Externally validated machine learning models for prediction of treatment selection and clinical outcomes in posterior communicating artery aneurysms
Abstract
Posterior communicating artery (PCOM) aneurysms account for approximately 25% of intracranial aneurysms and present clinical challenges regarding optimal treatment selection. This study developed and validated machine learning models to predict treatment modality, complications, and functional outcomes in PCOM aneurysm management using a comprehensive institutional database of 75 patients treated between 2002 and 2023. Five machine learning algorithms—Random Forest, Support Vector Machine, Logistic Regression, Decision Tree, and XGBoost—were systematically compared across 7 outcome variables: treatment type (open vs. endovascular), specific open surgical treatment, specific endovascular treatment, intraoperative rupture, complications, angiographic obliteration, and discharge modified Rankin Scale score. Models were developed using preoperative patient-specific (age, sex, family history) and aneurysm-specific (size, presentation, morphology, location) parameters, with rigorous preprocessing that included class-balancing strategies, feature engineering, and regularization to minimize overfitting. Cross-validation performance demonstrated high accuracy for treatment prediction (78.7% Random Forest), complications (94.7% Random Forest; however, sensitivity of 0% indicates that this accuracy should not be interpreted as clinically useful event detection), intraoperative rupture (92.0% Random Forest), and angiographic obliteration (87.3% Random Forest). External validation on an independent cohort from the University of Louisville (n=20–28; n=20 most complete cases for the primary external cohort, with up to n=28 for selected endpoints with available labels) revealed variable generalizability: treatment prediction maintained 78.1% accuracy, and complication prediction showed reduced external performance (70.3%), highlighting institution-specific factors. Comprehensive sensitivity analyses demonstrated that class balancing significantly improved minority class recall (0.0% → 52.2%–86.3%) for rare outcomes. Feature importance analyses identified age, aneurysm size, admission modified Rankin Scale score, and Hunt-Hess grade as the most influential predictors across multiple outcomes. This study represents the first externally validated, multioutcome machine learning framework for PCOM aneurysm management, providing quantitative risk estimates and evidence-based decision support for treatment selection and outcome prediction.
Related
- Lesion penetration predicts tuberculosis treatment shortening through a validated translational tool to de-risk development
- The dynamics of arterial pressure itself predict intraoperative hypotension beyond its current value: an interpretable additive model validated in 3,069 external patients under a selection-bias-resistant protocol
- Prenatal genomics and autism: detectable susceptibility without validated individual-level prediction
- AI-Based Delirium Risk Prediction Compared With the Validated 4AT-Score Screening Tool in Patients With Trauma: Prospective Cohort Study.
- Survival and treatment selection in NUT carcinoma: a population-based study and propensity score-matched comparison with poorly differentiated head and neck squamous cell carcinoma
BibTeX
@article{sanker2026externally,
title = {{Externally validated machine learning models for prediction of treatment selection and clinical outcomes in posterior communicating artery aneurysms}},
author = {Vivek Sanker and Ethan Register and Adam T. Eberle and Sania Javed and Brian W. Paul and Christopher Chang and Kate N. Jensen and Rahim Abo Kasem and Mustafa T. Almosawi and Lea Scherschinski and Joshua S. Catapano and Arnau Benet and Redi Rahmani and Michael T. Lawton},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-70508-3},
url = {https://www.nature.com/articles/s41598-026-70508-3},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Externally validated machine learning models for prediction of treatment selection and clinical outcomes in posterior communicating artery aneurysms
AU - Vivek Sanker
AU - Ethan Register
AU - Adam T. Eberle
AU - Sania Javed
AU - Brian W. Paul
AU - Christopher Chang
AU - Kate N. Jensen
AU - Rahim Abo Kasem
AU - Mustafa T. Almosawi
AU - Lea Scherschinski
AU - Joshua S. Catapano
AU - Arnau Benet
AU - Redi Rahmani
AU - Michael T. Lawton
PY - 2026
DA - 2026/10/16
JO - Scientific Reports
DO - 10.1038/s41598-026-70508-3
UR - https://www.nature.com/articles/s41598-026-70508-3
AB - Posterior communicating artery (PCOM) aneurysms account for approximately 25% of intracranial aneurysms and present clinical challenges regarding optimal treatment selection. This study developed and validated machine learning models to predict treatment modality, complications, and functional outcomes in PCOM aneurysm management using a comprehensive institutional database of 75 patients treated between 2002 and 2023. Five machine learning algorithms—Random Forest, Support Vector Machine, Logistic Regression, Decision Tree, and XGBoost—were systematically compared across 7 outcome variables: treatment type (open vs. endovascular), specific open surgical treatment, specific endovascular treatment, intraoperative rupture, complications, angiographic obliteration, and discharge modified Rankin Scale score. Models were developed using preoperative patient-specific (age, sex, family history) and aneurysm-specific (size, presentation, morphology, location) parameters, with rigorous preprocessing that included class-balancing strategies, feature engineering, and regularization to minimize overfitting. Cross-validation performance demonstrated high accuracy for treatment prediction (78.7% Random Forest), complications (94.7% Random Forest; however, sensitivity of 0% indicates that this accuracy should not be interpreted as clinically useful event detection), intraoperative rupture (92.0% Random Forest), and angiographic obliteration (87.3% Random Forest). External validation on an independent cohort from the University of Louisville (n=20–28; n=20 most complete cases for the primary external cohort, with up to n=28 for selected endpoints with available labels) revealed variable generalizability: treatment prediction maintained 78.1% accuracy, and complication prediction showed reduced external performance (70.3%), highlighting institution-specific factors. Comprehensive sensitivity analyses demonstrated that class balancing significantly improved minority class recall (0.0% → 52.2%–86.3%) for rare outcomes. Feature importance analyses identified age, aneurysm size, admission modified Rankin Scale score, and Hunt-Hess grade as the most influential predictors across multiple outcomes. This study represents the first externally validated, multioutcome machine learning framework for PCOM aneurysm management, providing quantitative risk estimates and evidence-based decision support for treatment selection and outcome prediction.
SN - 2045-2322
ER -