RESUMO
BACKGROUND: Machine learning algorithms depend on accurate and representative datasets for training in order to become valuable clinical tools that are widely generalizable to a varied population. We aim to conduct a review of machine learning uses in stroke literature to assess the geographic distribution of datasets and patient cohorts used to train these models and compare them to stroke distribution to evaluate for disparities. AIMS: 582 studies were identified on initial searching of the PubMed database. Of these studies, 106 full texts were assessed after title and abstract screening which resulted in 489 papers excluded. Of these 106 studies, 79 were excluded due to using cohorts from outside the United States or being review articles or editorials. 27 studies were thus included in this analysis. SUMMARY OF REVIEW: Of the 27 studies included, 7 (25.9%) used patient data from California, 6 (22.2%) were multicenter, 3 (11.1%) were in Massachusetts, 2 (7.4%) each in Illinois, Missouri, and New York, and 1 (3.7%) each from South Carolina, Washington, West Virginia, and Wisconsin. 1 (3.7%) study used data from Utah and Texas. These were qualitatively compared to a CDC study showing the highest distribution of stroke in Mississippi (4.3%) followed by Oklahoma (3.4%), Washington D.C. (3.4%), Louisiana (3.3%), and Alabama (3.2%) while the prevalence in California was 2.6%. CONCLUSIONS: It is clear that a strong disconnect exists between the datasets and patient cohorts used in training machine learning algorithms in clinical research and the stroke distribution in which clinical tools using these algorithms will be implemented. In order to ensure a lack of bias and increase generalizability and accuracy in future machine learning studies, datasets using a varied patient population that reflects the unequal distribution of stroke risk factors would greatly benefit the usability of these tools and ensure accuracy on a nationwide scale.
Assuntos
Mineração de Dados , Aprendizado de Máquina , Acidente Vascular Cerebral/epidemiologia , Viés , Confiabilidade dos Dados , Bases de Dados Factuais , Humanos , Prevalência , Prognóstico , Acidente Vascular Cerebral/diagnóstico , Acidente Vascular Cerebral/terapia , Estados Unidos/epidemiologiaRESUMO
Background and Purpose- Radial artery catheterization is an alternate route of access that has started to gain more widespread use for neuroendovascular procedures, and there have been few studies that describe its safety and efficacy. We present our institution's experience in performing neuroendovascular interventions via a transradial approach, with excellent clinical outcomes and patient satisfaction measures. Methods- We conducted a retrospective analysis and identified 223 patients who underwent 233 consecutive neuroendovascular interventions via radial artery access at our institution. The incidence of perioperative and postprocedural complications was investigated. We identified a subset of 98 patients who have undergone both transradial and transfemoral cerebral angiograms and compared clinical outcomes and patient satisfaction measures between the 2 groups. Results- The overall incidence of complications was low across all procedures performed via transradial access. Peri-procedurally, only 2 patients had symptomatic radial artery spasm, and there were no instances of iatrogenic complications (vessel dissection, stroke, and hemorrhage). In 10 cases (4.3%), the intended procedure could not be completed via a transradial approach, and, thus, femoral artery access had to be pursued instead. Ten patients complained of minor postprocedural complications, although none required therapeutic intervention. The mean procedure time was shorter for diagnostic angiograms performed via transradial versus transfemoral access (18.8±15.8 versus 39.5±31.1 minutes; P=0.025). Patients overall reported shorter recovery times with transradial access, and the majority of patients (94%) would elect to have subsequent procedures performed via this route. Conclusions- Radial artery catheterization is a safe and durable alternative to perform a wide range of neuroendovascular procedures, with a low rate of complications. On the whole, patients prefer transradial compared with transfemoral access.