Shorter Time to Assessment and Anticoagulation with Decreased Mortality in Patients with Pulmonary Embolism Following Implementation of Artificial Intelligence Software

Pulmonary embolism (PE) is a serious and potentially life-threatening condition. A streamlined PE workflow with timely assessment and initiation of treatment may improve a patient’s chance of survival. Artificial intelligence (AI) has been increasingly used in healthcare to improve clinical efficiency. In October 2022, our institution implemented an AI-powered parallel workflow tool designed to automatically detect and triage patients with suspected PE. The aim of this study was to evaluate the clinical impact of AI software on time to assessment, time to anticoagulation, and patient outcomes at our institution.

Methods:

A review of patients diagnosed with PE between January 2017 and July 2023 (N=158) was performed.  Demographics and risk factors were noted (Table I). Retrospectively collected data on PE patients prior to AI implementation (pre-AI group) was compared against that of PE patients following AI implementation (post-AI group). Collected metrics included scan-to-assessment time, scan-to-alert time (used as a surrogate for scan-to-assessment time following AI implementation assuming best practice), time of anticoagulant administration, Pulmonary Embolism Response Team (PERT) activations, and in-hospital mortalities.   

Results:

Scan-to-alert time in the post-AI group (n=45; M=5.47; SD=2.76) was significantly faster than scan-to-assessment time in the pre-AI group (n=113; M=318.42; SD=339.99); t(156)=6.163, p< .001. Anticoagulants were administered significantly faster for post-AI cases with PERT activation (n=12; M=83.17; SD=61.32) compared to cases without PERT activation (n=24; M=164.96; SD=82.88); t(34)=-3.021, p=.005. In-hospital mortalities decreased from 8.4% (pre-AI) to 2.2% (post-AI). All mortalities occurred in cases without PERT activation. Results are shown in Table II.

Conclusions:

Adoption of AI into our workflow was associated with faster time to assessment of PE patients. With an average AI alert time of under 6 minutes, it optimizes standard of care by promoting quicker triage. The combined benefit of AI and PERT activation was highlighted by faster anticoagulation administration and decreased mortality in our sample. These findings suggest a link between earlier anticoagulant administration and reduced risk of mortality. Further research is needed to determine if there is a causal relationship. This study provides evidentiary support of the impact of AI in expediting clinical workflow, leading to earlier patient assessment, treatment, and improved outcomes.