Artificial intelligence (AI) is predicted to play an increasingly important role in perioperative medicine in the very near future. However, little is known about what anesthesiologists know and think about AI in this context. This is important because the successful introduction of new technologies depends on the understanding and cooperation of end users. We sought to investigate how much anesthesiologists know about AI and what they think about the introduction of AI-based technologies into the clinical setting. In order to better understand what anesthesiologists think of AI, we recruited 21 anesthesiologists from 2 university hospitals for face-to-face structured interviews. The interview transcripts were subdivided sentence-by-sentence into discrete statements, and statements were then grouped into key themes. Subsequently, a survey of closed questions based on these themes was sent to 70 anesthesiologists from 3 university hospitals for rating. In the interviews, the base level of knowledge of AI was good at 86 of 90 statements (96%), although awareness of the potential applications of AI in anesthesia was poor at only 7 of 42 statements (17%). Regarding the implementation of AI in anesthesia, statements were split roughly evenly between pros (46 of 105, 44%) and cons (59 of 105, 56%). Interviewees considered that AI could usefully be used in diverse tasks such as risk stratification, the prediction of vital sign changes, or as a treatment guide. The validity of these themes was probed in a follow-up survey of 70 anesthesiologists with a response rate of 70%, which confirmed an overall positive view of AI in this group. Anesthesiologists hold a range of opinions, both positive and negative, regarding the application of AI in their field of work. Survey-based studies do not always uncover the full breadth of nuance of opinion amongst clinicians. Engagement with specific concerns, both technical and ethical, will prove important as this technology moves from research to the clinic.
<b><i>Background:</i></b> Patient blood management (PBM) is a multidisciplinary and patient-centered treatment approach, comprising the detection and treatment of anemia, the minimization of blood loss, and the rational use of allogeneic transfusions. Pregnancy, delivery, and the puerperium are associated with increased rates of iron deficiency and anemia, which correlates with worse maternal and fetal outcomes and places pregnant women at increased risk of obstetric hemorrhage. <b><i>Summary:</i></b> Early screening for iron deficiency before the onset of anemia, as well as the use of oral and intravenous iron to treat iron deficiency anemia, has been shown to be beneficial. Anemia in pregnancy and the puerperium should be treated according to a staged regimen, administering either iron alone or in combination with an <i>off-label</i> use of human recombinant erythropoietin in selected patients. This regimen should be tailored to the needs of each individual patient. Postpartum hemorrhage (PPH) accounts for up to one-third of maternal deaths in both developing and developed countries. Bleeding complications should be anticipated and blood loss reduced by interdisciplinary preventive measures and individually tailored care. It is recommended that facilities have a PPH algorithm, primarily focusing on prevention through use of uterotonics, but also incorporating early diagnosis of the cause of bleeding, optimization of hemostatic conditions, timely administration of tranexamic acid, and integration of point-of-care tests to support the guided substitution of coagulation factors, alongside standard laboratory tests. Additionally, cell salvage has proven beneficial and should be considered for various indications in obstetrics including hematologic disturbances, as well as various forms of placental disorders. <b><i>Key Message:</i></b> This article reviews PBM in pregnancy, delivery, and the puerperium. The concept comprises early screening and treatment of anemia and iron deficiency, a transfusion and coagulation algorithm during delivery, as well as cell salvage.
BACKGROUND Artificial intelligence (AI) is predicted to play an increasingly important role in perioperative medicine in the very near future. However, little is known about what anesthesiologists know and think about AI in this context. This is important because the successful introduction of new technologies depends on the understanding and cooperation of end users. OBJECTIVE Investigate how much anesthesiologists know about AI, and what they think about the introduction of AI-based technologies into the clinical setting. METHODS In order to better understand what anesthesiologists think of AI, we recruited 21 anesthesiologists from two university hospitals for face-to-face structured interviews. Thematic analysis was applied to statements derived from these interviews, and key themes were determined. Subsequently, a survey of closed questions based on these themes was sent to 70 anesthesiologists from three university hospitals for rating. RESULTS In the interviews, the base level of knowledge of AI was good at 86 of 90 statements (96%), although awareness of potential applications of AI in anesthesia was poor at only 7 of 42 statements (17%). Regarding the implementation of AI in anesthesia, statements were split roughly evenly between pros (46 of 105, 44%) and cons (59 of 105, 56%). Interviewees considered that AI could usefully be used in diverse tasks such as risk stratification, the prediction of vital sign changes, or as a treatment guide. The validity of these themes was probed in a follow-up survey of 70 anesthesiologists with a response rate of 70%, which confirmed an overall positive view of AI in this group. CONCLUSIONS Anesthesiologists hold a range of opinions, both positive and negative, regarding the application of AI in their field of work. Survey-based studies do not always uncover the full breadth of nuance of opinion amongst clinicians. Engagement with specific concerns, both technical and ethical, will prove important as this technology moves from research into the clinic.
Acid–base homeostasis is crucial for all physiological processes in the body and is evaluated using arterial blood gas (ABG) analysis. Screens or printouts of ABG results require the interpretation of many textual elements and numbers, which may delay intuitive comprehension. To optimise the presentation of the results for the specific strengths of human perception, we developed Visual Blood, an animated virtual model of ABG results. In this study, we compared its performance with a conventional result printout. Seventy physicians from three European university hospitals participated in a computer-based simulation study. Initially, after an educational video, we tested the participants’ ability to assign individual Visual Blood visualisations to their corresponding ABG parameters. As the primary outcome, we tested caregivers’ ability to correctly diagnose simulated clinical ABG scenarios with Visual Blood or conventional ABG printouts. For user feedback, participants rated their agreement with statements at the end of the study. Physicians correctly assigned 90% of the individual Visual Blood visualisations. Regarding the primary outcome, the participants made the correct diagnosis 86% of the time when using Visual Blood, compared to 68% when using the conventional ABG printout. A mixed logistic regression model showed an odds ratio for correct diagnosis of 3.4 (95%CI 2.00–5.79, p < 0.001) and an odds ratio for perceived diagnostic confidence of 1.88 (95%CI 1.67–2.11, p < 0.001) in favour of Visual Blood. A linear mixed model showed a coefficient for perceived workload of −3.2 (95%CI −3.77 to −2.64) in favour of Visual Blood. Fifty-one of seventy (73%) participants agreed or strongly agreed that Visual Blood was easy to use, and fifty-five of seventy (79%) agreed that it was fun to use. In conclusion, Visual Blood improved physicians’ ability to diagnose ABG results. It also increased perceived diagnostic confidence and reduced perceived workload. This study adds to the growing body of research showing that decision-support tools developed around human cognitive abilities can streamline caregivers’ decision-making and may improve patient care.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.