{"stable_id":"8e195367ffc0725c","slug":"houston-stroke-transfer","company":"Greater Houston primary stroke centers","workflow_name":"Automated LVO detection with parallel transfer notification","function_code":"clinical_ops","pattern_codes":["coordination_compression","exception_based_operations"],"changed_assumption":"Large-vessel occlusion at a non-thrombectomy primary stroke center has to be recognized and the receiving team activated through sequential imaging review and conventional communication before transfer can start.","evidence_strength":"verified","publication_tier":"showcase","freshness":"current","reviewed_at":"2026-08-23","updated_at":"2026-08-22","source_quality_summary":"4 peer reviewed; publication outcomes are verified.","caveat_summary":"Observational pre/post design. Post-implementation n=35. Corresponding author reports consulting fees from Viz.AI outside the submitted work. Pre-AI median DIDO was long relative to some published networks, so effect size may not travel to faster centers. Wide confidence interval. Adjustment covariates were limited. A secular-trend test found no significant DIDO decline over calendar time (coefficient −0.05, 95% CI −0.33 to 0.23), which argues against unexplained process improvement as the whole explanation but does not prove causality. EVT after transfer rose 41.2% to 62.9% univariably (p=0.033) and was not significant after adjustment (OR 2.13, 95% CI 0.88–5.13); that secondary outcome is excluded from this catalog case.","freshness_caveat":null,"workflow_summary":{"before":[{"actor":"Emergency and telestroke team","action":"Receives a code-stroke patient and obtains noncontrast CT plus CTA under standard care.","actor_type":"human"},{"actor":"Radiology / interpreting clinician","action":"Reviews CTA for large-vessel occlusion without an automated LVO alert.","actor_type":"human"},{"actor":"Stroke and transfer coordinators","action":"Notifies the care team and arranges emergent transfer to a comprehensive stroke center after LVO is recognized.","actor_type":"control"}],"hinge":"Transfer activation does not need to wait for sequential communication.","after":[{"actor":"Emergency and telestroke team","action":"Receives a code-stroke patient; NCCT and CTA are acquired under the same standard-of-care protocols.","actor_type":"human"},{"actor":"Viz.AI LVO algorithm","action":"Analyzes CTA for LVO in under five minutes on average and alerts the care-team mobile app.","actor_type":"ai"},{"actor":"Stroke clinicians","action":"Verifies the mobile PACS finding, messages the care team, and transfers eligible patients.","actor_type":"system"}],"decision_mode":"retained","decision_marker":"AI alerts in parallel; clinicians verify and govern transfer"},"before":[{"order":1,"actor":"Emergency and telestroke team","action":"Receives a code-stroke patient and obtains noncontrast CT plus CTA under standard care.","handoff_to":"Radiology / interpreting clinician","control":"Institutional stroke order sets and imaging protocols"},{"order":2,"actor":"Radiology / interpreting clinician","action":"Reviews CTA for large-vessel occlusion without an automated LVO alert.","handoff_to":"Stroke and transfer coordinators","control":"Conventional PACS interpretation"},{"order":3,"actor":"Stroke and transfer coordinators","action":"Notifies the care team and arranges emergent transfer to a comprehensive stroke center after LVO is recognized.","handoff_to":"Receiving CSC team","control":"Phone and conventional messaging; transfer eligibility judged by humans"}],"after":[{"order":1,"actor":"Emergency and telestroke team","action":"Receives a code-stroke patient; NCCT and CTA are acquired under the same standard-of-care protocols.","handoff_to":"Viz.AI LVO algorithm","control":"Automatic image transmission from all ED stroke workups"},{"order":2,"actor":"Viz.AI LVO algorithm","action":"Analyzes CTA for LVO in under five minutes on average and alerts the care-team mobile app.","handoff_to":"Stroke clinicians","control":"Published algorithm performance NPV 0.99, PPV 0.65; humans must verify imaging"},{"order":3,"actor":"Stroke clinicians","action":"Verifies the mobile PACS finding, messages the care team, and transfers eligible patients.","handoff_to":"Receiving CSC team","control":"Human confirmation of imaging and treatment eligibility; AI does not independently authorize transfer"}],"decision_rights":"Humans retain transfer and EVT-eligibility decisions. The model does not independently dispatch the patient; clinicians must confirm imaging because positive predictive value is 0.65.","exception_path":"False-positive alerts are discarded after human image review. Patients without LVO, in-hospital code strokes, and inbound transfers were outside this workflow. Nighttime evaluations at all seven sites used telestroke.","removed_work":["Waiting for sequential CTA interpretation before any care-team notification can start","Assembling the transfer team through conventional phone and pager chains as the primary activation path"],"outcomes":[{"metric":"Primary-stroke-center door-in-door-out time (univariable median)","baseline":"210 minutes (IQR 140–328.5)","result":"133 minutes (IQR 100–167); p<0.001","period":"1 January 2021 to 27 February 2022","scale":"115 LVO patients transferred from 7 Greater Houston PSCs (80 pre-AI, 35 post-AI)","attribution_caveat":"Observational pre/post design. Post-implementation n=35. Corresponding author reports consulting fees from Viz.AI outside the submitted work. Pre-AI median DIDO was long relative to some published networks, so effect size may not travel to faster centers.","evidence_label":"verified"},{"metric":"Adjusted DIDO time (multivariable linear regression)","baseline":"Pre-AI DIDO in the same cohort","result":"106-minute reduction (95% CI −165 to −48); p<0.001","period":"1 January 2021 to 27 February 2022","scale":"115 LVO patients at 7 PSCs; model adjusted only for sex and on/off hours","attribution_caveat":"Wide confidence interval. Adjustment covariates were limited. A secular-trend test found no significant DIDO decline over calendar time (coefficient −0.05, 95% CI −0.33 to 0.23), which argues against unexplained process improvement as the whole explanation but does not prove causality. EVT after transfer rose 41.2% to 62.9% univariably (p=0.033) and was not significant after adjustment (OR 2.13, 95% CI 0.88–5.13); that secondary outcome is excluded from this catalog case.","evidence_label":"verified"}],"executive_lesson":"In a hub-and-spoke transfer workflow, the scarce resource is parallel activation, not a faster read of the same image. Moving LVO detection and team notification off the sequential critical path cut DIDO by more than an hour; the downstream treatment-rate claim did not survive adjustment and should not be sold as the result.","anti_pattern":"Publishing a vendor percentage from a bundled quality-improvement program as if it were the isolated effect of the detection model, or treating a non-significant adjusted EVT-rate change as a confirmed clinical outcome.","questions_for_leaders":["Which notification still sits on the sequential critical path after the model fires?","If the secondary clinical endpoint is not significant after adjustment, what operating metric is actually the decision-relevant outcome?","How will false positives be handled when the model's positive predictive value is 0.65?"],"collections":["human-still-decides","queue-eliminated","regulated-autonomy"],"bundle_version":"1.0.0","bundle_fingerprint":"sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93","canonical_url":"https://brianletort.ai/transformations/houston-stroke-transfer"}