Bayesian instrument for spinal disability: A predictive model for aircrew flying fitness

Objectives Spinal disabilities are a common problem in aircrew with or without obvious pathology in the spine. Department of Human Engineering, Institute of Aerospace Medicine (IAM) evaluates Indian air force (IAF) aircrew with spinal disabilities before they can fly again. This study aimed to develop a Bayesian Instrument for Spinal disability (BIS) based on clinical, radiological, and functional evaluations of aircrew at IAM. This research aims to develop a composite model of spinal disability assessment applicable to aircrew of different streams and to assess key factors that determine flying fitness. The study also aims to develop a computerized version of the scale that can be used in the field before referral to IAM. Material and Methods 120 aircrews reporting spinal-related disabilities to the Department of Human Engineering, IAM participated in the study. 14 predictors that determine the return to flying in an aircrew were incorporated in a Bayesian Belief Network using an Augmented Naïve Bayes algorithm to develop the BIS. The predictive characteristics of the final model were independently tested on an incomplete data set of 29 aircrews. Results Validation of the spinal disability scale was carried out using the Leave One Out method. The accuracy was found to be 0.97, sensitivity was 0.97, and specificity was 0.96. The spinal disability scale was also tested on partial data (11 predictors only) from 29 aircrews. It has a sensitivity of 0.94 and a specificity of 0.75 even when using just 11 predictors that are available before reporting to IAM. Conclusion The composite predictive model indicates the relative importance of ongoing evaluations and predicts focus areas affecting aircrew’s return to flying. It also functions as a decision assist tool for the Medical Officer in the field before referral to IAM for evaluation.