Discrimination of the notifiable pathogen Gyrodactylus salaris from G. thymalli (Monogenea) using statistical classifiers applied to morphometric data

• Published in: Parasitology Vol. 121 ( Pt 3); p. 315
• Main Authors: McHugh, E S, Shinn, A P, Kay, J W
• Format: Journal Article
• Language: English
• Published: England 01.09.2000
• Subjects: Animals; Discriminant Analysis; Fish Diseases - diagnosis; Fish Diseases - parasitology; Random Allocation; Reproducibility of Results; Salmon - parasitology; Statistics, Nonparametric; Trematoda - anatomy & histology; Trematoda - classification; Trematode Infections - diagnosis; Trematode Infections - parasitology; Trematode Infections - veterinary
• ISSN: 0031-1820
• DOI: 10.1017/S0031182099006381

The identification and discrimination of 2 closely related and morphologically similar species of Gyrodactylus, G. salaris and G. thymalli, were assessed using the statistical classification methodologies Linear Discriminant Analysis (LDA) and k-Nearest Neighbours (KNN). These statistical methods were applied to morphometric measurements made on the gyrodactylid attachment hooks. The mean estimated classification percentages of correctly identifying each species were 98.1% (LDA) and 97.9% (KNN) for G. salaris and 99.9% (LDA) and 73.2% (KNN) for G. thymalli. The analysis was expanded to include another 2 closely related species and the new classification efficiencies were 94.6% (LDA) and 98.% (KNN) for G. salaris; 98.2% (LDA) and 72.6% (KNN) for G. thymalli; 86.7% (LDA) and 91.8% (KNN) for G. derjavini; and 76.5% (LDA) and 77.7% (KNN) for G. truttae. The higher correct classification scores of G. salaris and G. thymalli by the LDA classifier in the 2-species analysis over the 4-species analysis suggested the development of a 2-stage classifier. The mean estimated correct classification scores were 99.97% (LDA) and 99.99% (KNN) for the G. salaris-G. thymalli pairing and 99.4% (LDA) and 99.92% (KNN) for the G. derjavini-G. truttae pairing. Assessment of the 2-stage classifier using only marginal hook data was very good with classification efficiencies of 100% (LDA) and 99.6% (KNN) for the G. salaris G. thymalli pairing and 97.2% (LDA) and 99.2% (KNN) for the G. derjavini-G. truttae pairing. Paired species were then discriminated individually in the second stage of the classifier using data from the full set of hooks. These analyses demonstrate that using the methods of LDA and KNN statistical classification, the discrimination of closely related and pathogenic species of Gyrodactylus may be achieved using data derived from light microscope studies.