Filtern
Erscheinungsjahr
Dokumenttyp
Sprache
- Englisch (168) (entfernen)
Volltext vorhanden
- ja (168)
Gehört zur Bibliographie
- nein (168)
Schlagworte
- Deutschland (11)
- Nachhaltigkeit (11)
- Rückenschmerz (11)
- COVID-19 (7)
- Maschinelles Lernen (7)
- China (6)
- Gesundheitswesen (6)
- Künstliche Intelligenz (6)
- Pandemie (6)
- Radar (6)
Institut
- FB Bauen + Leben (43)
- FB Umweltplanung/-technik (UCB) (43)
- FB Informatik + Therapiewissenschaft (30)
- FB Technik (12)
- IfaS - Institut für angewandtes Stoffstrommanagement (10)
- InDi - Institut für Internationale und Digitale Kommunikation (7)
- LaROS - Labor für Radiotechnologie und optische Systeme (6)
- FB Umweltwirtschaft/-recht (UCB) (5)
- ISS - Institut für Softwaresysteme in Wirtschaft, Umwelt und Verwaltung (5)
- FB Wirtschaft (3)
In recent years, the retail virtual store has become the main trend in social services. More and more people tend to shop in retail virtual stores. With the development of 3D virtual reality, this trend is getting stronger and stronger. Therefore, the development prospect of virtual retail stores has attracted much attention. This paper examines the impact of companies' and users' popularization of helmet gadgets on in-store traffic and analyzes how virtual reality (VR) could enhance the customer experience throughout the shopping trip. A qualitative research design has been used, which also included conversations with both professionals and consumers. Moreover, this paper seeks to break new ground by attempting to use the current literature to help predict future directions and trends for online shopping.
In this paper two simple synthetic aperture radar (SAR) methods are applied on data from a 24 GHz FMCW radar implemented on a linear drive for educational purposes. The data of near and far range measurements are evaluated using two different SAR signal processing algorithms featuring 2D-FFT and frequency back projection (FBP) method (Moreira et al., 2013). A comparison of these two algorithms is performed concerning runtime, image pixel size, azimuth and range resolution. The far range measurements are executed in a range of 60 to 135 m by monitoring cars in a parking lot. The near range measurement from 0 to 5 m are realised in a measuring chamber equipped with absorber foam and nearly ideal targets like corner reflectors. The comparison of 2D-FFT and FBP algorithm shows that both deliver good and similar results for the far range measurements but the runtime of the FBP algorithm is up to 150 times longer as the 2D-FFT runtime. In the near range measurements the FBP algorithm displays a very good azimuth resolution and targets which are very close to each other can be separated easily. In contrast to that the 2D-FFT algorithm has a lower azimuth resolution in the near range, thus targets which are very close to each other, merge together and cannot be separated.
Background: The STarT-MSK-Tool is an adaptation of the well established STarT-Back-Tool, used to risk-stratify patients with a wider range of musculoskeletal presentations.
Objective: To formally translate and cross-culturally adapt the Keele STarT-MSK risk stratification tool into German (STarT-MSKG) and to establish its reliability and validity.
Methods: A formal, multi-step, forward and backward translation approach was used. To assess validity patients aged ≥18 years, with acute, subacute or chronic musculoskeletal presentations in the lumbar spine, hip, knee, shoulder, or neck were included. The prospective cohort was used with initial data collected electronically at the point-of-consultation. Retest and 6-month follow-up questionnaires were sent by email. Test-retest reliability, construct validity, discriminative ability, predictive ability and floor or ceiling effects were analysed using intraclass correlation coefficient, and comparisons with a reference standard (Orebro-Musculoskeletal-Pain-Questionnaire: OMPQ) using correlations, ROC-curves and regression models.
Results: The participants’ (n = 287) mean age was 47 (SD = 15.8) years, 51% were female, with 48.8% at low, 43.6% at medium, and 7.7% at high risk. With ICC = 0.75 (95% CI 0.69; 0.81) test-retest-reliability was good. Construct validity was good with correlations for the STarT-MSKG-Tool against the OMPQ-Tool of rs = 0.74 (95% CI 0.68, 0.79). The ability of the tool [comparison OMPQ] to predict 6-month pain and disability was acceptable with AUC = 0.77 (95% CI 0.71, 0.83) [OMPQ = 0.74] and 0.76 (95% CI 0.69, 0.82) [OMPQ = 0.72] respectively. However, the explained variance (linear/logistic regression) for predicting 6-month pain (21% [OMPQ = 17%]/logistic = 29%) and disability (linear = 20%:[OMPQ = 19%]/logistic = 26%), whilst being comparable to the existing OMPQ reference standard, fell short of the a priori target of ≥30%.
