Autism spectrum disorder (ASD) is a developmental syndrome primarily characterized by deficits in social communication and interactions, and repetitive/restricted patterns of behaviors, interests, and/or activities, which are present, at least in part, from early in development [1]. The presentation of ASD is very heterogeneous, and changes depending on a child’s intellectual abilities, language proficiency, and age [2]. The phenotypic complexity of ASD has been associated with a variety of differences in both functional and anatomical neural substrates [3]. The multitude of neural atypicalities identified in individuals with ASD coupled with recent findings showing significant generic heterogeneity [4] have contributed to conceptualizing ASD as a syndrome characterized by differences in brain-wide neural circuitry that emerge across development. On the basis of this evidence, ASD is hypothesized to be a “disconnection syndrome”, one in which the anatomical and functional integration of neural circuits is disrupted [5]. Neural integration processes are reflected in various frequency domains of an individual’s EEG. High frequency activity in the gamma range, for example, is thought to bind neural information from different networks, a process that is required for a number of perceptual and cognitive tasks and that is disrupted in several neurocognitive disorders including ASD [6]. Disruptions in the binding function of gamma activity may explain a wide range of language and social communication deficits that characterize ASD [7]. More specifically, behaviors that require the coordinated function of several brain regions may not be sufficiently integrated without the appropriate amount of gamma frequency activity.

One question that has motivated recent research in this area is how early in development differences in gamma frequency metrics of neural integration arise. To investigate issues related to very early development, studies rely on infants with an older sibling with ASD [8], [9]. These infants are termed “high-risk” for ASD because they have an increased predisposition to develop ASD, estimated to be around fifteen to twenty times higher than infants with no family history of ASD [10], [11]. Studies of this population present several advantages to understanding ASD generally and to neural integration specifically [12]. First, we can ask questions about the developmental trajectories in biological and cognitive factors as they relate to the emergence of typical or atypical outcomes. Second, we can ask questions about which factors are specific to individuals who go on to develop ASD and which factors are more generally observed family members of those who have ASD. These latter factors are generally observed with greater frequency in family members of affected individuals are commonly referred to as endophenotypes or intermediate phenotypes. They form a bridge between the two ends of the causal sequence – genes and behavior [13]. Endophenotypes are particularly important to understanding ASD in that they will likely help sort through the heterogeneity that exists at each level of functionality–genetic, neural, cognitive, and behavioral [14].

With respect to neural integration as an early endophenotype, differences in gamma frequency activity have been identified in several studies of infants at high risk. For example, Elsabbagh et al. [15] found higher baseline but lower induced gamma power in response to an eye gaze paradigm in 10-month-old infants. Tierney et al. [16] found lower gamma power at 6 months and flattened developmental trajectories in high-risk infants between 6 and 24 months. Both findings are consistent with a disruption in the integration of neural networks, although the exact nature of the timing and direction of differences in baseline power still needs to be resolved. Evidence of differences in gamma power in infants at high-risk for ASD would not only provide support for the idea that ASD is a disorder of neural integration but would also provide evidence that differences of gamma activity are candidate endophenotypes.

Spectral power, however, is a limited measure of neural integration because it primarily reflects synchronized activity within the specific region in which it is measured. Other transformations of neurophysiological signals provide a better assessment of neural integration. For example, linear coherence is an index of synchronization across regions rendering it a better-suited measure of neural integration–or connectivity as it is referred to in this literature. Linear coherence assesses the correlation between the phase and power information of two EEG signals and can be applied to any frequency range. The higher the correlation, the more synchronized, and therefore integrated, the signals are interpreted to be. Indeed, studies of EEG coherence as a measure of neural connectivity have found that children and adults with ASD showed lower coherence compared to age- and IQ-matched typically developing controls [17], [18], [19]. These findings of lower coherence have contributed to the proposal that one characteristic of ASD is that there is underconnectivity between distant regions of the brain. More recent coherence studies indicate a more complex pattern of connectivity in children with ASD, finding perturbations in the proportion of long- and short-range connectivity in the theta and alpha frequency ranges [20].

Systematic studies of coherence in gamma activity in high-risk infants have not yet been conducted. If atypical patterns of neural connectivity are responsible for the symptomatology of ASD in older individuals, they are likely to emerge very early in development either before behavioral and cognitive differences emerge or concurrently with the divergence in behavior and cognitive development. If these biological indices are present early in development, they could either be biomarkers of the disorder, or like many of the other measure of neural integration, endophenotypes that are found among individuals with a high genetic load for ASD. Thus, the goal of the present study was to investigate functional connectivity in infants high-risk for ASD in order to evaluate it as a potential endophenotype or biomarker of ASD. Using coherence of gamma frequency activity as a metric of connectivity, we examined whether differences emerge during the first year of life, a period of development that precedes the onset of ASD symptoms, in infants at high or low risk for ASD as well as in the subset of those who go on to develop the disorder.

We assessed functional connectivity in the EEG signal acquired as infants were presented with speech sounds and evaluated differences in coherence in response to hearing these sounds. We employed a task that involved language relevant sounds, given that: (1) language impairments are a common feature of ASD and of the broader phenotype [21], [22] and (2) previous studies of toddlers and older children with ASD identified differences in measures of connectivity, specifically as they relate to language-based tasks [23]–[26]. This paradigm has been used to evaluate speech perception in infants [27] and previous studies of infant siblings using this task have found that there are ASD risk-related differences in the ERPs [28]. Overall we hypothesized that risk for ASD will be associated with reduced functional connectivity in response to speech sounds, which might be a manifestation of disrupted neural integration processes.

