Search

Patient monitoring is crucial in critical care medicine. Perceiving and interpreting multiple vital signs requires a high workload that can lead to decreased situation awareness and consequently inattentional blindness, defined as impaired perception of unexpectedly changing data. To facilitate information transfer, we developed and validated the Visual-Patient avatar. Generated by numerical data, the animation displays the status of vital signs and patient installations according to a user-centered design to improve situation awareness. As a surrogate parameter for information transfer in patient monitoring, we recorded visual attention using eye-tracking data. In this computer-based study, we compared the correlation of visually perceived and correctly interpreted vital signs between a Visual-Patient-avatar ICU and conventional patient monitoring. A total of 50 recruited study participants (25 nurses, 25 physicians) from five European study centers completed five randomized scenarios in both modalities. Using a stationary eye tracker as the primary endpoint, we recorded how long different areas of interest of the two monitoring modalities were viewed. In addition, we tested for a possible association between the length of time an area of interest was viewed and the correctness of the corresponding question. With the conventional monitor, participants looked at the installation site the longest (median 2.13–2.51 s). With the Visual-Patient-avatar ICU, gaze distribution was balanced; no area of interest was viewed for particularly long. For both modalities, the longer an area was viewed, the more likely the associated question was answered incorrectly (OR 0.97, 95% CI 0.95–0.99, p = 0.008). The Visual-Patient-avatar ICU facilitates and improves information transfer through its visualizations, especially with written information. The longer an area of interest was viewed, the more likely the associated question was answered incorrectly.

Background: Machine learning can analyze vast amounts of data and make predictions for events in the future. Our group created machine learning models for vital sign predictions. To transport the information of these predictions without numbers and numerical values and make them easily usable for human caregivers, we aimed to integrate them into the Philips Visual-Patient-avatar, an avatar-based visualization of patient monitoring. Methods: We conducted a computer-based simulation study with 70 participants in 3 European university hospitals. We validated the vital sign prediction visualizations by testing their identification by anesthesiologists and intensivists. Each prediction visualization consisted of a condition (e.g., low blood pressure) and an urgency (a visual indication of the timespan in which the condition is expected to occur). To obtain qualitative user feedback, we also conducted standardized interviews and derived statements that participants later rated in an online survey. Results: The mixed logistic regression model showed 77.9% (95% CI 73.2–82.0%) correct identification of prediction visualizations (i.e., condition and urgency both correctly identified) and 93.8% (95% CI 93.7–93.8%) for conditions only (i.e., without considering urgencies). A total of 49 out of 70 participants completed the online survey. The online survey participants agreed that the prediction visualizations were fun to use (32/49, 65.3%), and that they could imagine working with them in the future (30/49, 61.2%). They also agreed that identifying the urgencies was difficult (32/49, 65.3%). Conclusions: This study found that care providers correctly identified >90% of the conditions (i.e., without considering urgencies). The accuracy of identification decreased when considering urgencies in addition to conditions. Therefore, in future development of the technology, we will focus on either only displaying conditions (without urgencies) or improving the visualizations of urgency to enhance usability for human users.

Blood gas analysis plays a central role in modern medicine. Advances in technology have expanded the range of available parameters and increased the complexity of their interpretation. By applying user-centered design principles, it is possible to reduce the cognitive load associated with interpreting blood gas analysis. In this international, multicenter study, we explored anesthesiologists’ perspectives on Visual Blood, a novel visualization technique for presenting blood gas analysis results. We conducted interviews with participants following two computer-based simulation studies, the first utilizing virtual reality (VR) (50 participants) and the second without VR (70 participants). Employing the template approach, we identified key themes in the interview responses and formulated six statements, which were rated using Likert scales from 1 (strongly disagree) to 5 (strongly agree) in an online questionnaire. The most frequently mentioned theme was the positive usability features of Visual Blood. The online survey revealed that participants found Visual Blood to be an intuitive method for interpreting blood gas analysis (median 4, interquartile range (IQR) 4-4, p < 0.001). Participants noted that minimal training was required to effectively learn how to interpret Visual Blood (median 4, IQR 4-4, p < 0.001). However, adjustments are necessary to reduce visual overload (median 4, IQR 2-4, p < 0.001). Overall, Visual Blood received a favorable response. The strengths and weaknesses derived from these data will help optimize future versions of Visual Blood to improve the presentation of blood gas analysis results.

