Chukwudelunzu, Felix E.

Background: Artificial intelligence (AI) stroke imaging software is becoming mainstay in many hub-and-spoke hospitals. Brainomix 360 Stroke software is the market leader in Europe focused on leveraging simple imaging (non-contrast computerized topography (NCCT) and CT angiography (CTA)) and has recently been FDA-cleared for use in the USA. We evaluated the implementation of Brainomix 360 AI Stroke software in the 17 spoke, multi-state Mayo Clinic Health System (MCHS) telestroke network. Methods: This prospective study compared decision and treatment times before and after Brainomix AI implementation, as well as clinician feedback and simulated decision making to better understand any changes seen. Patients were included if they underwent telestroke evaluation at an MCHS emergency department within 90 days of implementation (2/9/2024-8/8/2024), and excluded if they were already admitted to the hospital or if video evaluation was not performed. Data collection included demographics, clinical decisions and treatment times. Qualitative surveys were conducted at baseline and evaluation end, as well as simulated decision making in 20 de-identified cases randomized to with/without AI through an online portal. Results: A total of 907 patients were included (444 pre- and 463 post-implementation, 287 (32%) with ischemic stroke final diagnosis). Median NIHSS was 2. IVT was recommended in 20.3% (27/148 ischemic stroke patients) pre- and 25.9% (36/139) post-implementation. EVT was recommended in 16.2% (24/148) pre and 14.4% (20/139) post. AI use was associated with trends of faster telestroke activation to IVT decision (36 vs 32 mins, p=0.6), IVT administration (47 vs 40 minutes, p=0.6), and EVT decision (36 vs 33 minutes, p=0.5). In the simulation, imaging interpretation was significantly faster when randomized to AI use (3.4 vs 2.1 mins, p<0.001) and associated with improved physician confidence (62 vs 88%, p=0.004). Qualitative feedback from 14/24 neurologists showed the greatest perceived value was improved confidence of treatment decisions (43%) and faster triaging (36%). Most value was gained from e-ASPECTS (NCCT) and LVO modules. Conclusion: This service evaluation highlighted the opportunity to improve efficiency of decision making even in the setting of a well-developed telestroke system. The impact was underpinned by the improved speed and confidence of imaging interpretation reflected in an offline simulation and qualitative feedback.

Background and purpose: In-hospital stroke-onset assessment and management present numerous challenges, especially in community hospitals. Comprehensive analysis of key stroke care metrics in community-based primary stroke centers is under-studied. Methods: Medical records were reviewed for patients admitted to a community hospital for non-cerebrovascular indications and for whom a stroke alert was activated between 2013 and 2019. Demographic, clinical, radiologic and laboratory information were collected for each incident stroke. Descriptive statistical analysis was employed. When applicable, Kruskal-Wallis and Chi-Square tests were used to compare median values and categorical data between pre-specified groups. Statistical significance was set at alpha = 0.05. Results: There were 192 patients with in-hospital stroke-alert activation; mean age (SD) was 71.0 years (15.0), 49.5% female. 51.6% (99/192) had in-hospital ischemic and hemorrhagic stroke. The most frequent mechanism of stroke was cardioembolism. Upon stroke activation, 45.8% had ischemic stroke while 40.1% had stroke mimics. Stroke team response time from activation was 26 minutes for all in-hospital activations. Intravenous thrombolysis was utilized in 8% of those with ischemic stroke; 3.4% were transferred for consideration of endovascular thrombectomy. In-hospital mortality was 17.7%, and the proportion of patients discharged to home was 34.4% for all activations. Conclusion: The in-hospital stroke mortality was high, and the proportions of patients who either received or were considered for acute intervention were low. Quality improvement targeting increased use of acute stroke intervention in eligible patients and reducing hospital mortality in this patient cohort is needed.

Background and Purpose —Case-control, cohort, and twin studies support a genetic contribution to ischemic stroke risk. Sibling pair linkage methods require identification of concordant or discordant siblings or both. We designed and tested a structured telephone interview to verify the stroke-free phenotype. Methods —A coordinator unaware of medical record data used an 8-item questionnaire to conduct a structured telephone interview of 70 outpatients aged >60 years. The questionnaire inquired about the sudden onset of deficits in strength, sensation, vision, and language. A subject was defined as stroke free by interview if responses to all items on the questionnaire were negative. Results of the telephone interview were compared with data obtained from a systematic medical record review (benchmark). Results —Interview time was 5 minutes or less for all subjects. All subjects who began the interview completed it. Records were reviewed in all subjects. Medical record review detected ischemic stroke or transient ischemic attack (TIA), or both, in 5 patients (7%). There were no significant differences in sex distribution or risk factor rates in patients who were designated stroke free or not stroke free by interview. Having 1 or more positive items on the questionnaire was significantly associated with finding stroke ( P <0.001), TIA ( P <0.001), or either stroke or TIA ( P <0.001), on medical record review. The telephone interview had a sensitivity of 1.0 (95% CI 0.48 to 1.0), specificity of 0.86 (95% CI 0.75 to 0.93), positive predictive value of 0.36 (95% CI 0.13 to 0.65), and negative predictive value of 1.0 (95% CI 0.94 to 1.0). Conclusions —Our instrument can identify the stroke-free individual with a high degree of confidence in a very efficient manner. It may be particularly suited for centralized verification of stroke discordancy in multicentered sib-pair genetic studies.