Getinge (Germany)

Due to connectivity and automation trends, the medical device industry is experiencing increased demand for safety and security mechanisms. Anomaly detection has proven to be a valuable approach for ensuring safety and security in other industries, such as automotive or IT. Medical devices must operate across a wide range of values due to variations in patient anthropometric data, making anomaly detection based on a simple threshold for signal deviations impractical. For example, surgical robots directly contacting the patient's tissue require precise sensor data. However, since the deformation of the patient's body during interaction or movement is highly dependent on body mass, it is impossible to define a single threshold for implausible sensor data that applies to all patients. This also involves statistical methods, such as Z-score, that consider standard deviation. Even pure machine learning algorithms cannot be expected to provide the required accuracy simply due to the lack of available training data. This paper proposes using hybrid filters by combining dynamic system models based on expert knowledge and data-based models for anomaly detection in an operating room scenario. This approach can improve detection performance and explainability while reducing the computing resources needed on embedded devices, enabling a distributed approach to anomaly detection.

Abstract Background Mechanical ventilation, a crucial intervention for acute respiratory distress syndrome (ARDS), can lead to ventilator-induced lung injury (VILI). This study focuses on individualizing mechanical power (MP) in mechanically ventilated patients to minimize VILI and reduce ICU mortality. Methods A retrospective analysis was conducted using the Amsterdam University Medical Centers Database (AmsterdamUMCdb) data. The study included patients aged 18 and older who needed at least 48 hours of pressure-controlled mechanical ventilation. Patients who died or were extubated within 48 hours and those with inadequate data were excluded. Patients were categorized into hypoxemia groups based on their PaO2/FiO2 ratio. MP was calculated using a surrogate formula and normalized to ideal body weight (IBW). Statistical analyses and machine learning models, including logistic regression and random forest, were used to predict ICU mortality and establish safe upper limits for IBW-adjusted MP. Results Out of 23,106 admissions, 2,338 met the criteria. Nonsurvivors had a significantly higher time-weighted average MP (TWA-MP) than survivors. Safe upper limits for IBW-adjusted MP varied across hypoxemia groups. The XGBoost model showed the highest predictive accuracy for ICU mortality. An individualization method for mechanical ventilation settings, based on real-time physiological variables, demonstrated reduced predicted mortality in a subset of patients. Discussion Elevated TWA-MP is associated with increased ICU mortality, underscoring the need for personalized mechanical ventilation strategies. The study highlights the complexity of VILI and the multifactorial nature of ICU mortality. Further studies to define a safe upper limit for IBW-adjusted MP may help clinicians optimize mechanical ventilation settings and decrease the risk of VILI and mortality. Conclusions Despite the fact that the study's retrospective design and reliance on a single-center database may limit the generalizability of findings, this study offers valuable insights into the relationship between mechanical power and ICU mortality, emphasizing the need for individualized mechanical ventilation strategies. The findings suggest a potential for more personalized, data-driven approaches in managing mechanically ventilated patients, which could improve patient outcomes in critical care settings.

Since interoperability between medical devices is becoming mandatory in the Operating Room (OR), manufacturer-independent communication standards following a Plug and Play (PnP) approach are on the rise. Medical devices such as Operating Room tables (OR tables) are also reconfigurable and modular systems following a PnP approach. But enabling a networked system with multiple reconfigurable medical devices in a highly regulated and safety-critical area requires a continuous architecture with clear semantics. Thus, we propose an ontology-based service composition in a Service-Oriented architecture (SOA) for modular and interoperable medical devices that ensures unified semantics. Therefore, we use an OR table that is connected to other devices in an OR as an example.

Since interoperability in the operating room (OR) is considered a main factor to increase safety and improve the quality of surgeries, new challenges arise for the medical device industry in this increasingly connected environment. Therefore, new architectural approaches are needed, some of which may be inspired by other domains. In the meantime, novel communication paradigms are also gaining practical relevance in the automotive industry, which faces similar challenges. As a result, service-oriented architectures (SOAs) are often considered to provide a higher degree of flexibility for changes during the development and after product deployment. In this paper, we derive requirements of future networked OR tables from challenges and trends ahead. Based on these requirements, we propose a mixed electric and electronic architecture (E/E-architecture) inspired by the state-of-the-art measures from automotive domain and present an Identity and Access Management (IAM) approach to improve system security. In addition, a prototypical implementation is used to demonstrate the practicality of the proposed solution and to discuss necessary adjustments to the development process resulting from a mixed E/E-architecture approach.

The medical device industry faces new challenges in an increasingly connected environment. In addition, with interoperable medical devices, flexibility and adaptability are gaining more importance. Meanwhile, to support a higher degree of flexibility for adaptations during and after the development process, new communication paradigms are gaining practical importance in the automotive industry.In this paper, we compare the state-of-the-art measures from the automotive domain for requirements of future interconnected Operating-Room-Tables (OR-Tables). Based on these requirements, we propose a mixed architecture and present an Identity and Access Management (IAM) approach to improving the security of the system.

Transpulmonary thermodilution is well established as a tool for in-depth hemodynamic monitoring of critically ill patients during surgical procedures and intensive care. It permits easy assessment of graft function following cardiac transplantation and guides post-operative volume and catecholamine therapy. Since no pulmonary catheter is needed, transpulmonary thermodilution could be useful in experimental cardiac pig-to-baboon xenotransplantation. However, normal values for healthy animals have not yet been reported. Here, we present data from piglets and baboons before xenotransplantation experiments and highlight differences between the two species and human reference values. Transpulmonary thermodilution from baboons (body weight 10-34kg) and piglets (body weight 10-38kg) were analyzed. Measurements were taken in steady state after induction of general anesthesia before surgical procedures commenced. Cardiac index (CI), mean arterial pressure (MAP), systemic vascular resistance index (SVRI), parameters quantifying cardiac filling (global end-diastolic volume index, GEDI), and pulmonary edema (extravascular lung water, ELWI) were assessed. Preload, afterload, and contractility parameters clearly correlated with total body weight or body surface area. Baboons had lower CI values than weight-matched piglets (4.2±0.9l/min/m2 vs 5.3±1.0/min/m2 , P<.01). MAP and SVRI were higher in baboons than piglets (MAP: 99±22mmHg vs 62±11mmHg, P<.01; SVRI: 1823±581dyn*s/cm5 *m2 vs 827±204dyn*s/cm5 *m2 , P<.01). GEDI and ELWI did differ significantly between both species, but measurements were within similar ranges (GEDI: 523±103mL/m2 vs 433±78mL/m2 , P<.01; ELWI: 10±3mL/kg vs 11±2mL/kg, P<.01). Regarding adult human reference values, CI was similar to both baboons and piglets, but all other parameters were different. Parameters of preload, afterload, and contractility differ between baboons and piglets. In particular, baboons have a much higher afterload than piglets, which might be instrumental in causing perioperative xenograft dysfunction and post-operative myocardial hypertrophy after orthotopic pig-to-baboon cardiac xenotransplantation. Most transpulmonary thermodilution-derived parameters obtained from healthy piglets and baboons lie outside the reference ranges for humans, so human normal values should not be used to guide treatment in those animals. Our data provide reference values as a basis for developing algorithms for perioperative hemodynamic management in pig-to-baboon cardiac xenotransplantation.