Identifying sources of variability in scoliosis classification using a rule-based automated algorithm.

STUDY DESIGN: Use of a rule-based automated algorithm to determine sources of variability in radiographic classification.

OBJECTIVES: To determine whether unambiguous rules encoded in a computer program would ensure reliable classification.

SUMMARY OF BACKGROUND DATA: Reliability problems have been identified in classifications used in surgical planning for patients with thoracic idiopathic scoliosis, but the sources of unreliability are not understood.

METHODS: Objective classification methodology was tested on the King et al (1983) scheme. There were two novel components: 1) positions of the corners of vertebrae in radiographs were digitized relative to a defined axis system and used in automated evaluation of spinal shape parameters required for classification; and 2) the assignment of a classification was done with a rule-based algorithm. The algorithm was implemented after some ambiguities and absence of precise definitions in the King et al classification scheme had been resolved. The algorithm was tested with radiographs of patients having adolescent idiopathic scoliosis.

RESULTS: The automated procedure could encounter reliability problems in cases in which a lumbar curve was very close to crossing the midline, thoracic and lumbar curves were of approximately equal value, when the apex level in the thoracolumbar region was ambiguous, when a Cobb angle was close to 10 degrees, or when the flexibility index was close to unity.

CONCLUSION: Objective measurements and rule-based algorithms can eliminate some sources of interobserver and intraobserver errors in classification of spinal deformity. When classification parameters fall close to the boundaries for classification, reliability problems will persist.