Aim: The effects of using handheld devices in combination with filtering and delaying alarms were investigated. Effects on the number of alarms, patient safety, and nurses' experience were evaluated. Methods: Alarm and physiological trend data were collected over two periods of three months for a control (n = 54) and intervention (n = 47) group. During the intervention period, an adapted alarm architecture, filtering and delaying alarms, was implemented, and the number of alarms, critical cardiorespiratory events, and episodes of decreased oxygen saturation and heart rate were compared to the contemporary alarm architecture. Nurses filled out a survey on their experiences. Results: The adapted alarm architecture reduced the number of alarms by 84%. This reduction did not result in significant differences in the number of critical events. Additionally, the duration and depth of the patient's episodes of mildly decreased oxygen saturation and heart rate were unaffected. Nurses reported that they continue to receive too many alarms and occasionally miss alarms. Conclusion: Alarms can be filtered and delayed, reducing the number of alarms and preventing alarm fatigue. Patient safety is not at risk since the number of critical events and the decreases in oxygen saturation and heart rate do not differ significantly between the groups.

Background
Switching from controlled to assisted ventilation is crucial in the trajectory of intensive care unit (ICU) stay, but no guidelines exist. We described current practices, analyzed patient characteristics associated with switch success or failure, and explored the feasibility to predict switch failure.

Methods
In this retrospective study, we obtained highly granular longitudinal ICU data sets from three medical centers, covering demographics, severity scores, vital signs, ventilation, and laboratory parameters. The primary endpoint was switch success, considering a switch attempt to be successful if a patient did not return to controlled ventilation for the next 72 h while alive, and to be failed otherwise. We compared the characteristics of patients with successful vs. failed first switch attempts at ICU admission, immediately before, and 3 h after the attempt. We trained LASSO logistic regression models to predict switch failure.

Results
In 4524/6715 (67%) patients attempting a switch, the first attempt failed. The first switch attempt, regardless of success or failure, was generally made at normalized PaCO2 and pH levels, with PEEP < 10 cmH2O and PaO2/FiO2 indicating mild injury. Despite very similar baseline disease severity, switch failure was associated with significantly worse outcomes, including a 28-day mortality of 27% vs. 16% and median ventilator-free days of 16 vs. 22 (p < 0.001). Failed attempts were initiated significantly earlier than successful ones (median 1.8 vs. 1.3 days, p < 0.001). Before the switch, PaO2/FiO2, if measured at PEEP > 10 cmH2O, and respiratory system compliance was lower in patients with switch failure (median 185 vs. 205 mmHg, p < 0.001; 39 vs. 41 mL/cmH2O, P = 0.001), and post-switch, patients with switch failure experienced greater deterioration in gas exchange and minimal improvement in ventilatory parameters post-switch. Contrary to our hypotheses, patient characteristics for failed vs. successful switches were surprisingly similar, resulting in prediction models with limited discriminative performance.

Conclusions
Approximately two-thirds of attempts to switch patients to assisted ventilation fail, which are associated with significantly worse clinical outcomes, despite similar baseline disease severity. Contrary to our hypotheses, patients with successful and failed attempts showed similar characteristics, making switch failure difficult to predict. These findings underscore the importance of preventing switch failures and, given the retrospective nature of this study, highlight the need for prospective studies to better understand the reasons for switch failure and when spontaneous breathing can be safely initiated.

Despite artificial intelligence (AI) technology progresses at unprecedented rate, our ability to translate these advancements into clinical value and adoption at the bedside remains comparatively limited. This paper reviews the current use of implementation outcomes in randomized controlled trials evaluating AI-based clinical decision support and found limited adoption. To advance trust and clinical adoption of AI, there is a need to bridge the gap between traditional quantitative metrics and implementation outcomes to better grasp the reasons behind the success or failure of AI systems and improve their translation into clinical value.

Artificial intelligence (AI) research in the intensive care unit (ICU) mainly focuses on developing models (from linear regression to deep learning) to predict out-
comes, such as mortality or sepsis [1, 2]. However, there is another important aspect of AI that is typically not framed as AI (although it may be more worthy of the name), which is the prediction of patient outcomes or events that would result from different actions, known as causal inference [3, 4]. This aspect of AI is crucial for decision-making in the ICU. To emphasize the impor- tance of causal inference, we propose to refer to any data- driven model used for causal inference tasks as ‘action- able AI’, as opposed to ‘predictive AI’, and discuss how these models could provide meaningful decision support in the ICU.

Background: The COVID-19 pandemic continues to overwhelm intensive care units (ICUs) worldwide, and improved prediction of mortality among COVID-19 patients could assist decision making in the ICU setting. In this work, we report on the development and validation of a dynamic mortality model specifically for critically ill COVID-19 patients and discuss its potential utility in the ICU. Methods: We collected electronic medical record (EMR) data from 3222 ICU admissions with a COVID-19 infection from 25 different ICUs in the Netherlands. We extracted daily observations of each patient and fitted both a linear (logistic regression) and non-linear (random forest) model to predict mortality within 24 h from the moment of prediction. Isotonic regression was used to re-calibrate the predictions of the fitted models. We evaluated the models in a leave-one-ICU-out (LOIO) cross-validation procedure. Results: The logistic regression and random forest model yielded an area under the receiver operating characteristic curve of 0.87 [0.85; 0.88] and 0.86 [0.84; 0.88], respectively. The recalibrated model predictions showed a calibration intercept of −0.04 [−0.12; 0.04] and slope of 0.90 [0.85; 0.95] for logistic regression model and a calibration intercept of −0.19 [−0.27; −0.10] and slope of 0.89 [0.84; 0.94] for the random forest model. Discussion: We presented a model for dynamic mortality prediction, specifically for critically ill COVID-19 patients, which predicts near-term mortality rather than in-ICU mortality. The potential clinical utility of dynamic mortality models such as benchmarking, improving resource allocation and informing family members, as well as the development of models with more causal structure, should be topics for future research.

Psychological needs of users as a basis for design are at the core of design practice, yet the importance of fundamental human needs when designing soundscapes has not been studied specifically. This paper investigates the relationship between nine fundamental human needs and the affective qualities and categories of soundscapes. In a free-labeling survey study, we collected descriptions of imagined sound environments for the fulfilment of the needs, as well as ratings of the perceived affective quality of these environments. We found that needs were associated with pleasant soundscapes, while their eventfulness varied. ‘Human’ sounds were a common category for each of the nine needs considered in this study, but systematic variations of the categories were found dependent on the need. Results suggest that designing categorically different soundscapes dependent on the users’ needs will have beneficial effects.

Objective Although the role of artificial intelligence (AI) in medicine is increasingly studied, most patients do not benefit because the majority of AI models remain in the testing and prototyping environment. The development and implementation trajectory of clinical AI models are complex and a structured overview is missing. We therefore propose a step-by-step overview to enhance clinicians' understanding and to promote quality of medical AI research. Methods We summarised key elements (such as current guidelines, challenges, regulatory documents and good practices) that are needed to develop and safely implement AI in medicine. Conclusion This overview complements other frameworks in a way that it is accessible to stakeholders without prior AI knowledge and as such provides a step-by-step approach incorporating all the key elements and current guidelines that are essential for implementation, and can thereby help to move AI from bytes to bedside.