Analysis of 20,000 Patients with Acute Ischemic Stroke treated with Endovascular Thrombectomy using Machine Learning Clustering Algorithm
Rafay Khan1, Adam Kiss1, Aryan Malhotra1, Mateusz Faltyn2, Fawaz Al-Mufti3
1New York Medical College, 2Trilemma Capital, 3Westchester Medical Center
Objective:
This study employs machine learning-based clustering algorithms to identify unique clinical patient profiles with Acute Ischemic Stroke (AIS) treated with Endovascular Thrombectomy (EVT), providing insights into the stratification of risk factors and treatment outcomes.
Background:
Not Applicable
Design/Methods:
The 2015-2019 National Inpatient Sample was queried using ICD-10 PCS/CM coding to identify patients with AIS who underwent EVT. A machine learning clustering analysis evaluated the population based on 50 comorbidities, complications and clinical covariates. Optimal number of clusters was determined using the Davies-Bouldin Index and Calinski-Harabasz Index. Between-cluster multivariate logistic regression analysis was performed to assess risk of mortality and non-routine discharge. Kruskal-Wallis H-Testing was performed to assess variance in length-of-stay between clusters. Statistical analysis was performed using Python.
Results:
20,817 patients were included and categorized into four clusters, ranging from 354 to 17,142 patients. Mortality ranged from 8.21% in Cluster 1 to 28.78% in Cluster 4. Clusters 2-4 each displayed significantly higher rates of mortality [AOR 1.99-6.53, p<0.001] relative to Cluster 1. Individual cluster profiles are visualized in a heatmap. Cluster 1 had the greatest prevalence of hypertension and hyperlipidemia among groups. Cluster 4 had the greatest prevalence of hypertension and arrhythmia.
Risk of non-routine discharge was highest in Cluster 4 [OR 6.14, p<0.001] when compared to Cluster 1. Kruskall-Wallis H-testing and post-hoc pairwise comparison of length-of-stay variance showed significant (p<0.001) differences between all clusters except 3 and 4 with the greatest test statistics occurring when comparing group 1 to all other groups.
Conclusions:
Clustering analysis of patients identified 4 distinct subgroups within the AIS and EVT sample. This data-based approach enables a nuanced understanding of comorbidity interactions, enhancing available tools for personalized clinical decision-making.
Disclaimer: Abstracts were not reviewed by Neurology® and do not reflect the views of Neurology® editors or staff.