Aiding diagnosis of normal pressure hydrocephalus with enhanced gait feature separability

Abstract

Normal Pressure Hydrocephalus (NPH) is a neurological condition that challenges differential diagnosis, as the symptoms -- cognitive and gait impairment and urinary incontinence -- are similar to those of many aging disorders, including Alzheimer's disease and other forms of dementia. Since NPH is caused by abnormal accumulation of cerebrospinal fluid (CSF) around the brain, a high volume lumbar puncture (HVLP) to remove excess fluid is used as the stimulus for a suspected NPH patient, and a diagnosis is made based on the observed cognitive and functional response. Gait features have long been used as functional indicators in the pre- and post-HVLP assessment. However, these assessments are limited to visual observation in the clinic. Therefore, only simple gait features such as walking speed (based on time to walk 10m) and average stride length/time (based on the number of steps to walk 10m) are used. However, these features provide limited separability in the NPH diagnosis. This paper presents methods for enhanced diagnostic separability using additional gait features extracted from an inertial body sensor network (BSN), including stride time variability, double support time, and stability. A pilot study on six HVLP patients -- four of whom were ultimately diagnosed with NPH -- revealed that gait stability assessed by Lyapunov exponent provides better separability and can enhance the differential diagnosis. In addition, these results suggest that additional testing can be performed continuously outside of the clinic to account for patients' variable HVLP response times.