Conclusions: The German version of the STarT-MSK-Tool is a valid instrument for use across multiple musculoskeletal conditions and is availabe for use in clinical practice. Comparison with the OMPQ suggests it is a good alternative.
Context: In the framework of studying cosmic microwave background polarization and characterizing its Galactic foregrounds, the angular power spectrum analysis of the thermal dust polarization map has led to intriguing evidence of an E/B asymmetry and a positive TE correlation. The interpretation of these observations is the subject of theoretical and simulation-driven studies in which the correlation between the density structure of the interstellar medium (ISM) and the magnetic field appears to be a key aspect. In this context, and when the magnetized ISM structures are modeled in three dimensions, dust clouds are generally considered to be filamentary structures only, but both filamentary and sheet-like shapes are supported by observational and theoretical evidence.
Aims: We aim to study the influence of the cloud shape and its connection to the local magnetic field, as well as the influence from the viewing angle, on the angular power spectra measured on thermal dust polarization maps; we specifically focus on the dependence of the E/B power asymmetry and TE correlation.
Methods: To this end, we simulated realistic interstellar clouds with both filament-like and sheet-like shapes using the software ASTERION, which also allowed us to generate synthetic maps of thermal dust polarized emission with an area of 400 square degrees. Then, we computed their polarization power spectra in the multipole range ℓ ϵ [100, 500] and focused on the E/B power asymmetry, quantified through the ℛEB ratio, and the correlation coefficient rTE between Τ and Ε modes. We quantified the dependence of ℛEB and rTE values on the offset angle (between the longest cloud axis and local magnetic field lines) and inclination angle (between the line of sight and the magnetic field) for both types of cloud shapes, either embedded in a regular magnetic field or coupled to a nonregular field to mimic turbulence.
Results: We find that both types of cloud shapes cover the same regions of the (ℛEB, rTE) parameter space. The dependence on the inclination and offset angles is similar for both shapes, although sheet-like structures generally show larger scatter than filamentary structures. In addition to the known dependence on the offset angle, we find a strong dependence of ℛEB and rTE on the inclination angle.
Conclusions: The very fact that filament-like and sheet-like structures may lead to polarization power spectra with similar (ℛEB,rTE) values complicates their interpretation. We argue that interpreting them solely in terms of filament characteristics is risky, and in future analyses, this degeneracy should be accounted for, as should the connection to the magnetic field geometry. Our results based on maps of 400 square degrees clarify that the overall geometrical arrangement of the magnetized ISM surrounding the observer leaves its marks on polarization power spectra.
Background: Stratified care has the potential to be efficient in addressing the physical and psychosocial components of low back pain (LBP) and optimise treatment outcomes essential in low-income countries. This study aimed to investigate the perceptions of physiotherapists and patients in Nigeria towards stratified care for the treatment of LBP, exploring barriers and enablers to implementation.
Methods: A qualitative design with semistructured individual telephone interviews for physiotherapists and patients with LBP comprising research evidence and information on stratified care was adopted. Preceding the interviews, patients completed the Subgroups for Targeted Treatment tool. The interviews were recorded, transcribed and analysed following grounded theory methodology.
Results: Twelve physiotherapists and 13 patients with LBP participated in the study (11 female, mean age 42.8 (SD 11.47) years). Seven key categories emerged: recognising the need for change, acceptance of innovation, resistance to change, adapting practice, patient’s learning journey, trusting the therapist and needing conviction. Physiotherapists perceived stratified care to be a familiar approach based on their background training. The prevalent treatment tradition and the patient expectations were seen as major barriers to implementation of stratified care by the physiotherapists. Patients see themselves as more informed than therapists realise, yet they need conviction through communication and education to cooperate with their therapist using this approach. Viable facilitators were also identified as patients’ trust in the physiotherapist and adaptations in terms of training and modification of the approach to enhance its use.
Conclusion: Key barriers identified are the patients’ treatment expectations and physiotherapists’ adherence to the tradition of practice. Physiotherapists might facilitate implementation of the stratified care by communication, hierarchical implementation and utilisation of patients’ trust. Possibilities to develop a consensus on key strategies to overcome barriers and on utilisation of facilitators should be tested in future research.
