Autism risk classification using placental chorionic surface vascular network features.

BMC Med Inform Decis Mak 2017 Dec 6;17(1):162. Epub 2017 Dec 6.

NIH National Children's Study Placenta Consortium, Bethesda, MD, USA.

Background: Autism Spectrum Disorder (ASD) is one of the fastest-growing developmental disorders in the United States. It was hypothesized that variations in the placental chorionic surface vascular network (PCSVN) structure may reflect both the overall effects of genetic and environmentally regulated variations in branching morphogenesis within the conceptus and the fetus' vital organs. This paper provides sound evidences to support the study of ASD risks with PCSVN through a combination of feature-selection and classification algorithms.

Methods: Twenty eight arterial and 8 shape-based PCSVN attributes from a high-risk ASD cohort of 89 placentas and a population-based cohort of 201 placentas were examined for ranked relevance using a modified version of the random forest algorithm, called the Boruta method. Principal component analysis (PCA) was applied to isolate principal effects of arterial growth on the fetal surface of the placenta. Linear discriminant analysis (LDA) with a 10-fold cross validation was performed to establish error statistics.

Results: The Boruta method selected 15 arterial attributes as relevant, implying the difference in high and low ASD risk can be explained by the arterial features alone. The five principal features obtained through PCA, which accounted for about 88% of the data variability, indicated that PCSVNs associated with placentas of high-risk ASD pregnancies generally had fewer branch points, thicker and less tortuous arteries, better extension to the surface boundary, and smaller branch angles than their population-based counterparts.

Conclusion: We developed a set of methods to explain major PCSVN differences between placentas associated with high risk ASD pregnancies and those selected from the general population. The research paradigm presented can be generalized to study connections between PCSVN features and other maternal and fetal outcomes such as gestational diabetes and hypertension.

Download full-text PDF

Source
http://dx.doi.org/10.1186/s12911-017-0564-8DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5719902PMC
December 2017
40 Reads

Publication Analysis

Top Keywords

asd pregnancies
8
chorionic surface
8
surface vascular
8
boruta method
8
vascular network
8
placental chorionic
8
high-risk asd
8
asd
6
pcsvn
5
method selected
4
selected arterial
4
arterial attributes
4
attributes relevant
4
statisticsresults boruta
4
validation performed
4
cross validation
4
performed establish
4
establish error
4
error statisticsresults
4
relevant implying
4

References

(Supplied by CrossRef)

DL Christensen et al.
MMWR Surveill Summ 2016 2016

AV Buescher et al.
JAMA Pediatr 2014

RE Rosenberg et al.
Arch Pediatr Adolesc Med 2009

J Hallmayer et al.
Arch Gen Psychiatr 2011

S Ozonoff et al.
Pediatrics 2011

S Sumi et al.
J Hum Genet 2006

S Ozonoff et al.
Pediatrics 2011

JA Davies et al.
Bioessays 2002

L Leach et al.
J Anat 2009

F Herr et al.
Z Geburtshilfe Neonatol 2009

F Barut et al.
Diagn Pathol 2010

Similar Publications