Failed back surgery syndrome is a clinical pathology in which patients present with a set of
symptoms encountered after they have had one or more technically, anatomically successful surgical
procedures on the lumbar spine for correcting their disc related pathology. The Principal
symptom of this pathology is a persistent recurrent pain mainly in the region of the lower back
and legs that is generally resistant to physiotherapy and pharmacological treatment. An alternative
proposed treatement to FBSS patients is Spinal Cord Stimulation which is becoming a widely used
treatement for a number of pain conditions, and it is frequently considered as a last resort pain
management option when conservative or less invasive techniques have proven ineffective. While
research on SCS is growing, the SCS success rates are at best modest. It is clear that substantial
variation exists in the degree of benefit obtained from SCS, and the procedure does not come without
risks; thus focused patient selection is becoming very important. The current method used in
forcasting who may benefit most from SCS consists of a 5 to 10 days trial period which requires
an invasive surgical procedure that may lead to complications such as electrode migration, dural
puncture during electrode placement and/or infection. In order to propose an alternative to
this trial procedure, we used available data to develop and test eight machine learning binary 
classification algorithms which can be used as screening tools of SCS efficacy.