Abstract: This paper is about detecting the difference between fully-random and semi-random shuffleing data sets, with the use of unsupervised learning algorithms. Because of the limits of the k-means algorithm alone, a recurrent autoencoder is used for feature extraction to improve the results of k-means. In the next step the autoencoder alone is used for clustering.
Introduction: In the last years, machine learning has been used more and more in different areas and it is also appropriate for for pattern recognition in data. Random data is characterized through the missing of defined patterns. Permutations without repetitions have the highest amount of entropy for a sequence of its length, which is similar to random data according to Andrei Kolmogorov, who states that random data have the highest amount of information and can’t be compressed. Therefore, this paper analyses the difference between random permutations and good shuffled permutations, which have some remaining patterns left. This is done via a recurrent autoencoder.
Background: The extramuscular connective tissue (ECT) has been shown to play a significant role in mechanical force transmission between musculoskeletal structures. Due to this and owing to its tight connection with the underlying muscle, the ECT may be vulnerable to excessive loading. The present study aimed to investigate the effect of eccentric elbow flexor exercise on the morphology of the biceps brachii ECT. In view of the high nociceptive capacity of the ECT, an additional objective was to elucidate the potential relationship between ECT damage and the occurrence of delayed onset muscle soreness (DOMS).
Methods: Eleven healthy participants (♂ = 7; 24 ± 2 years) performed fatiguing dumbbell elbow flexor eccentric exercise (EE) for one arm and concentric exercise (CE) for the other arm in random order and with random arm allocation. Before, immediately after and 24–96 h post-exercise, maximal voluntary isometric contraction torque of the elbow flexors (dynamometer), pressure pain (algometer), palpation pain (100 mm visual analog scale), biceps brachii ECT thickness and ECT/muscle mobility during passive movement (both high-resolution ultrasound) were examined.
Results: Palpation pain, suggestive of DOMS, was greater after EE than CE, and maximal voluntary isometric contraction torque decreased greater after EE than CE (p < .05). Relative to CE, EE increased ECT thickness at 48 (+ 17%), 72 (+ 14%) and 96 (+ 15%) hours post-exercise (p < .05). At 96 h post-EE, the increase in ECT thickness correlated with palpation pain (r = .68; p < .05). ECT mobility was not different between conditions, but compared to CE, muscle displacement increased at 24 (+ 31%), 72 (+ 31%) and 96 (+ 41%) hours post-EE (p < .05).
Conclusion: Collectively, these results suggest an involvement of the ECT changes in delayed onset muscle soreness.
Research integrity (RI) has been a focus of society in recent years as a means to create and to keep trust in science. Higher education institutions (HEIs) play a key role in promoting a culture of RI and responsible conduct of research (RCR). The understanding and practice of RI can vary across cultures. This article aims to outline initial insights into university students’ RI mindsets based on five RI facets: understanding, importance, value-action gap, enforcement approaches, and training. A qualitative exploratory cross-cultural study was conducted with participants from Germany and Bulgaria via semi-structured guided group interviews. An explicit transcultural agreement regarding the significance of RI was categorically indicated. Intercultural differences between the two European countries were revealed and discussed in reference to understanding RI, the value-action gap, enforcement approaches, and training preferences.
Background: Improving movement control might be a promising treatment goal during chronic non-specific low back pain (CLBP) rehabilitation. The objective of the study is to evaluate the effect of a single bout of game-based real-time feedback intervention on trunk movement in patients with CLBP.
Methods: Thirteen CLBP patients (8female;41 ± 16 years;173 ± 10 cm;78 ± 22 kg) were included in this randomized cross-over pilot trial. During one laboratory session (2 h), participants performed three identical measurements on trunk movement all including: first, maximum angle of lateral flexion was assessed. Secondly, a target trunk lateral flexion (angle: 20°) was performed. Main outcome was maximum angle ([°]; MA). Secondary outcomes were deviation [°] from the target angle (angle reproduction; AR) and MA of the secondary movement planes (rotation; extension/flexion) during lateral flexion. The outcomes were assessed by an optical 3D-motion-capture-system (2-segment-trunk-model). The measurements were separated by 12-min of intervention and/or resting (randomly). The intervention involved a sensor-based trunk exergame (guiding an avatar through virtual worlds). After carryover effect-analysis, pre-to-post intervention data were pooled between the two sequences followed by analyses of variances (paired t-test).
