RGB Medical Devices (Spain)

Knowledge-Centric Systems Engineering is an industrial approach to systems and software engineering that advocates the development and use of knowledge bases that represent system domains. This approach can also exploit artificial intelligence techniques. These means can be used for early V&V (verification and validation) activities, e.g., for system artefact quality analysis and traceability management. This paper presents advances made in these activities with the SES Engineering Studio industrial tool and its underlying methods to meet further early-V& V needs in practice. The methods and the tool have been improved to better address model quality analysis, traceability project management, trace specification, and compliance with standards. For validation, we have initially applied the new features on a medical device. This has also allowed us to study the benefits of the features. The results show that the advances made can lead to wider system artefact analyses, more precise traceability management, better system artefacts, lower V & V effort, and lower issue resolution costs. All in all, the paper presents specific examples of how early- V & V industrial practices and tools can be improved.

One of the most powerful techniques to diagnose cardiovascular diseases is to analyze the electrical activity of the heart acquired on the skin surface, the electrocardiogram (ECG). To increase the diagnostic sensitivity, the ECG might need to be acquired using a reduced, portable system, as symptoms may occur during patient's normal daily life. There are techniques proposed to reduce the number of leads and estimating the views that would have been obtained with a standard ECG location, reconstructing the complete standard 12-lead system, the most accepted system for diagnosis by cardiologists. Patients may have an implantable cardiac device such as a pacemaker or implantable cardioverter defibrillator (ICD), which sporadically introduce artifacts and artificial signals into the system, that may severely affect the ECG reconstruction. This study analyzes how these pulses affect the quality of the reconstruction and whether it is possible to deal with them to obtain a reliable reconstruction. To solve the problem, a masking of the pulses is proposed, so that the algorithm ignores these parts of the ECG and provides reliable reconstruction results for the rest of the records. The good performance of this strategy allows to generate reliable 12-Lead records from a reduced number of electrodes with the method previously proposed by the authors in the presence of pacemaker and ICD activity.

The pace of population ageing is increasing and is currently becoming one of the challenges our society faces. The introduction of Cyber-Physical Systems (CPS) has fostered the development of e-Health solutions that ease the associated economic and social burden. In this work, a CPS-based solution is presented to partially tackle the problem: a Deep Multimodal Habit Tracking system. The aim is to monitor daily life activities to alert in case of life-threatening situations improving their autonomy and supporting healthy lifestyles while living alone at home. Our approach combines video and heart rate cues to accurately identify indoor actions, running the processing locally in embedded edge nodes. Local processing provides inherent protection of data privacy since no image or vital signs are transmitted to the network, and reduces data bandwidth usage. Our solution achieves an accuracy of more than 80% in average, reaching up to a 95% for specific subjects after adapting the system. Adding heart-rate information improves F1-score by 2.4%. Additionally, the precision and recall for critical actions such as falls reaches up to 93.75%. Critical action detection is crucial due to their dramatic consequences, it helps to reduce false alarms, leading to building trust in the system and reducing economic cost. Also, the model is optimized and integrated in a Nvidia Jetson Nano embedded device, reaching real-time performance below 3.75 Watts. Finally, a dataset specifically designed for indoor action recognition using synchronized video and heart rate pulses has been collected.

Model-informed drug development (MIDD) approaches receive wide regulatory acceptance in the European Medicines Agency (EMA) to support new drug development. For generic drugs, the European regulators have not reached a common position on how to use these methods. This commentary expands on the existing EMA regulatory framework for bioequivalence and physiological based pharmacokinetic (PBPK) modeling to propose conditions where mechanistic models could support or potentially waive clinical bioequivalence (BE)/bioavailability (BA) studies.

This paper presents a compensation scheme for an externally compensated low drop-out (LDO) regulator, which has to provide fast high-load currents with low-noise and high-PSRR. The approach overcomes the challenge of the presence of large parasitics (ESR and ESL) when the external capacitor is placed far away from the chip, which is becoming more common in many space constrained electronic modules. The proposed scheme has been validated in a 5V LDO designed in TSMC's 40nm DMOS technology. It delivers 200ns wide 200mA current pulses while maintaining low noise and high PSRR (40dB) up to 1MHz. The LDO is stabilized with an external 2.2 μF capacitor and can accommodate large bonding parasitics (up to 4nH).

The increasing complexity of the medical regulatory environment and the inherent complexity of medical devices, especially due to the increased use of connected devices and embedded control software, impose adoption of new methods and tools for the system design, safety and security analyses. In this paper, we propose a method and an associated toolchain to couple model-based system engineering and safety/security analyses at the design phase of medical devices. The method is compliant with ANSI/AAMI/ISO TIR57 safety and security guidance, and compatible with INCOSE Biomedical-Healthcare Model-Based Systems Engineering works. The toolchain is based on a system architecture modelling tool and supports medical device domain specific reference architecture, as well as tools for safety and security risk analyses. The proposed method and toolchain are illustrated by considering a RGB’s TOF-CUFF monitor device analyzed in the scope of the AQUAS project as a medical device use case.

Enhanced user interface environments is a hot topic in industry. Multi-touch technologies based on projected capacitance are preferred in the consumer market as they provide a more friendly interaction with the user. Also, these technologies allow the tracking of an infinite number of fingers on the touch screen. However, resistive technologies cover applications gaps such as medical, automotive, or environments where wearing gloves is required. Additionally, resistive panels allow the use of basic stylus or pens which is essential for character recognition in Asian languages. Traditionally, resistive technologies have been used to detect the position of a single touch on the screen. The paper will describe how to detect the most common two finger gestures (zooms, pinches, and rotations) using inexpensive 4-wire resistive touch screens and how to detect the true location of dual touch with some modeling and calibration of the screen.

The Ubiquitous Tele-monitoring Kit (UTK) is aimed at helping the clinician in acquiring, managing and normalizing information coming from the patients at home and storing the data in a distributed system. This approach aims to reduce costs in the healthcare system and alleviate the inherent problems to chronic patients who usually may visit the doctors. The proposed system closes the tele-monitoring loop; wearable and ergonomic sensors integrated in the textile, automatic detection and storage of the information coming from the sensors in a common platform (XNAT) and processing and visualization of the retrieved physiological signals presenting the data treated to the clinician to optimize the continuum of care and the decision-making.