Background: Artificial intelligence–based clinical decision support (AI-CDS) tools have great potential to benefit intensive care unit (ICU) patients and physicians. There is a gap between the... Show moreBackground: Artificial intelligence–based clinical decision support (AI-CDS) tools have great potential to benefit intensive care unit (ICU) patients and physicians. There is a gap between the development and implementation of these tools.Objective: We aimed to investigate physicians’ perspectives and their current decision-making behavior before implementing a discharge AI-CDS tool for predicting readmission and mortality risk after ICU discharge.Methods: We conducted a survey of physicians involved in decision-making on discharge of patients at two Dutch academic ICUs between July and November 2021. Questions were divided into four domains: (1) physicians’ current decision-making behavior with respect to discharging ICU patients, (2) perspectives on the use of AI-CDS tools in general, (3) willingness to incorporate a discharge AI-CDS tool into daily clinical practice, and (4) preferences for using a discharge AI-CDS tool in daily workflows.Results: Most of the 64 respondents (of 93 contacted, 69%) were familiar with AI (62/64, 97%) and had positive expectations of AI, with 55 of 64 (86%) believing that AI could support them in their work as a physician. The respondents disagreed on whether the decision to discharge a patient was complex (23/64, 36% agreed and 22/64, 34% disagreed); nonetheless, most (59/64, 92%) agreed that a discharge AI-CDS tool could be of value. Significant differences were observed between physicians from the 2 academic sites, which may be related to different levels of involvement in the development of the discharge AI-CDS tool.Conclusions: ICU physicians showed a favorable attitude toward the integration of AI-CDS tools into the ICU setting in general, and in particular toward a tool to predict a patient’s risk of readmission and mortality within 7 days after discharge. The findings of this questionnaire will be used to improve the implementation process and training of end users. Show less
Background Despite the availability of guidelines for the performance of transcatheter aortic valve implantation (TAVI), current treatment pathways vary between countries and institutions, which... Show moreBackground Despite the availability of guidelines for the performance of transcatheter aortic valve implantation (TAVI), current treatment pathways vary between countries and institutions, which impact on the mean duration of postprocedure hospitalization.Methods and Results This was a prospective, multicenter registry of 502 patients to validate the appropriateness of discharge timing after transfemoral TAVI, using prespecified risk criteria from FAST-TAVI (Feasibility and Safety of Early Discharge After Transfemoral [TF] Transcatheter Aortic Valve Implantation), based on hospital events within 1-year after discharge. The end point-a composite of all-cause mortality, vascular access-related complications, permanent pacemaker implantation, stroke, cardiac rehospitalization, kidney failure, and major bleeding-was reached in 27.0% of patients (95% CI, 23.3-31.2) within 1 year after intervention; 7.5% (95% CI, 5.5-10.2) had in-hospital complications before discharge and 19.6% (95% CI, 16.3-23.4) within 1 year after discharge. Overall mortality within 1 year after discharge was 7.3% and rates of cardiac rehospitalization 13.5%, permanent pacemaker implantation 4.2%, any stroke 1.8%, vascular-access-related complications 0.7%, life-threatening bleeding 0.7%, and kidney failure 0.4%. Composite events within 1 year after discharge were observed in 18.8% and 24.3% of patients with low risk of complications/early (<= 3 days) discharge and high risk and discharged late (>3 days) (concordant discharge), respectively. Event rate in patients with discordant discharge was 14.3% with low risk but discharged late and increased to 50.0% in patients with high risk but discharged in <= 3 days.Conclusions The FAST-TAVI risk assessment provides a tool for appropriate, risk-based discharge that was validated with the 1-year event rate after transfemoral TAVI.Registration URL: https://www.ClinicalTrials.gov; Unique identifier: NCT02404467. Show less
