TY - JOUR
T1 - Rescue therapy for vasospasm following aneurysmal subarachnoid hemorrhage
T2 - a propensity score-matched analysis with machine learning
AU - SAHIT Collaboration
AU - Martini, Michael L.
AU - Neifert, Sean N.
AU - Shuman, William H.
AU - Chapman, Emily K.
AU - Schupper, Alexander J.
AU - Oermann, Eric K.
AU - Mocco, J.
AU - Todd, Michael
AU - Torner, James C.
AU - Molyneux, Andrew
AU - Mayer, Stephan
AU - Le Roux, Peter
AU - Vergouwen, Mervyn D.
AU - Rinkel, Gabriel J. E.
AU - Wong, George K. C.
AU - Kirkpatrick, Peter
AU - Quinn, Audrey
AU - Hanggi, Daniel
AU - Etminan, Nima
AU - van den Bergh, Walter M.
AU - Jaja, Blessing N. R.
AU - Cusimano, Michael
AU - Schweizer, Tom A.
AU - Suarez, Jose
AU - Fukuda, Hitoshi
AU - Yamagata, Sen
AU - Lo, Benjamin
AU - de Oliveira Manoel, Airton Leonardo
AU - Boogaarts, Hieronymus D.
AU - Macdonald, R. Loch
PY - 2022/1
Y1 - 2022/1
N2 - OBJECTIVE Rescue therapies have been recommended for patients with angiographic vasospasm (aVSP) and delayed cerebral ischemia (DCI) following subarachnoid hemorrhage (SAH). However, there is little evidence from randomized clinical trials that these therapies are safe and effective. The primary aim of this study was to apply game theory-based methods in explainable machine learning (ML) and propensity score matching to determine if rescue therapy was associated with better 3-month outcomes following post-SAH aVSP and DCI. The authors also sought to use these explainable ML methods to identify patient populations that were more likely to receive rescue therapy and factors associated with better outcomes after rescue therapy.METHODS Data for patients with aVSP or DCI after SAH were obtained from 8 clinical trials and 1 observational study in the Subarachnoid Hemorrhage International Trialists repository. Gradient boosting ML models were constructed for each patient to predict the probability of receiving rescue therapy and the 3-month Glasgow Outcome Scale (GOS) score. Favorable outcome was defined as a 3-month GOS score of 4 or 5. Shapley Additive Explanation (SNAP) values were calculated for each patient-derived model to quantify feature importance and interaction effects. Variables with high S HAP importance in predicting rescue therapy administration were used in a propensity score-matched analysis of rescue therapy and 3-month GOS scores.RESULTS The authors identified 1532 patients with aVSP or DCI. Predictive, explainable ML models revealed that aneurysm characteristics and neurological complications, but not admission neurological scores, carried the highest relative importance rankings in predicting whether rescue therapy was administered. Younger age and absence of cerebral ischemia/ infarction were invariably linked to better rescue outcomes, whereas the other important predictors of outcome varied by rescue type (interventional or noninterventional). In a propensity score-matched analysis guided by SHAP-based variable selection, rescue therapy was associated with higher odds of 3-month GOS scores of 4-5 (OR 1.63, 95% CI 1.22-2.17).CONCLUSIONS Rescue therapy may increase the odds of good outcome in patients with aVSP or DCI after SAH. Given the strong association between cerebral ischemia/infarction and poor outcome, trials focusing on preventative or therapeutic interventions in these patients may be most able to demonstrate improvements in clinical outcomes. Insights developed from these models may be helpful for improving patient selection and trial design.
AB - OBJECTIVE Rescue therapies have been recommended for patients with angiographic vasospasm (aVSP) and delayed cerebral ischemia (DCI) following subarachnoid hemorrhage (SAH). However, there is little evidence from randomized clinical trials that these therapies are safe and effective. The primary aim of this study was to apply game theory-based methods in explainable machine learning (ML) and propensity score matching to determine if rescue therapy was associated with better 3-month outcomes following post-SAH aVSP and DCI. The authors also sought to use these explainable ML methods to identify patient populations that were more likely to receive rescue therapy and factors associated with better outcomes after rescue therapy.METHODS Data for patients with aVSP or DCI after SAH were obtained from 8 clinical trials and 1 observational study in the Subarachnoid Hemorrhage International Trialists repository. Gradient boosting ML models were constructed for each patient to predict the probability of receiving rescue therapy and the 3-month Glasgow Outcome Scale (GOS) score. Favorable outcome was defined as a 3-month GOS score of 4 or 5. Shapley Additive Explanation (SNAP) values were calculated for each patient-derived model to quantify feature importance and interaction effects. Variables with high S HAP importance in predicting rescue therapy administration were used in a propensity score-matched analysis of rescue therapy and 3-month GOS scores.RESULTS The authors identified 1532 patients with aVSP or DCI. Predictive, explainable ML models revealed that aneurysm characteristics and neurological complications, but not admission neurological scores, carried the highest relative importance rankings in predicting whether rescue therapy was administered. Younger age and absence of cerebral ischemia/ infarction were invariably linked to better rescue outcomes, whereas the other important predictors of outcome varied by rescue type (interventional or noninterventional). In a propensity score-matched analysis guided by SHAP-based variable selection, rescue therapy was associated with higher odds of 3-month GOS scores of 4-5 (OR 1.63, 95% CI 1.22-2.17).CONCLUSIONS Rescue therapy may increase the odds of good outcome in patients with aVSP or DCI after SAH. Given the strong association between cerebral ischemia/infarction and poor outcome, trials focusing on preventative or therapeutic interventions in these patients may be most able to demonstrate improvements in clinical outcomes. Insights developed from these models may be helpful for improving patient selection and trial design.
KW - subarachnoid hemorrhage
KW - vasospasm
KW - delayed cerebral ischemia
KW - rescue therapy
KW - machine learning
KW - feature importance
KW - propensity score matching
KW - vascular disorders
KW - DELAYED CEREBRAL-ISCHEMIA
KW - VEHICLE-CONTROLLED TRIAL
KW - DOUBLE-BLIND
KW - TIRILAZAD MESYLATE
KW - OPEN-LABEL
U2 - 10.3171/2020.12.JNS203778
DO - 10.3171/2020.12.JNS203778
M3 - Article
SN - 0022-3085
VL - 136
SP - 134
EP - 147
JO - Journal of Neurosurgery
JF - Journal of Neurosurgery
IS - 1
ER -