Digital behavioral phenotyping emerges as a promising tool for the early detection of autism

Digital behavioral phenotyping has emerged as a promising tool for the early detection of autism, a neurodevelopmental condition that impacts social communication abilities. Traditional autism screening questionnaires have shown lower accuracy in real-world settings, particularly for children of color and girls, compared to research studies.

A recent multiclinic, prospective study evaluated the effectiveness of an autism screening digital application administered during pediatric well-child visits for 475 children aged 17 to 36 months. Of these children, 49 were diagnosed with autism while 98 were diagnosed with developmental delay without autism. The app utilized computer vision and machine learning techniques to quantify behavioral signs of autism, ultimately achieving a high level of diagnostic accuracy with an area under the receiver operating characteristic curve of 0.90.

The algorithm developed in this study displayed a sensitivity of 87.8%, specificity of 80.8%, negative predictive value of 97.8%, and positive predictive value of 40.6%. Remarkably, the algorithm maintained consistent sensitivity performance across subgroups defined by sex, race, and ethnicity. These results highlight the potential of digital phenotyping as an objective and scalable approach to autism screening in real-world settings. Additionally, combining digital phenotyping results with caregiver questionnaires could further enhance screening accuracy and help address disparities in access to diagnosis and intervention.

Autism, also known as Autism Spectrum Disorder (ASD), manifests with challenges in social communication and the presence of restricted and repetitive behaviors. Early signs of autism typically appear between 9 and 18 months of age and can include reduced attention to people, lack of response to name, differences in affective engagement, and motor delays.

Currently, children are screened for autism during their 18 to 24-month well-child visits using parent questionnaires like the Modified Checklist for Autism in Toddlers-Revised with Follow-Up (M-CHAT-R/F). However, research has shown that these screening tools may not be as accurate when used in real-world settings, particularly for girls and children of color due to low rates of follow-up completion by pediatricians.

While eye-tracking technology has shown promise in measuring attentional preferences for social stimuli in children with autism, it may not be sufficient as a standalone screening tool given the heterogeneous nature of the condition. This has led to the exploration of digital phenotyping tools, such as the SenseToKnow application, which uses computer vision analysis and machine learning to capture a wide range of autism-related behaviors in children.

By quantifying behaviors like gaze patterns, head movements, facial expressions, and motor behaviors, digital phenotyping can provide a more comprehensive assessment of autism symptoms. The potential of combining digital phenotyping with existing screening methods to improve accuracy and reduce disparities in autism diagnosis and intervention is a promising avenue for future research.


Comparing Autism Screening Rates: A Population-Based Study in Two Groups Receiving Usual Care

Screening for autism spectrum disorder (ASD) has become a common practice in various countries and settings to detect the condition at an early stage. Numerous studies have examined the efficacy of screening procedures and tools such as the Modified Checklist for Autism in Toddlers, Revised with Follow-Up (M-CHAT-R/F). However, the focus of these studies has typically been on follow-up care for children who screen positive for ASD.

In contrast, a recent study conducted in Iceland aimed to assess the effectiveness of ASD screening in identifying the condition early on. The study involved cluster randomization and compared the rate of ASD in a group invited to a screening program with rates in two control groups receiving usual care. The study included all children registered for their 30-month well-child visits at primary healthcare centers (PHCs) in Iceland, with a total of 7173 children eligible for screening.

In this study, nine PHCs in the capital area of Reykjavik were selected for the intervention group (invited group), while eight PHCs received usual care (control group 1). PHCs outside the capital area were not randomized and served as control group 2. An interdisciplinary team comprised of a pediatrician, a psychologist, and a social worker diagnosed ASD cases based on a consensus reached using the ICD-10 diagnostic system.

During the two-year follow-up period, 119 cases of ASD were identified, resulting in an overall cumulative incidence of 1.66. The incidence rate of ASD was found to be 2.13 in the invited group, 1.83 in control group 1, and 1.02 in control group 2. While the incidence rate was higher in the invited group compared to the control groups, the wide confidence intervals prevented the researchers from drawing conclusive results regarding the efficacy of screening for ASD.

This study is unique in its approach as it utilizes cluster randomization to evaluate the effectiveness of ASD screening. While previous studies have focused primarily on follow-up care for children identified with ASD, this study sought to determine whether screening could lead to earlier detection of the condition compared to usual care.

The research team acknowledges that similar studies have been planned to include screening for ASD along with high-quality treatment and long-term follow-up. However, the study in Iceland stands out as the first of its kind to employ randomization in evaluating ASD screening. The authors hope that the results of this study will contribute valuable insights to the ongoing debate on the efficacy of screening for ASD.

The study is part of a larger project on ASD screening at the 30-month well-child visit in primary healthcare centers in Reykjavik. Previous phases of the project focused on educating healthcare professionals and implementing ASD screening using the M-CHAT-R/F tool. The current phase aimed to determine the rate of ASD in children invited to screening compared to those receiving usual care.

Overall, the study highlights the importance of evaluating the effectiveness of ASD screening in identifying the condition at an early stage. By utilizing a randomized approach, the researchers in Iceland have made a significant contribution to the existing literature on ASD screening, paving the way for further research in this area.


The Evolution of Brain: From Decline to Increase in Pregnancy and Postpartum Period

A recent study conducted on first-time mothers has shed light on the neuroplasticity that occurs during pregnancy, childbirth, and the postpartum period. In this longitudinal study, researchers tracked changes in brain cortical volume in 110 mothers during late pregnancy and early postpartum, comparing them to 34 nulliparous women. The results showed that during late pregnancy, mothers exhibited lower cortical volume compared to the control group across all functional networks. However, these differences seemed to diminish during the early postpartum period. Interestingly, the researchers found that the default mode network and frontoparietal networks displayed below-expected volume increases during the peripartum period, indicating that these reductions may persist for a longer time.

The study also revealed that mothers who delivered by scheduled C-section exhibited different cortical trajectories compared to those who had a natural childbirth. These findings were further confirmed in an independent sample of 29 mothers and 24 nulliparous women. Overall, the data suggest that there is a dynamic trajectory of cortical changes during pregnancy that gradually stabilizes in the postpartum period, with the rate of change dependent on the brain network and type of childbirth.

Pregnancy is a transformative period in a woman’s life, marked by significant adaptations that impact nearly every aspect of her body. Recent research has highlighted the brain as an additional organ that undergoes changes during gestation. Studies utilizing non-invasive brain imaging techniques such as magnetic resonance imaging (MRI) have provided valuable insights into how pregnancy influences brain structure. Longitudinal MRI studies have shown that pregnant women experience cortical volume reductions in regions of the default mode network that persist for years after giving birth. Conversely, studies examining brain changes during the postpartum period have found the opposite effect, with cortical volume increasing across several brain networks.

Although these findings may seem contradictory, researchers believe that they reflect a dynamic evolution of brain volume changes, with initial declines during pregnancy followed by increases postpartum that do not reach pre-pregnancy levels, particularly in default mode regions. This study contributes to the understanding of how pregnancy, childbirth, and postpartum impact maternal neuroplasticity. The researchers theorize that pregnancy and postpartum induce opposite effects on the cerebral cortex, with reductions occurring during pregnancy and increases during the postpartum period. They also suggest that childbirth, a unique event with hormonal, immunological, and physiological implications, may be the critical point at which these cortical changes reverse course.

Overall, this study underscores the intricate neuroplasticity that occurs during the peripartum period and highlights the importance of considering the type of childbirth when evaluating brain changes in new mothers. These findings have significant implications for understanding the impact of motherhood on the brain and may pave the way for future research in this area.