy practices for a patient death that occurs on the cloud. We question how autopsy practices may require adaptation for a death that presents via the ‘Internet of Things’, examining how existing guidelines capture data related to death which is no longer confined to the patient's body.Case presentationThe patient was a British man in his 50s, who came to the attention of the medical team via an alert on the cloud-based platform that monitored his implanted cardioverter defibrillator (ICD). The patient had a background of congenital heart disease, with previous ventricular fibrillation cardiac arrest, for which the ICD had been implanted two years earlier. Retrospective analysis of the cloud data demonstrated a gradually decreasing nocturnal heart rate over the previous three months, falling to a final transmission of 24 beats per minute (bpm). In the patient post-mortem the ICD was treated as medical waste, structural tissue changes precluded the effective evaluation of device hardware, potential issues related to device software were not investigated and the cause of death was assigned to underlying heart failure. The documentation from the attending law enforcement officials did not consider possible digital causes of harm and relevant technology was not collected from the scene of death.ConclusionThrough this patient case we explore novel challenges associated with digital deaths including; (1) device hardware issues (difficult extraction processes, impact of pathological tissue changes), (2) software and data limitations (impact of negative body temperatures and mortuary radio-imaging on devices, lack of retrospective cloud data analysis), (3) guideline limitations (missing digital components in autopsy instruction and death certification), and (4) changes to clinical management (emotional impact of communicating deaths occurring over the internet to members of family). We consider the implications of our findings for public health services, the security and intelligence community, and patients and their families. In sharing this report we seek to raise awareness of digital medical cases, to draw attention to how the nature of dying is changing through technology, and to motivate the development of digitally appropriate clinical practice.

Analysis of reject pinhole hardfacing process for stellite alloy metal motorcycle engine valves

If businesses wish to compete in the industrial world, they must produce quality and process results. No matter how big or little, some goods will always fail to generate or be rejected in a production process. In this case, companies in the automobile sector have noticed an increase in the number of pinholes that have been returned during the past three months. The company established a maximum reject rate of 0.9% each month based on the rejected data; from May to July, the average reject rate was 0.23%. Finding the factors causing the surge in pinhole rejects that occurred between May and July is the aim of this investigation. The analysis showed that the increase in pinhole rejects was caused by a variety of variables, including machine, process, and human factors. Further examination disclosed alterations to the device's configuration and software, along with the operator's persistent incapacity to comprehend the process. As operations become less efficient, repair components build up in the manufacturing line area. As a result, an improvement plan is needed, which is put into action by giving operator training and rearranging the machine and its software according to process requirements. Operators with a greater understanding of the process yield better results and higher productivity. As a result, operator confidence will rise along with performance. It was discovered that after developments in the field of human resource development, the number of rejections had dropped. Before the repair was finished, the average reject from May to July 2023 was 0.23%; following the repair, the average reject from August to October 2023 was 0.09%

Long-term explantation risk in patients with chronic pain treated with spinal cord or dorsal root ganglion stimulation

ObjectiveTo investigate long-term explantation risks and causes for the explantation of neuromodulation devices for the treatment of chronic pain from different manufacturers.MethodsThis retrospective analysis included patients implanted with a system...