Penalized linear discriminant analysis and Discrete AdaBoost to distinguish human hair metal profiles: The case of adolescents residing near Mt. Etna
- Authors: Abbruzzo, A.; Tamburo, E.; Varrica, D.; Dongarrà, G.; Mineo, A.
- Publication year: 2016
- Type: Articolo in rivista (Articolo in rivista)
- OA Link: http://hdl.handle.net/10447/177653
The research focus of the present paper was twofold. First, we tried to document that human intake of trace elements is influenced by geological factors of the place of residence. Second, we showed that the elemental composition of human hair is a useful screening tool for assessing people's exposure to potentially toxic substances. For this purpose, we used samples of human hair from adolescents and applied two robust statistical approaches. Samples from two distinct geological and environmental sites were collected: the first one was characterized by the presence of the active volcano Mt. Etna (ETNA group) and the second one lithologically made up of sedimentary rocks (SIC group). Chemical data were statistically processed by Penalized Linear Discriminant Analysis (pLDA) and Discrete AdaBoost (DAB). The separation between the two groups turned out well, with few overlaps accounting for less than 5%. The chemical variables that better distinguished ETNA group from SIC group were As, Cd, Co, Li, Mo, Rb, Sr, U and V. Both pLDA and DAB allowed us to characterize the elements most closely related to the volcanic contribution (As, U and V) and those (Cd, Co, Li, Mo, Rb and Sr) prevalently influenced by the geology of the area where SIC samples were collected. We conclude that the geological characteristics of the area of residence constitute a key factor in influencing the potential exposure to trace elements. Hair analysis coupled with robust statistical methods can be effectively used as a screening procedure to identify areas at great environmental risk.