Feature Selection for Better Identification of Subtypes of Guillain-Barré Syndrome

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td align="left">Feature</td><td align="center">Meaning</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td align="left">v105</td><td align="center">Amplitude of left ulnar motor nerve</td></tr><tr><td align="left">v106*</td><td align="center">Area under the curve of left ulnar motor nerve</td></tr><tr><td align="left">v116</td><td align="center">Amplitude of right ulnar motor nerve</td></tr><tr><td align="left">v172*</td><td align="center">Amplitude of left median sensory nerve</td></tr><tr><td align="left">v177*</td><td align="center">Amplitude of right median sensory nerve</td></tr><tr><td align="left">v182*</td><td align="center">Amplitude of left ulnar sensory nerve</td></tr><tr><td align="left">v187</td><td align="center">Amplitude of right ulnar sensory nerve</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

List of variables with the highest purity (0.7984) selected by information gain and symmetrical uncertainty.

Computational and Mathematical Methods in Medicine

tab3

Table 3

Table 3: Feature Selection for Better Identification of Subtypes of Guillain-Barré Syndrome 