Long-form recording of infant body position in the home using wearable inertial sensors

Assessing Infant Gross Motor Performance With an At-Home Wearable

BACKGROUND

Early development of gross motor skills is foundational for the upcoming neurocognitive performance. Here, we studied whether at-home wearable measurements performed by the parents could be used to quantify and track infants' developing motor abilities.

METHODS

Unsupervised at-home measurements of the infants' spontaneous activity were made repeatedly by the parents using a multisensor wearable suit (altogether 620 measurements from 134 infants at age 4-22 months). Machine learning-based algorithms were developed to detect the reaching of gross motor milestones (GMM), to measure times spent in key postures, and to track the overall motor development longitudinally. Parental questionnaires regarding GMMs were used for developing the algorithms, and the results were benchmarked with the interrater agreement levels established by World Health Organization (WHO). A total of 97 infants were used for the algorithm development and cross-validation, whereas an external validation was done using 37 infants from an independent recruitment in the same hospital.

RESULTS

The algorithms detected the reaching of GMMs very accurately (cross-validation: accuracy, 90.9%-95.5%; external validation, 92.4%-96.8%), which compares well with the human experts in the WHO reference study. The wearable-derived postural times showed strong correlation to parental assessments (ρ = .48-.81). Individual trajectories of motor maturation showed strong correlation to infants' age (ρ = .93).

CONCLUSIONS

These findings suggest that infants' gross motor skills can be quantified reliably and automatically from unsupervised at-home wearable recordings. Such methodology could be used in health care practice and in all developmental studies for gaining real-world quantitation and tracking of infants' motor abilities.

Identifying Infant Body Position from Inertial Sensors with Machine Learning: Which Parameters Matter?

The efficient classification of body position is crucial for monitoring infants' motor development. It may fast-track the early detection of developmental issues related not only to the acquisition of motor milestones but also to postural stability and movement patterns. In turn, this may facilitate and enhance opportunities for early intervention that are crucial for promoting healthy growth and development. The manual classification of human body position based on video recordings is labour-intensive, leading to the adoption of Inertial Motion Unit (IMU) sensors. IMUs measure acceleration, angular velocity, and magnetic field intensity, enabling the automated classification of body position. Many research teams are currently employing supervised machine learning classifiers that utilise hand-crafted features for data segment classification. In this study, we used a longitudinal dataset of IMU recordings made in the lab in three different play activities of infants aged 4-12 months. The classification was conducted based on manually annotated video recordings. We found superior performance of the CatBoost Classifier over the Random Forest Classifier in the task of classifying five positions based on IMU sensor data from infants, yielding excellent classification accuracy of the Supine (97.7%), Sitting (93.5%), and Prone (89.9%) positions. Moreover, using data ablation experiments and analysing the SHAP (SHapley Additive exPlanations) values, the study assessed the importance of various groups of features from both the time and frequency domains. The results highlight that both accelerometer and magnetometer data, especially their statistical characteristics, are critical contributors to improving the accuracy of body position classification.

An update of the development of motor behavior

This primer describes research on the development of motor behavior. We focus on infancy when basic action systems are acquired-posture, locomotion, manual actions, and facial actions-and we adopt a developmental systems perspective to understand the causes and consequences of developmental change. Experience facilitates improvements in motor behavior and infants accumulate immense amounts of varied everyday experience with all the basic action systems. At every point in development, perception guides behavior by providing feedback about the results of just prior movements and information about what to do next. Across development, new motor behaviors provide new inputs for perception. Thus, motor development opens up new opportunities for acquiring knowledge and acting on the world, instigating cascades of developmental changes in perceptual, cognitive, and social domains. This article is categorized under: Cognitive Biology > Cognitive Development Psychology > Motor Skill and Performance Neuroscience > Development.

Classification of windswept posture in daily life using tri-axial accelerometers

An asymmetric windswept posture is often seen in children with severe cerebral palsy (CP). However, it is still unclear how long children with CP remain in the windswept posture in daily life. Thus, we developed a triple-accelerometer system for detecting windswept posture. The aim of this study was to assess the validity of a system for classifying various body postures and movements. We assessed the accuracy of our system in nine healthy young adults (age range, 21-23 years). The participants wore acceleration monitors on the sternum and both thighs, then spent 3 min each in eight different positions and three physical activities. Once accuracy was confirmed, we assessed the posture and movements for 24 h in six healthy young adults (age range, 21-23 years) in their home environments. The body postures and activities were correctly detected: the agreement across the subjects were 100% compatible with the subjects' activity logs at least 68% of the time, and at least 96% of the time for recumbent positions. We concluded that the proposed monitoring system is a reliable and valid approach for assessing windswept hip posture in a free-living setting.

Stop trying to carve Nature at its joints! The importance of a process-based developmental science for understanding neurodiversity

Nature is dynamic and interdependent. Yet we typically study and understand it as a hierarchy of independent static things (objects, factors, capacities, traits, attributes) with well-defined boundaries. Hence, since Plato, the dominant research practice has been to 'carve Nature at its joints' (Phaedrus 265e), rooted in the view that the world comes to us pre-divided - into static forms or essences - and that the goal of science is to simply discover (identify and classify) them. This things-based approach dominates developmental science, and especially the study of neurodevelopmental conditions. The goal of this paper is to amplify the marginalised process-based approach: that Nature has no joints. It is a hierarchy of interacting processes from which emerging functions (with fuzzy boundaries) softly assemble, become actively maintained, and dissipate over various timescales. We further argue (with a specific focus on children with Down syndrome) that the prevailing focus on identifying, isolating, and analysing things rather than understanding dynamic interdependent processes is obstructing progress in developmental science and particularly our understanding of neurodiversity. We explain how re-examining the very foundation of traditional Western thought is necessary to progress our research on neurodiversity, and we provide specific recommendations on how to steer developmental science towards the process-based approach.

Preliminary Technical Validation of LittleBeats™: A Multimodal Sensing Platform to Capture Cardiac Physiology, Motion, and Vocalizations

Across five studies, we present the preliminary technical validation of an infant-wearable platform, LittleBeats™, that integrates electrocardiogram (ECG), inertial measurement unit (IMU), and audio sensors. Each sensor modality is validated against data from gold-standard equipment using established algorithms and laboratory tasks. Interbeat interval (IBI) data obtained from the LittleBeats™ ECG sensor indicate acceptable mean absolute percent error rates for both adults (Study 1, N = 16) and infants (Study 2, N = 5) across low- and high-challenge sessions and expected patterns of change in respiratory sinus arrythmia (RSA). For automated activity recognition (upright vs. walk vs. glide vs. squat) using accelerometer data from the LittleBeats™ IMU (Study 3, N = 12 adults), performance was good to excellent, with smartphone (industry standard) data outperforming LittleBeats™ by less than 4 percentage points. Speech emotion recognition (Study 4, N = 8 adults) applied to LittleBeats™ versus smartphone audio data indicated a comparable performance, with no significant difference in error rates. On an automatic speech recognition task (Study 5, N = 12 adults), the best performing algorithm yielded relatively low word error rates, although LittleBeats™ (4.16%) versus smartphone (2.73%) error rates were somewhat higher. Together, these validation studies indicate that LittleBeats™ sensors yield a data quality that is largely comparable to those obtained from gold-standard devices and established protocols used in prior research.