Noninvasive intracranial hypertension detection utilizing semisupervised learning.

Intracranial pressure (ICP) monitoring is an established clinical practice in managing patients with risk of acute ICP elevation although the clinically accepted way of measuring ICP remains invasive. However, the invasive nature of ICP measurement obviates its application in many clinical circumstances such as diagnosis of idiopathic intracranial hypertension (IH). We propose a noninvasive diagnostic tool for IH based on the morphological analysis of cerebral blood flow velocity waveforms. We mainly compare two types of IH detection methods: one based on the traditional supervised learning approach and the other based on the semisupervised learning approach. Our simulation results demonstrate that the predictive accuracy (area under the curve) of the semisupervised IH detection method can be as high as 92% while that of the supervised IH detection method is only around 82%. It should be noted that the predictive accuracy of the pulsatility index (PI)-based IH detection method is as low as 59%. Although the predictive accuracy is a widely used accuracy measurement, it does not consider clinical consequences of necessary and unnecessary treatments. For this reason, we have adopted the decision curve analysis to address this issue. The decision curve analysis results show that the semisupervised IH detection method is not only more accurate, but also clinically more useful than the supervised IH detection method or the PI-based IH detection method.