Impact of an artificial intelligence-driven triage system on workflow and transfer efficiency: stratified…

AI / informaticsJournal of neurology, neurosurgery, and psychiatry· Jun 2026

Impact of an artificial intelligence-driven triage system on workflow and transfer efficiency: stratified analysis of 4548 admissions to four thrombectomy hubs receiving transfers from sixty spokes.

Mohamed F Doheim, Matthew Starr, Nirav R Bhatt … Raul G Nogueira

Prehospital & RetrievalAI / informaticsClinical practiceQ1IF 6.6

Artificial intelligence-enabled stroke triage cut door-in-door-out transfer times by 41.6 minutes

Impact of an artificial intelligence-driven triage system on workflow and transfer efficiency: stratified analysis of 4548 admissions to four thrombectomy hubs receiving transfers from sixty spokes.

Mohamed F Doheim … Raul G Nogueira

Journal of neurology, neurosurgery, and psychiatry · Jun 2026

Purpose

We aimed to evaluate the impact of implementing an artificial intelligence (artificial intelligence)-enabled acute ischaemic stroke triage system on workflow efficiency and transfer optimisation in a large academic healthcare network.

Methods

A prospectively maintained database was reviewed comparing equivalent time periods before and after artificial intelligence-enabled triage platform implementation (January 2021-December 2022).

n = 4548 admissions

Results

Artificial intelligence-enabled sites got patients out the door faster, cutting delay to transfer

MD -41.60 (95% CI -60.90 to -24.10)

null 0

-60.90

-24.10

CI excludes the null - significant

More results

A difference-in-differences analysis demonstrated that DIDO improvements were specific to artificial intelligence-enabled spokes (-27 min; 95% CI -62 to -4; p=0.029).

More results

Endovascular therapy utilisation was also significantly higher in artificial intelligence-enabled versus non-artificial intelligence spokes where artificial intelligence-enabled spokes had increased endovascular therapy rates by +17.8% (39.3% to 57.1%) compared with +1.1% in non-artificial intelligence spokes (41.3% to 42.4%, P interaction =0.006).

“

Conclusion · 1 of 3

Implementation of an artificial intelligence-enabled triage platform was associated with significant reductions in workflow times and increased endovascular therapy utilisation, with effects specific to artificial intelligence-enabled spokes rather than secular trends alone.

Conclusion · 2 of 3

The proportion of transfers who did not proceed to endovascular therapy decreased in artificial intelligence-enabled spokes, though counterfactual outcomes for non-transferred patients remain unknown.

Conclusion · 3 of 3

Clinical outcomes at discharge were unchanged.

Impact of an artificial intelligence-driven triage system on workflow and transfer efficiency: stratified analysis of 4548 admissions to four thrombectomy hubs receiving transfers from sixty spokes.

Impact of an artificial intelligence-driven triage system on workflow and transfer efficiency: stratified analysis of 4548 admissions to four thrombectomy hubs receiving transfers from sixty spokes.

Related papers