Evaluation of an artificial intelligence model for identification of obstructive hydrocephalus on computed tomography of the head
Introduction
Obstructive hydrocephalus is a critical radiographic finding requiring emergent treatment. Its identification on head computed tomography (CT) by an artificial intelligence (AI) model could facilitate sooner life-saving interventions, although there are common co-occurring findings including intracranial hemorrhage that can confound this interpretation. This study assessed the accuracy of an AI model (Annalise Enterprise CTB) at identifying obstructive hydrocephalus including in the presence or absence of other findings.
Methods
This retrospective cohort included 177 thin (≤ 1.5mm) series and 194 thick (> 1.5 and ≤ 5mm) series from 200 non-contrast head CT cases. These cases were obtained from patients aged ≥ 18 years at 5 hospitals in the United States. Each case was interpreted independently by up to three neuroradiologists. Each series was then interpreted by the AI model.
Results
The AI model performed with area under the curve 0.988 (95% confidence interval (CI): 0.971 to 0.998) on thin series and 0.986 (95% CI: 0.969 to 0.997) on thick series. These results were broadly maintained in subgroups for the presence or absence of intracranial hemorrhage, parenchymal abnormality and ventricular drain, and across demographic and scanner manufacturer subgroups.
Conclusions
The AI model accurately identified obstructive hydrocephalus in this dataset. Its performance in subgroup analyses reflected its robustness.
Disclaimer
Harrison.ai Radiology Solutions were previously marketed as Annalise.ai solutions.
