Anticoagulation Treatment Response Among Phenotypic ESUS Clusters: Evidence From CASPR

ABSTRACT Objective To evaluate treatment effect heterogeneity across phenotypic clusters of patients with cryptogenic embolic stroke using causal inference methods. Methods From a retrospective, multicenter cohort of patients with cryptogenic embolic stroke, we estimated the treatment effect of anticoagulation versus antiplatelet therapy in patients with ESUS in two ways: (1) Partitioning Around Medoids and (2) causal survival forest modeling. We assessed cluster‐level associations with time to primary outcome (recurrent stroke, major bleeding, or death) using Kaplan–Meier survival analysis to assess cluster differences. We then extracted SHapley Additive exPlanations (SHAP) feature importances from the causal forest model to identify candidate effect modifiers from the causal forest. Results Among 1869 patients with ESUS, three phenotypically distinct clusters were extracted with significant differences in event‐free survival across clusters (log‐rank p < 0.0001). There was no significant population‐level benefit of anticoagulation over antiplatelet therapy ( p = 0.23). SHAP feature importance analysis identified several candidate effect modifiers; however, only higher LVEF ( β = −327, 95% CI: −580 to −74, p = 0.011) and cancer history ( β = −226, 95% CI: −441 to −11, p = 0.039) were independent predictors of response to antiplatelet over anticoagulation using best linear projections. Phenotypic cluster assignment did not significantly predict treatment effect heterogeneity. Interpretation Three distinct phenotypic clusters of cryptogenic stroke patients emerged with a differential risk of the composite outcome, but they did not predict responsiveness to anticoagulation. LVEF and cancer history, however, showed differential outcomes across antithrombotic strategies. These findings demonstrate the potential of causal inference methods for identifying effect heterogeneity and individualizing treatment strategies.

Authors

Institutions

Publication Details

Journal
Annals of Clinical and Translational Neurology
Published
2026-10-06
DOI
https://doi.org/10.1002/acn3.70542
Primary Topic
Acute Ischemic Stroke Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Anticoagulation Treatment Response Among Phenotypic ESUS Clusters: Evidence From CASPR

Wayneho Kam, Matthew M. Smith, Hamid Ali, Dalia Chahien et al.
Annals of Clinical and Translational Neurology
Acute Ischemic Stroke Management
article

Anticoagulation Treatment Response Among Phenotypic ESUS Clusters: Evidence From CASPR

Wayneho Kam, Matthew M. Smith, Hamid Ali, Dalia Chahien, Mudassir Farooqui, Alicia M. Zha, Emiliya Melkumova, Setareh Salehi Omran, Frank Garrett Conyers, Franziska Herpich, Simona Nedelcu, David S. Liebeskind, Shadi R. Yaghi, Deborah L.G. Kerrigan, Balaji Krishnaiah, Diana Rojas-Soto, Patrick A. Glover, Mahan Shahrivari, Mehdi Abbasi, Mary Penckofer, Sean L. Thompson, Hassan Aboul Nour, Siddharth Sehgal, Dinesh V. Jillella, Yasmin Tarek Ali Abdel Aziz, James Ernest Siegler, Narendra Kala, Christina M. Lineback, Collin J. Culbertson, Fadi B. Nahab, Patrick Ellsworth, Sami Al Kasab, Vivek G. Patel, Kelsey Eklund, Eesha Singh, Elena Badillo Goicoechea, Marissa D’Souza, Guillermo Linares, James R. Brorson, Farid Khasiyev, Anna Bowman, Jesse M. Thon, Aaron Rothstein, Shani Peter, Russell J. Van Coevering, Oana M. Dumitrascu, Wenzheng Yu, Ahmad Abu Qdais, Jean-Philippe Auguste Daniel, Muhammad Alvi, Thanh N. Nguyen, Richa Sharma, Lucia Chen, Fawad Talat
article en

Abstract

ABSTRACT Objective To evaluate treatment effect heterogeneity across phenotypic clusters of patients with cryptogenic embolic stroke using causal inference methods. Methods From a retrospective, multicenter cohort of patients with cryptogenic embolic stroke, we estimated the treatment effect of anticoagulation versus antiplatelet therapy in patients with ESUS in two ways: (1) Partitioning Around Medoids and (2) causal survival forest modeling. We assessed cluster‐level associations with time to primary outcome (recurrent stroke, major bleeding, or death) using Kaplan–Meier survival analysis to assess cluster differences. We then extracted SHapley Additive exPlanations (SHAP) feature importances from the causal forest model to identify candidate effect modifiers from the causal forest. Results Among 1869 patients with ESUS, three phenotypically distinct clusters were extracted with significant differences in event‐free survival across clusters (log‐rank p < 0.0001). There was no significant population‐level benefit of anticoagulation over antiplatelet therapy ( p = 0.23). SHAP feature importance analysis identified several candidate effect modifiers; however, only higher LVEF ( β = −327, 95% CI: −580 to −74, p = 0.011) and cancer history ( β = −226, 95% CI: −441 to −11, p = 0.039) were independent predictors of response to antiplatelet over anticoagulation using best linear projections. Phenotypic cluster assignment did not significantly predict treatment effect heterogeneity. Interpretation Three distinct phenotypic clusters of cryptogenic stroke patients emerged with a differential risk of the composite outcome, but they did not predict responsiveness to anticoagulation. LVEF and cancer history, however, showed differential outcomes across antithrombotic strategies. These findings demonstrate the potential of causal inference methods for identifying effect heterogeneity and individualizing treatment strategies.

Annals of Clinical and Translational Neurology
West Virginia University (US), Brigham and Women's Hospital (US), Sentara Norfolk General Hospital (US), Boston Medical Center (US), Lahey Hospital and Medical Center (US), Tufts Medical Center (US), University of Minnesota (US), Trinity Health (US), Grady Memorial Hospital (US), Yale New Haven Hospital (US), Mayo Clinic (US), Emory University (US), Medical University of South Carolina (US), University of Tennessee Health Science Center (US), University of California, Los Angeles (US), Brown University (US), University of Michigan (US), Hospital of the University of Pennsylvania (US), Cooper University Hospital (US), Saint Louis University Hospital (US), University of Iowa Hospitals and Clinics (US), The Ohio State University Wexner Medical Center (US), University of Chicago (US), Augusta University Health (US), Christiana Hospital (US), Dartmouth Psychiatric Research Center (US), Mayo Clinic in Arizona (US), Duke Medical Center (US), Duke University Hospital (US), Jersey Shore University Medical Center (US), University of Houston (US), University of Colorado Anschutz Medical Campus (US), The Ohio State University (US), University of Cincinnati (US), University of Pennsylvania (US), Vanderbilt University Medical Center (US), The University of Texas Health Science Center at Houston (US)
Openalex Percentile: Top 11%
Acute Ischemic Stroke Management
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.