Exemplary classification of otolaryngologic data using the Kohonen artificial neural network

: An exemplary classification of otolaryngological data with use of the Kohonen artificial neural network is presented along with an evaluation of grouping effectiveness. The study was based on 220 patients with otosclerosis, including 184 women and 36 men, aged 16-68, operated at the Otosurgery Department, Medical University of Lodz in 1984-1992. The neural network distinguished 3 clusters considerably differing in air and bone conduction preoperatively and as a result in the values of postoperative air-bone gap. The effectiveness of classification was also exhibited in congruent with previous knowledge differences between clusters in many other variables not presented to the neural network.