Results: No significant change from pre to post intervention for MA or AR for any segment occurred for the main movement plane, lateral flexion (p > .05). The upper trunk segment showed a significant decrease of the MA for trunk extension/flexion from pre to post intervention ((4.4° ± 4.4° (95% CI 7.06–1.75)/3.5° ± 1.29° (95% CI 6.22–0.80); p = 0.02, d = 0.20).
Conclusions: A single bout of game-based real-time feedback intervention lead to changes in the secondary movement planes indicating reduced evasive motion during trunk movement.
Research in global change ecology relies heavily on global climatic grids derived from estimates of air temperature in open areas at around 2 m above the ground. These climatic grids do not reflect conditions below vegetation canopies and near the ground surface, where critical ecosystem functions occur and most terrestrial species reside. Here, we provide global maps of soil temperature and bioclimatic variables at a 1-km2 resolution for 0–5 and 5–15 cm soil depth. These maps were created by calculating the difference (i.e. offset) between in situ soil temperature measurements, based on time series from over 1200 1-km2 pixels (summarized from 8519 unique temperature sensors) across all the world's major terrestrial biomes, and coarse-grained air temperature estimates from ERA5-Land (an atmospheric reanalysis by the European Centre for Medium-Range Weather Forecasts). We show that mean annual soil temperature differs markedly from the corresponding gridded air temperature, by up to 10°C (mean = 3.0 ± 2.1°C), with substantial variation across biomes and seasons. Over the year, soils in cold and/or dry biomes are substantially warmer (+3.6 ± 2.3°C) than gridded air temperature, whereas soils in warm and humid environments are on average slightly cooler (−0.7 ± 2.3°C). The observed substantial and biome-specific offsets emphasize that the projected impacts of climate and climate change on near-surface biodiversity and ecosystem functioning are inaccurately assessed when air rather than soil temperature is used, especially in cold environments. The global soil-related bioclimatic variables provided here are an important step forward for any application in ecology and related disciplines. Nevertheless, we highlight the need to fill remaining geographic gaps by collecting more in situ measurements of microclimate conditions to further enhance the spatiotemporal resolution of global soil temperature products for ecological applications.
This article discusses ethics in times of pandemic crisis (COVID-19) taking into consideration the sustainability paradigm. Two related ethical approaches are discussed and contrasted. On the one hand, the relational embodied ethics of the commons is discussed in the background of the pandemic of COVID-19. On the other hand, "lifeboat ethics" is interpreted in considering the pandemic situation. The main goal of the article is to compare the two ethical approaches as a way of dealing with our shared predicament in times of a pandemic, a state of exception, and based on that, to additionally derive conclusions about their application in further crises in the Anthropocene, whereby the primacy of sustainability is presumed.
Unintended nuclear war
(2021)
Carbon footprinting of universities worldwide: Part I — objective comparison by standardized metrics
(2021)
Background: Universities, as innovation drivers in science and technology worldwide, should be leading the Great Transformation towards a carbon–neutral society and many have indeed picked up the challenge. However, only a small number of universities worldwide are collecting and publishing their carbon footprints, and some of them have defined zero emission targets. Unfortunately, there is limited consistency between the reported carbon footprints (CFs) because of different analysis methods, different impact measures, and different target definitions by the respective universities.
Results: Comprehensive CF data of 20 universities from around the globe were collected and analysed. Essential factors contributing to the university CF were identified. For the first time, CF data from universities were not only compared. The CF data were also evaluated, partly corrected, and augmented by missing contributions, to improve the consistency and comparability. The CF performance of each university in the respective year is thus homogenized, and measured by means of two metrics: CO2e emissions per capita and per m2 of constructed area. Both metrics vary by one order of magnitude across the different universities in this study. However, we identified ten universities reaching a per capita carbon footprint of lower than or close to 1.0 Mt (metric tons) CO2e/person and year (normalized by the number of people associated with the university), independent from the university’s size. In addition to the aforementioned two metrics, we suggested a new metric expressing the economic efficiency in terms of the CF per $ expenditures and year. We next aggregated the results for all three impact measures, arriving at an overall carbon performance for the respective universities, which we found to be independent of geographical latitude. Instead the per capita measure correlates with the national per capita CFs, and it reaches on average 23% of the national impacts per capita. The three top performing universities are located in Switzerland, Chile, and Germany.