Decision confidence—the subjective belief to have made the right decision—is central in planning actions in a complex environment such as the medical field. It is unclear by which factors it is influenced. We analyzed a pooled data set of eight studies and performed a multicenter online survey assessing anesthesiologists’ opinions on decision confidence. By applying mixed models and using multiple imputation to determine the effect of missing values from the dataset on the results, we investigated how task performance, perceived workload, the utilization of user-centered medical diagnostic devices, job, work experience, and gender affected decision confidence. The odds of being confident increased with better task performance (OR: 1.27, 95% CI: 0.94 to 1.7; p = 0.12; after multiple imputation OR: 3.19, 95% CI: 2.29 to 4.45; p < 0.001) and when user-centered medical devices were used (OR: 5.01, 95% CI: 3.67 to 6.85; p < 0.001; after multiple imputation OR: 3.58, 95% CI: 2.65 to 4.85; p < 0.001). The odds of being confident decreased with higher perceived workload (OR: 0.94, 95% CI: 0.93 to 0.95; p < 0.001; after multiple imputation, OR: 0.94, 95% CI: 0.93 to 0.95; p < 0.001). Other factors, such as gender, job, or professional experience, did not affect decision confidence. Most anesthesiologists who participated in the online survey agreed that task performance (25 of 30; 83%), perceived workload (24 of 30; 80%), work experience (28 of 30; 93%), and job (21 of 30; 70%) influence decision confidence. Improved task performance, lower perceived workload, and user-centered design in medical equipment enhanced the decision confidence of anesthesia providers.

Visual-Patient-avatar, an avatar-based visualisation of patient monitoring, is a newly developed technology aiming to promote situation awareness through user-centred design. Before the technology’s introduction into clinical practice, the initial design used to validate the concept had to undergo thorough examination and adjustments where necessary. This mixed qualitative and quantitative study, consisting of three different study parts, aimed to create a design with high user acceptance regarding perceived professionalism and potential for identification while maintaining its original functionality. The first qualitative part was based on structured interviews and explored anaesthesia personnel’s first impressions regarding the original design. Recurrent topics were identified using inductive coding, participants’ interpretations of the vital sign visualisations analysed and design modifications derived. The second study part consisted of a redesign process, in which the visualisations were adapted according to the results of the first part. In a third, quantitative study part, participants rated Likert scales about Visual-Patient-avatar’s appearance and interpreted displayed vital signs in a computer-based survey. The first, qualitative study part included 51 structured interviews. Twenty-eight of 51 (55%) participants mentioned the appearance of Visual-Patient-avatar. In 23 of 51 (45%) interviews, 26 statements about the general impression were identified with a balanced count of positive (14 of 26) and negative (12 of 26) comments. The analysis of vital sign visualisations showed deficits in several vital sign visualisations, especially central venous pressure. These findings were incorporated into part two, the redesign of Visual-Patient-avatar. In the subsequent quantitative analysis of study for part three, 20 of 30 (67%) new participants agreed that the avatar looks professional enough for medical use. Finally, the participants identified 73% (435 of 600 cases) of all vital sign visualisations intuitively correctly without prior instruction. This study succeeded in improving the original design with good user acceptance and a reasonable degree of intuitiveness of the new, revised design. Furthermore, the study identified aspects relevant for the release of Visual-Patient-avatar, such as the requirement for providing at least some training, despite the design’s intuitiveness. The results of this study will guide further research and improvement of the technology. The study provides a link between Visual-Patient-avatar as a scientific concept and as an actual product from a cognitive engineering point of view, and may serve as an example of methods to study the designs of technologies in similar contexts.