The use of a neural network to detect upper airway obstruction caused by goiter.

Abstract

Goiter is a common condition and can cause upper airway obstruction (UAO), which may be difficult to detect. We have studied maximal expiratory and inspiratory flow volume loops using a neural network to see if this offers a better way to identify patients with UAO. The flow-volume loops from 155 patients with goiter were assessed by a human expert and sorted into those with and without UAO. The reliability of this assessment was judged by using two observers who repeated the sorting 8 wk apart. A set of 46 patients with loops suggesting UAO and a set of 51 patients with normal flow loops were taken from these 155, and the loops from a further 50 subjects with airflow limitation caused by chronic obstructive pulmonary disease were used for training and testing the neural network. Novel and standard indices were derived from the loops and used by the neural network. The kappa score for agreement between each of the observers and the original classification were 0.5 and 0.46, respectively, with the agreement between the observers at each reading of 0.58 and 0.68. The neural network found that a combination of four novel scores for flatness of the expiratory loop, the moment ratio, and the FEV1/PEF ratio was best at identifying UAO with a kappa score of 0.81, a sensitivity of 88%, specificity of 94% and an accuracy of 92%. We conclude that a neural network using only six indices taken from the expiratory limb of a flow-volume loop was better than human experts at identifying flow loops with UAO.