Can CTA-Based Machine Learning Identify Patients for Whom Successful Endovascular Stroke Therapy Is Insufficient?

Despite advances in endovascular stroke therapy (EST) devices and techniques, many patients are left with substantial disability, even if the final infarct volumes (FIVs) remain small. Here, we evaluate the performance of a machine learning (ML) approach by using pretreatment CTA to identify this cohort of patients that may benefit from additional interventions.

We identified consecutive subjects with large vessel occlusion (LVO) acute ischemic stroke (AIS) who underwent EST with successful reperfusion in a multicenter prospective registry cohort. We included only subjects with FIV < 30 mL and recorded 90-day outcome (mRS). A deep learning model was pretrained and then fine-tuned to predict 90-day mRS 0-2 by using pretreatment CTA images (DeepsymNet-v3 model pretrained on radiology reports and fine-tuned on detection of unexpected clinical outcomes using brain CTA images [DSN-CTA] model). The primary outcome was the predictive performance of the DSN-CTA model compared with a logistic regression model with clinical variables, measured by the area under the receiver operating characteristic curve (AUROC).

The DSN-CTA model was pretrained on 1542 subjects and then fine-tuned and cross-validated with 48 subjects, all of whom underwent EST with TICI 2b-3 reperfusion. Of this cohort, 56.2% of subjects had 90-day mRS 3-6 despite successful EST and FIV < 30 mL. The DSN-CTA model showed significantly better performance than a model with clinical variables alone when predicting good 90-day mRS (AUROC 0.81 versus 0.492; P = .006).

The CTA-based ML model was able to more reliably predict unexpected poor functional outcome after successful EST and small FIV for patients with LVO AIS compared with standard clinical variables. ML models may identify a priori patients in whom EST-based LVO reperfusion alone is insufficient to improve clinical outcomes.