Conclusion: The usual reporting of CO2 emissions is categorized into Scopes 1–3 following the GHG Protocol Corporate Accounting Standard which makes comparison across universities challenging. In this study, we attempted to standardize the CF metrics, allowing us to objectively compare the CF at several universities. From this study, we observed that, almost 30 years after the Earth Summit in Rio de Janeiro (1992), the results are still limited. Only one zero emission university was identified, and hence, the transformation should speed up globally.
Laboratory protocols using magnetic beads have gained importance in the purification of mRNA for vaccines. Here, the produced mRNA hybridizes specifically to oligo(dT)-functionalized magnetic beads after cell lysis. The mRNA-loaded magnetic beads can be selectively separated using a magnet. Subsequently, impurities are removed by washing steps and the mRNA is eluted. Magnetic separation is utilized in each step, using different buffers such as the lysis/binding buffer. To reduce the time required for purification of larger amounts of mRNA vaccine for clinical trials, high-gradient magnetic separation (HGMS) is suitable. Thereby, magnetic beads are selectively retained in a flow-through separation chamber. To meet the requirements of biopharmaceutical production, a disposable HGMS separation chamber with a certified material (United States Pharmacopeia Class VI) was developed which can be manufactured using 3D printing. Due to the special design, the filter matrix itself is not in contact with the product. The separation chamber was tested with suspensions of oligo(dT)-functionalized Dynabeads MyOne loaded with synthetic mRNA. At a concentration of cB = 1.6–2.1 g·L–1 in lysis/binding buffer, these 1 μm magnetic particles are retained to more than 99.39% at volumetric flows of up to 150 mL·min–1 with the developed SU-HGMS separation chamber. When using the separation chamber with volumetric flow rates below 50 mL·min–1, the retained particle mass is even more than 99.99%.
Purification of mRNA with oligo(dT)-functionalized magnetic particles involves a series of magnetic separations for buffer exchange and washing. Magnetic particles interact and agglomerate with each other when a magnetic field is applied, which can result in a decreased total surface area and thus a decreased yield of mRNA. In addition, agglomeration may also be caused by mRNA loading on the magnetic particles. Therefore, it is of interest how the individual steps of magnetic separation and subsequent redispersion in the buffers used affect the particle size distribution. The lysis/binding buffer is the most important buffer for the separation of mRNA from the multicomponent suspension of cell lysate. Therefore, monodisperse magnetic particles loaded with mRNA were dispersed in the lysis/binding buffer and in the reference system deionized water, and the particle size distributions were measured. A concentration-dependent agglomeration tendency was observed in deionized water. In contrast, no significant agglomeration was detected in the lysis/binding buffer. With regard to magnetic particle recycling, the influence of different storage and drying processes on particle size distribution was investigated. Agglomeration occurred in all process alternatives. For de-agglomeration, ultrasonic treatment was examined. It represents a suitable method for reproducible restoration of the original particle size distribution.
The implementation of single-use technologies offers several major advantages, e.g. prevention of cross-contamination, especially when spore-forming microorganisms are present. This study investigated the application of a single-use bioreactor in batch fermentation of filamentous fungus Penicillium sp. (IBWF 040-09) from the Institute of Biotechnology and Drug Research (IBWF), which is capable of intracellular production of a protease inhibitor against parasitic proteases as a secondary metabolite. Several modifications to the SU bioreactor were suggested in this study to allow the fermentation in which the fungus forms pellets. Simultaneously, fermentations in conventional glass bioreactor were also conducted as reference. Although there are significant differences in the construction material and gassing system, the similarity of the two types of bioreactors in terms of fungal metabolic activity and the reproducibility of fermentations could be demonstrated using statistic methods. Under the selected cultivation conditions, growth rate, yield coefficient, substrate uptake rate, and formation of intracellular protease-inhibiting substance in the single-use bioreactor were similar to those in the glass bioreactor.
Thailand’s power system has been facing an energy transition due to the increasing amount of Renewable Energy (RE) integration, prosumers with self-consumption, and digitalization-based business models in a Local Energy Market (LEM). This paper introduces a decentralized business model and a possible trading platform for electricity trading in Thailand’s Micro-Grid to deal with the power system transformation. This approach is Hybrid P2P, a market structure in which sellers and buyers negotiate on energy exchanging by themselves called Fully P2P trading or through the algorithm on the market platform called Community-based trading. A combination of Auction Mechanism (AM), Bill Sharing (BS), and Traditional Mechanism (TM) is the decentralized price mechanism proposed for the Community-based trading. The approach is validated through a test case in which, during the daytime, the energy import and export of the community are significantly reduced when 75 consumers and 25 PV rooftop prosumers participate in this decentralized trading model. Furthermore, a comparison analysis confirms that the decentralized business model outperforms a centralized approach on community and individual levels.
