Autism risk classification using placental chorionic surface vascular network features

Abstract

BackgroundAutism 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.MethodsTwenty 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.ResultsThe 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.ConclusionWe 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.

Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments

“…Precisely, Boruta [24]- [26] starts with the complete set of features and applies n iterations that each train a RF on a feature set augmented by "fake features" obtained by random permutations of the actual ones. The features that, for a statistically significant number of iterations, are less/more relevant than all the fake features (relevance is quantified by the mean decrease in accuracy when the feature is permuted), are selected and removed/confirmed.…”

“…Secondarily, in Section V we present a novel feature selection technique exploiting a cross-validation strategy to combine the Boruta [24] – [26] algorithm and a permutation-based feature selector embedded into Random Forests (RFs, [27] ). The proposed feature selection method enables robust and stable feature selection ( Section V-A1 ).…”

The Prenatal Hormone Milieu in Autism Spectrum Disorder

“…Trophoblastic inclusions, a histological finding that results from atypical growth and folding of the placenta (190), are more common in genetically atypical gestations (191)(192)(193)(194). Furthermore, studies of high ASD risk cohorts (defined by having at least one older sibling with ASD) also found increased placental trophoblastic inclusions (195) in addition to altered placental morphology (196) and placental chorionic surface vascular networks (197). The specific morphological changes found, such as increased thickness and roundness, may reflect decreased ability to adapt to variations in the prenatal environment (196).…”

“…The specific morphological changes found, such as increased thickness and roundness, may reflect decreased ability to adapt to variations in the prenatal environment ( 196 ). Notably, variations within the placental chorionic surface vascular networks may be the result of atypical vasculogenesis and angiogenesis ( 197 ). Several conditions associated with ASD, such as pre-eclampsia ( 198 ), intrauterine growth restriction ( 41 ), and pre-term birth ( 16 ) are also attributed to placental vascular abnormalities ( 199 – 201 ).…”

Artificial Intelligence in Predicting Clinical Outcome in COVID-19 Patients from Clinical, Biochemical and a Qualitative Chest X-Ray Scoring System

“…Samples below the CXR cut-off point were considered as moderate/mild patients, while those above the CXR cut-point were further analyzed to select the most important variables for a more precise outcome prediction. To this aim, Boruta algorithm 23,[26][27][28][29] used an internal 5-fold crossvalidation as detailed by Casiraghi et al 24 3. Selected variables were used to train an RF, which was then pruned and simplified to create a simple associative tree 30,31 and to finally estimate the importance of the variables.…”