Physiologic monitoring is a key to guiding severe head injury therapy in the neurological intensive care unit (ICU), of which intracranial pressure (ICP) plays a critical role. Currently, decision-making with respect to escalating therapy in the stepwise protocol for refractory raised ICP is made by interpreting absolute values of the physiologic parameters coupled with the doctor clinician knowledge and experience. In this paper, we proposed a fractal dimension-based method for processing and quantification of time-series ICP data for neurological monitoring to predict the transition from maximal medical therapy to decompressive craniectomy. The fractal analysis results in a quantitative measure, known as a fractal dimension (FD), describing the self-similar patterns observed in time-series data. In this paper, we proposed fractal based method to analyse ICP data to predict changes in the patient state. We processed ICP data of 9 patients before and after decompression with well known Box-counting and Higuchi algorithms. Our results suggest that FD values could be used as a valuable additional parameter to indicate the need for surgical decompression. The FD based method could potentially be implemented as a software tool in intensive care units.