July 2, 2022
  • July 2, 2022

AI predicts infant age, sex based on temperament – WSU Insider

By on May 10, 2022 0

PULLMAN, Wash. — It’s hard to tell the difference between a newborn boy and girl based on temperament characteristics alone such as the baby’s propensity to show fear, smile or laugh. But once babies reach around a year old, that starts to change.

A new study in PLOS ONE used machine learning to analyze temperament data from 4,438 babies with the aim of classifying infants by sex and age.

The results indicate that it is much easier for computer algorithms to determine a baby’s age than to decipher a baby’s sex based on temperament data during the infant’s first 48 weeks of life.

However, once babies passed 48 weeks of age, sex classification improved for the multiple algorithms considered, suggesting that sex differences in infancy are accentuated at this time.

“This suggests at least a picture where temperament begins to differentiate more potently by sex around one year of age,” said Maria Gartstein, lead author of the study and professor of psychology at the University. of Washington State.

Previous research has investigated age- and sex-based differences in temperament in babies, but few, if any, studies have looked at the two variables together.

Gartstein said this is primarily due to a single lab’s difficulty in collecting enough data on infant behavior to make their results statistically reliable and relevant to a large enough segment of the population.

To overcome this challenge, she and her colleagues reached out to scientists nationwide to collect the Infant Behavior Questionnaire data collected between 2006 and 2019.

The questionnaire is a parent-reported measure of temperament that asks parents to record the frequency of 191 different behaviors their child displays over the past week from 3 to 12 months. This data can then be used to rate babies on 14 different temperament dimensions such as smile, activity level, anger/frustration and fear. Overall, Gartstein and his colleagues collected data for 2,298 boys and 2,093 girls.

For the analysis, co-author Erich Seamon of the University of Idaho’s Institute for Modeling, Collaboration, and Innovation used machine learning algorithms to classify infants as male or women aged 0-24 weeks, 24-48 weeks and older. over 48 weeks based on ratings of the 14 temperament dimensions. Accuracy rates increased with age, ranging from a low of 38% for age group one to 57% for age group three.

“It was a great opportunity to do a kind of demonstration study using these machine learning techniques that require very large datasets and are not very common in socio-emotional development research,” said said Gartstein. “It gave us for the first time the opportunity to really consider the extent to which sex differences are influenced by infant age.”

Maria Garstein

The results of the researchers’ analysis showed that fear was the most important characteristic in distinguishing boys and girls for the youngest and middle age groups. As babies got older, declining responsiveness or the ability to recover quickly from high stress situations, and approach, showing more willingness to initiate interactions and engage with people and objects, have become more influential.

For infants older than 48 weeks, low-intensity pleasure or pleasure from familiar quiet activities such as playing peekaboo with a parent was the most influential variable in distinguishing boys from girls. Overall, girls scored higher in fear, falling responsiveness, and low-intensity fun, and boys in approach.

Interestingly, some temperament characteristics have detracted from the accuracy of machine learning algorithms in classifying infants by sex, particularly cuddliness, vocal responsiveness, smiling and laughter in the youngest age group and smiling, laughing, perceptual sensitivity (eg, noticing very subtle changes) and activity in the older age group.

While a number of factors may contribute to the researchers’ pattern of results, their work is consistent with previous findings that show the effects of socialization really start to kick in around one year of age.

“Mothers take different approaches to socialization for their sons and daughters, and over time such differences can lead to divergent trajectories with respect to temperament,” Gartstein said. “Specifically, parents may prioritize relationship orientation for daughters, but competence and autonomy for sons.”

Going forward, Gartstein said the plan is to leverage the machine learning approach she and her collaborators developed for the current study to investigate other hard-to-answer questions about the social-emotional development in infants.

“What I’m actually interested in right now is seeing if you can predict differences in the quality of caregiving based on the child’s brain activity,” she said. declared. “The analytical method we developed for this study is particularly powerful when it comes to answering questions that rely on multiple input variables to solve a problem of classification, high or low quality care delivery. ”