As productive biofilms are increasingly gaining interest in research, the quantitative monitoring of biofilm formation on- or offline for the process remains a challenge. Optical coherence tomography (OCT) is a fast and often used method for scanning biofilms, but it has difficulty scanning through more dense optical materials. X-ray microtomography (μCT) can measure biofilms in most geometries but is very time-consuming. By combining both methods for the first time, the weaknesses of both methods could be compensated. The phototrophic cyanobacterium Tolypothrix distorta was cultured in a moving bed photobioreactor inside a biocarrier with a semi-enclosed geometry. An automated workflow was developed to process µCT scans of the biocarriers. This allowed quantification of biomass volume and biofilm-coverage on the biocarrier, both globally and spatially resolved. At the beginning of the cultivation, a growth limitation was detected in the outer region of the carrier, presumably due to shear stress. In the later phase, light limitations could be found inside the biocarrier. µCT data and biofilm thicknesses measured by OCT displayed good correlation. The latter could therefore be used to rapidly measure the biofilm formation in a process. The methods presented here can help gain a deeper understanding of biofilms inside a process and detect any limitations.
Introduction: The use of social marketing strategies to induce the promotion of cognitive health has received little attention in research. The objective of this scoping review is twofold: (i) to identify the social marketing strategies that have been used in recent years to initiate and maintain health-promoting behaviour; (ii) to advance research in this area to inform policy and practice on how to best make use of these strategies to promote cognitive health.
Methods and analysis: We will use the five-stage methodological framework of Arksey and O'Malley. Articles in English published since 2010 will be searched in electronic databases (the Cochrane Library, DoPHER, the International Bibliography of the Social Sciences, PsycInfo, PubMed, ScienceDirect, Scopus). Quantitative and qualitative study designs as well as reviews will be considered. We will include those articles that report the design, implementation, outcomes and evaluation of programmes and interventions concerning social marketing and/or health promotion and/or promotion of cognitive health. Grey literature will not be searched. Two independent reviewers will assess in detail the abstracts and full text of selected citations against the inclusion criteria. A Preferred Reporting Items for Systematic Reviews and Meta-Analyses flowchart for Scoping Reviews will be used to illustrate the process of article selection. We will use a data extraction form, present the results through narrative synthesis and discuss them in relation to the scoping review research questions.
Ethics and dissemination: Ethics approval is not required for conducting this scoping review. The results of the review will be the first step to advance a conceptual framework, which contributes to the development of interventions targeting the promotion of cognitive health. The results will be published in a peer-reviewed scientific journal. They will also be disseminated to key stakeholders in the field of the promotion of cognitive health.
The aim of this work was to develop and evaluate the reinforcement learning algorithm VentAI, which is able to suggest a dynamically optimized mechanical ventilation regime for critically-ill patients. We built, validated and tested its performance on 11,943 events of volume-controlled mechanical ventilation derived from 61,532 distinct ICU admissions and tested it on an independent, secondary dataset (200,859 ICU stays; 25,086 mechanical ventilation events). A patient “data fingerprint” of 44 features was extracted as multidimensional time series in 4-hour time steps. We used a Markov decision process, including a reward system and a Q-learning approach, to find the optimized settings for positive end-expiratory pressure (PEEP), fraction of inspired oxygen (FiO2) and ideal body weight-adjusted tidal volume (Vt). The observed outcome was in-hospital or 90-day mortality. VentAI reached a significantly increased estimated performance return of 83.3 (primary dataset) and 84.1 (secondary dataset) compared to physicians’ standard clinical care (51.1). The number of recommended action changes per mechanically ventilated patient constantly exceeded those of the clinicians. VentAI chose 202.9% more frequently ventilation regimes with lower Vt (5–7.5 mL/kg), but 50.8% less for regimes with higher Vt (7.5–10 mL/kg). VentAI recommended 29.3% more frequently PEEP levels of 5–7 cm H2O and 53.6% more frequently PEEP levels of 7–9 cmH2O. VentAI avoided high (>55%) FiO2 values (59.8% decrease), while preferring the range of 50–55% (140.3% increase). In conclusion, VentAI provides reproducible high performance by dynamically choosing an optimized, individualized ventilation strategy and thus might be of benefit for critically ill patients.