Enzo Grossi1, Federica Veggo1,2, Antonio Narzisi3, Angelo Compare4, Filippo Muratori5. 1. Department of Autism Research, Villa Santa Maria Institute, Tavernerio, Italy. 2. Department of Child and Adolescent Psychiatry, University of Milano-Bicocca, Monza, Italy. 3. Department of Developmental Neuroscience, IRCCS Stella Maris Foundation, Calambrone, Italy. 4. Department of Psychology, University of Bergamo, Bergamo, Italy. 5. Department of Developmental Neuroscience, University of Pisa, Calambrone, Italy.
Abstract
BACKGROUND: Autism is a multifactorial condition in which a single risk factor can unlikely provide comprehensive explanation for the disease origin. Moreover, due to the complexity of risk factors interplay, traditional statistics is often unable to explain the core of the problem due to the strong inherent nonlinearity of relationships. The aim of this study was to assess the frequency of 27 potential risk factors related to pregnancy and peri-postnatal period. METHODS: The mothers of 45 autistic children and of 68 typical developing children completed a careful interview. Twenty-four siblings of 19 autistic children formed an internal control group. RESULTS: A higher prevalence of potential risk factors was observed in 22 and 15 factors in external control and internal control groups, respectively. For six of them, the difference in prevalence was statistically significant. Specialized artificial neural networks (ANNs) discriminated between autism and control subjects with 80.19% global accuracy when the dataset was preprocessed with TWIST (training with input selection and testing) system selecting 16 out of 27 variables. Logistic regression applied to 27 variables gave unsatisfactory results with global accuracy of 46%. CONCLUSION: Pregnancy factors play an important role in autism development. ANNs are able to build up a predictive model, which could represent the basis for a diagnostic screening tool.
BACKGROUND:Autism is a multifactorial condition in which a single risk factor can unlikely provide comprehensive explanation for the disease origin. Moreover, due to the complexity of risk factors interplay, traditional statistics is often unable to explain the core of the problem due to the strong inherent nonlinearity of relationships. The aim of this study was to assess the frequency of 27 potential risk factors related to pregnancy and peri-postnatal period. METHODS: The mothers of 45 autisticchildren and of 68 typical developing children completed a careful interview. Twenty-four siblings of 19 autisticchildren formed an internal control group. RESULTS: A higher prevalence of potential risk factors was observed in 22 and 15 factors in external control and internal control groups, respectively. For six of them, the difference in prevalence was statistically significant. Specialized artificial neural networks (ANNs) discriminated between autism and control subjects with 80.19% global accuracy when the dataset was preprocessed with TWIST (training with input selection and testing) system selecting 16 out of 27 variables. Logistic regression applied to 27 variables gave unsatisfactory results with global accuracy of 46%. CONCLUSION: Pregnancy factors play an important role in autism development. ANNs are able to build up a predictive model, which could represent the basis for a diagnostic screening tool.
Authors: B Ya Ryzhavskii; T V Sokolova; R V Uchakina; Yu I Fel'dsherov; Yu A Sapozhnikov; E V Vasil'eva; I R Eremenko Journal: Bull Exp Biol Med Date: 2002-08 Impact factor: 0.804
Authors: Erin C McCanlies; Desta Fekedulegn; Anna Mnatsakanova; Cecil M Burchfiel; Wayne T Sanderson; Luenda E Charles; Irva Hertz-Picciotto Journal: J Autism Dev Disord Date: 2012-11
Authors: Mats Anders Eriksson; Joakim Westerlund; Britt Marie Anderlid; Christopher Gillberg; Elisabeth Fernell Journal: Res Dev Disabil Date: 2012-05-02
Authors: Fred Volkmar; Matthew Siegel; Marc Woodbury-Smith; Bryan King; James McCracken; Matthew State Journal: J Am Acad Child Adolesc Psychiatry Date: 2014-02 Impact factor: 8.829
Authors: Alistair T Pagnamenta; Hameed Khan; Susan Walker; Dianne Gerrelli; Kirsty Wing; Maria Clara Bonaglia; Roberto Giorda; Tom Berney; Elisa Mani; Massimo Molteni; Dalila Pinto; Ann Le Couteur; Joachim Hallmayer; James S Sutcliffe; Peter Szatmari; Andrew D Paterson; Stephen W Scherer; Veronica J Vieland; Anthony P Monaco Journal: J Med Genet Date: 2010-10-23 Impact factor: 6.318
Authors: Amanda T Langridge; Emma J Glasson; Natasha Nassar; Peter Jacoby; Craig Pennell; Ronald Hagan; Jenny Bourke; Helen Leonard; Fiona J Stanley Journal: PLoS One Date: 2013-01-07 Impact factor: 3.240
Authors: Calvin P Sjaarda; Patrick Hecht; Amy J M McNaughton; Audrina Zhou; Melissa L Hudson; Matt J Will; Garth Smith; Muhammad Ayub; Ping Liang; Nansheng Chen; David Beversdorf; Xudong Liu Journal: Sci Rep Date: 2017-08-18 Impact factor: 4.379
Authors: Dustin Scheinost; Rajita Sinha; Sarah N Cross; Soo Hyun Kwon; Gordon Sze; R Todd Constable; Laura R Ment Journal: Pediatr Res Date: 2016-09-27 Impact factor: 3.756