Participants included 42 very young boys with FXS who completed a T1-weighted anatomical MRI and cognitive/behavioral assessment at two longitudinal time points, with mean ages of 2.89 y and 4.91 y. We sought to examine early structural brain growth as a potential marker for identification of clinically meaningful subgroups. The cognitive, behavioral, and neurological phenotypes observed in affected individuals can vary considerably, making it difficult to predict outcomes and determine the need for interventions. The correction layer on the CNN model improved its prediction accuracy significantly while the inspection of failure modes for the EAF model provided guiding insights into the domain-specific reasons behind several high-error regions.įragile X syndrome (FXS), due to mutations of the FMR1 gene, is the most common known inherited cause of developmental disability.
We demonstrate FiFa on two scenarios: a convolutional neural network (CNN) predicting MNIST images with added noise, and an artificial neural network (ANN) predicting the electrical energy consumption of an electric arc furnace (EAF). We demonstrate two ways to use the failure mode groupings: either to produce a correction layer that adjusts predictions by similarity to the failure modes or to inspect members of the failure modes to illustrate and investigate what characterizes each failure mode.
Our method uses Mapper, an algorithm from topological data analysis (TDA), to build a graphical model of input data stratified by prediction errors. We describe fibers of failure (FiFa), a method to classify failure modes of predictive processes. These faulty predictions can be more or less malignant depending on the model application. Predictive models are used in many different fields of science and engineering and are always prone to make faulty predictions. In addition, these findings underscore the potential of TDA as a powerful tool in the search for biological phenotypes of neuropsychiatric disorders. These results suggest that despite arising from a single gene mutation, FXS may encompass two biologically, and clinically separable phenotypes.
In addition to neuroanatomy, the groups showed significant differences in IQ and autism severity scores. Comparison of these subgroups showed significant between-subgroup neuroanatomical differences similar to those previously reported to distinguish children with FXS from typically developing controls (e.g., enlarged caudate).
Application of topological methods to structural MRI data revealed two large subgroups within the study population. To this end, we analyzed imaging and behavioral data from young boys (n = 52 aged 1.57–4.15 years) diagnosed with FXS. Our goal was to examine variation in brain structure in FXS with topological data analysis (TDA), and to assess how such variation is associated with measures of IQ and autism-related behaviors. Fragile X syndrome (FXS), due to mutations of the FMR1 gene, is the most common known inherited cause of developmental disability as well as the most common single-gene risk factor for autism.