Objective:

To evaluate the reliability and agreement of automated Evans index (EI) measurement using TotalSegmentator (TS) in patients with acute subarachnoid hemorrhage (SAH) and its correlation with clinical decision-making regarding external ventricular drainage (EVD).

Approach:

Key Findings:

• TS demonstrated excellent reproducibility (ICC = 0.996, 95% CI 0.996–0.997).
• High agreement between expert readers (ICC = 0.983, 95% CI 0.978–0.988).
• Good agreement between TS and expert EI measurements (ICC = 0.76, 95% CI 0.73–0.81), improving to (ICC = 0.87, 95% CI 0.85–0.89) after excluding frontal horn hematoma.
• TS identified more positive EI > 0.30 cases than expert assessment (29% vs. 17%).
• TS-derived EI showed discrimination for EVD placement (AUC = 0.75, 95% CI 0.73–0.79), approaching expert-derived EI (AUC = 0.80, 95% CI 0.78–0.83).
• TS-derived EI remained independently associated with EVD placement (adjusted OR = 1.09, 95% CI 1.03–1.17).

Interpretation:

Automated EI measurement using TS provides a reproducible assessment of ventricular enlargement in acute SAH, with agreement with expert assessments.

Limitations:

• Threshold-sensitive disagreement occurred near EI = 0.30.
• The study was conducted at a single center, which may limit generalizability.
• Exclusion of certain cases (frontal horn hematoma) may affect the applicability of findings.

Conclusion:

Automated EI measurement using TS is a reliable tool for assessing ventricular enlargement in acute SAH and correlates with clinical decision-making regarding EVD placement.

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.