The study reported here is part of a comprehensive and ongoing longitudinal project on the neurocognitive development of infants at risk for ASD conducted at Boston Children’s Hospital/Harvard Medical School and Boston University. All components of the study were approved by the IRB review boards at both institutions and are covered under IRB guidelines approved by both institutions. Written, informed consent was provided by the parents or guardians prior to their child’s the participation in the study.

Analyses were conducted cross-sectionally by age (6 months and 12 months) because not all infants contributed data at both time points. Repeated measures mixed-model factorial ANOVAs were used to compare group differences in linear coherence. The models included group (LRC and HRA) as the between-subject factor; hemisphere (right and left), and condition (standard, native deviant, non-native deviant) as within-subject factors; subject was treated as a random effect. Given that the number of subjects was not equivalent across the two groups, the restricted maximum likelihood (REML) method was used. The dependent measure was linear coherence. Because of the change in equipment, we also evaluated the influence of net type (64-channel, 128-channel) but found no effects; therefore this factor was excluded from the analyses reported below. Additionally, we conducted a preliminary analysis in order to compare the differences in the 12-month data between the subset of infants who at 36 months met criteria for ASD and those who did not. See tables 3 and 4 for a complete summary of the statistical analyses.

The goal of the present study was to examine whether there are differences in functional connectivity between infants at high- and low- risk for ASD by the first year of life. First, our results show that by 12 months of age, infants at high-risk of developing ASD display significantly lower functional connectivity between frontal and parietal sites compared to infants at low-risk for ASD. Second, infants at high-risk for ASD showed lower functional connectivity compared to low-risk infants, irrespective of ASD outcome. Third, coherence appears to be lowest in those high-risk infants who go on to develop ASD, compared to high-risk infants who do not (see figure 3), but a larger sample is needed to confirm this result. Finally, our results did not show any group differences with regard to the sensitivity to native and non-native phonetic contrast or hemispheric lateralization.

The present results are consistent with a growing body of literature showing the emergence of risk-related differences in electrophysiological responses that emerge over the course of the first year of life [16], [37], [38]. More specifically, our findings of reduced functional connectivity associated with risk for ASD are consistent with recent studies of infants and toddlers that have used fNIRS [39], DTI [40], and fMRI [23]. Taken together, these results confirm the emerging trend toward atypical developmental patterns in measures of neural integration and anatomical connectivity associated with risk for ASD.

Our findings are the first to demonstrate the presence of reduced functional connectivity as indexed by linear coherence in gamma frequency activity in infants at high-risk for ASD. Furthermore, this is an endophenotype of ASD because reduced functional connectivity between our low-risk group and our high-risk group was present even after infants who went on to develop ASD were excluded from the analyses. Together with recent findings reporting abnormalities in white matter structures in the children with ASD and their unaffected siblings [41], our results provide evidence for a neural architecture that is both anatomically and functionally different from the early stages of development in individuals who are genetically vulnerable to ASD. It is likely that many qualitative and quantitative differences in neural connectivity can account for the heterogeneous phenotypic variations observed in individuals at risk for ASD. Our preliminary results suggest that quantitative differences in functional connectivity might be present between infants at-risk for ASD who later develop ASD and those who do not. This result is not surprising giving the strong evidence of reduced functional and anatomical connectivity in individuals ASD [42]. Nevertheless, it is remarkable that such differences can be detected as early as 12-months-of-age.

The stimuli used in this study derive from a paradigm designed to examine phonetic perception in relation to the perceptual content that infants are exposed to [27], [28]. A recent study carried out with the same sample of infants using ERP showed that both low- and high-risk infants displayed experience-dependent changes in their responses to native and non-native phonemes over the first year of life, such that by 12 months of age there were no differences in the ERP responses to a non-native phonetic contrast [28]. Here we demonstrate that linear coherence between frontal and parietal sites is a neural measure sensitive to differences between native and non-native contrasts in both 6-month and 12-month old infants irrespective of risk status, as evidenced by significant differences between the standard condition and both deviant conditions. This pattern is somewhat similar to some of the ERP findings by Seery and colleagues [28] in which, irrespective of risk status, at 6 months and 9 months the P150 amplitude in the frontal region showed a main effect of condition with the two deviant conditions different from the standard, but no differences between the deviants. Nevertheless, Seery and colleagues [28] found that at 12-months-of-age the P150 amplitude in the frontal region was no longer different between non-native deviant and standard conditions. It is important to point out that there are some key methodological differences between the two studies that could account for the differences in results at 12 months. First, linear coherence in the gamma frequency band and ERP used non-overlapping portions of the EEG signal: whereas we focused our analyses on frequencies from 30 to 50 Hz, the ERP signal contains information only from frequencies below 30 Hz. Second, linear coherence, as an index of synchronized activity across sites, is not dependent on morphological attributes of the localized EEG signal across trials, but rather on the relationship in phase and power of the EEG signal between 2 locations. In contrast, ERPs reflect localized activity and are primarily sensitive to the presence of specific morphological characteristics within the EEG signal that are consistent across experimental trials. Third, in Seery et al. [28] these effects were found only in the frontal region, whereas the linear coherence reported on here assesses the connection between frontal and parietal regions.

Previous electrophysiological research on infant siblings has also found evidence of differences in hemispheric lateralization in ERP responses to speech sounds between low- and high-risk infants [28]. Similarly atypical patterns of hemispheric lateralization have also been found using fMRI in tasks that involved language processing [43], [44]. In the present study we failed to find any differences in hemispheric lateralization of linear coherence, regardless of risk status or ASD outcome. As discussed above, linear coherence is an index of synchronized activity between regions and does not reflect the absolute amount of activation in response to specific stimuli, in contrast to ERP and fMRI. As such, it is possible that over the first year of life the left and right hemisphere networks sampled by the electrodes chosen in this study are comparably synchronous, irrespective of any differences in absolute activation.