Decision tree predicts hematoma expansion in women with spontaneous ICH using CT signs

In women with spontaneous intracerebral hemorrhage (ICH), a decision tree model using midline shift, blend sign, and time to first CT predicted hematoma expansion with an AUC of 0.803 (training) and sensitivity 81.8% (test), outperforming HEP model.

• Independent predictors were midline shift (OR 1.18), time to initial CT (OR 0.71), and blend sign (OR 2.81).
• Compared with BRAIN model, the decision tree had lower AUC but higher sensitivity (81.8% vs 72.7%), which may aid early intervention.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.