The Artificial Intelligence Revolution in Stroke Care: A Decade of Scientific Evidence in Review.

BACKGROUND: The emergence of artificial intelligence (AI) has significantly influenced the diagnostic evaluation of stroke and has revolutionized acute stroke care delivery. The scientific evidence evaluating the role of AI, especially in areas of stroke treatment and rehabilitation is limited but continues to accumulate. We performed a systemic review of current scientific evidence evaluating the use of AI in stroke evaluation and care and examined the publication trends during the past decade. METHODS: A systematic search of electronic databases was conducted to identify all studies published from 2012 to 2022 that incorporated AI in any aspect of stroke care. Studies not directly relevant to stroke care in the context of AI and duplicate studies were excluded. The level of evidence and publication trends were examined. RESULTS: A total of 623 studies were examined, including 101 reviews (16.2%), 9 meta-analyses (1.4%), 140 original articles on AI methodology (22.5%), 2 case reports (0.3%), 2 case series (0.3%), 31 case-control studies (5%), 277 cohort studies (44.5%), 16 cross-sectional studies (2.6%), and 45 experimental studies (7.2%). The highest published area of AI in stroke was diagnosis (44.1%) and the lowest was rehabilitation (12%). A 10-year trend analysis revealed a significant increase in AI literature in stroke care. CONCLUSIONS: Most research on AI is in the diagnostic area of stroke care, with a recent noteworthy trend of increased research focus on stroke treatment and rehabilitation.

Predictors of occlusion, long-term outcomes, and safety in a cohort of 674 aneurysms treated with the Pipeline embolization device.

OBJECTIVE: By providing a more physiological approach to the treatment of intracranial aneurysms, the Pipeline embolization device (PED) has revolutionized the endovascular treatment of aneurysms. Although there are many flow diverters on the market, the authors report their experience with the PED, the first flow diverter to be approved by the Food and Drug Administration. They aimed to assess the efficacy and safety of PED flow diversion for the treatment of a wide range of aneurysms, as well as to look at factors affecting occlusion. METHODS: This is a retrospective study of a prospectively maintained database of patients treated with the PED between January 2011 and December 2019. Charts were reviewed for patient, aneurysm, and procedure characteristics. The primary outcomes of interest were complication rates, occlusion outcomes (O'Kelly-Marotta grading scale), and functional outcomes (modified Rankin Scale [mRS]). Secondary outcomes included predictors of incomplete occlusion at 6 and 24 months of follow-up. RESULTS: The study cohort included 581 patients with 674 aneurysms. Most aneurysms (90.5%) were in the anterior circulation and had a saccular morphology (85.6%). Additionally, 638 aneurysms (94.7%) were unruptured, whereas 36 (5.3%) were acutely ruptured. The largest mean aneurysm diameter was 8.3 ± 6.1 mm. Complications occurred at a rate of 5.5% (n = 32). The complete occlusion rate was 89.3% at 24 months' follow-up, and 94.8% of patients had a favorable neurological outcome (mRS score 0-2) at the last follow-up. On multivariate analysis, predictors of incomplete aneurysm occlusion at 6 months were hypertension (OR 1.7, p = 0.03), previous aneurysm treatment (OR 2.4, p = 0.001), and increasing aneurysm neck diameter (OR 1.2, p = 0.02), whereas a saccular morphology was protective (OR 0.5, p = 0.05). Predictors of incomplete occlusion at 24 months were increasing aneurysm neck diameter (OR 1.2, p = 0.01) and previous aneurysm treatment (OR 2.3, p = 0.01). CONCLUSIONS: The study findings are corroborated by those of previous studies and trials. The complete occlusion rate was 89.3% at 24 months' follow-up, with 94.8% of patients having favorable functional outcomes (mRS score 0-2). Aneurysm treatment before PED deployment and an increasing aneurysm neck diameter increase the risk of incomplete occlusion at 6 and 24 months.

Causes and Predictors of 30-Day Readmission in Patients With Stroke Undergoing Mechanical Thrombectomy: A Large Single-Center Experience.

BACKGROUND AND OBJECTIVES: The 30-day readmission rate has emerged as a metric of quality care and is associated with increased health care expenditure. We aim to identify the rate and causes of 30-day readmission after mechanical thrombectomy and provide the risk factors of readmission to highlight high-risk patients who may require closer care. METHODS: This is a retrospective study from a prospectively maintained database of 703 patients presenting for mechanical thrombectomy between 2017 and 2023. All patients who presented with a stroke and underwent a mechanical thrombectomy were included in this study. Patients who were deceased on discharge were excluded from this study. RESULTS: Our study comprised 703 patients, mostly female (n = 402, 57.2%) with a mean age of 70.2 years ±15.4. The most common causes of readmission were cerebrovascular events (stroke [n = 21, 36.2%], intracranial hemorrhage [n = 9, 15.5%], and transient ischemic attack [n = 1, 1.7%]).Other causes of readmission included cardiovascular events (cardiac arrest [n = 4, 6.9%] and bradycardia [n = 1, 1.7%]), infection (wound infection postcraniectomy [n = 3, 5.2%], and pneumonia [n = 1, 1.7%]). On multivariate analysis, independent predictors of 30-day readmission were history of smoking (odds ratio [OR]: 2.2, 95% CI: 1.1-4.2) P = .01), distal embolization (OR: 3.2, 95% CI: 1.1-8.7, P = .03), decompressive hemicraniectomy (OR: 9.3, 95% CI: 3.2-27.6, P < .01), and intracranial stent placement (OR: 4.6, 95% CI: 2.4-8.7) P < .01). CONCLUSION: In our study, the rate of 30-day readmission was 8.3%, and the most common cause of readmission was recurrent strokes. We identified a history of smoking, distal embolization, decompressive hemicraniectomy, and intracranial stenting as independent predictors of 30-day readmission in patients with stroke undergoing mechanical thrombectomy.