Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 2 appraisals
Developmental science
Making Machine Learning Accessible for Developmental Science: The Case of Automated Face Detection
The last decade has seen rapid advancements in machine learning, significantly transforming fields like cybersecurity and healthcare. Developmental science has been slower to adopt these technologies. Yet, machine learning holds immense potential to transform this field, enabling scalable and data-driven insights into developmental processes. Broader adoption is currently hindered by challenges in algorithm selection and technical implementation. We address these barriers by focusing on an area that has reached high sophistication from a machine learning perspective while also being of significant interest to developmental scientists: face detection. Face detection is crucial for analysing visual experiences through children's dynamic, first-person views. Automatising this process allows efficient handling of large egocentric datasets, enabling well-powered studies otherwise limited by labour-intensive manual annotation. Here, we systematically evaluated 13 state-of-the-art face detection algorithms (DeepFace library) using data from two increasingly common developmental methodologies involving children under 3 years of age: head-mounted eye-tracking in more structured settings (N = 20; n = 10 4-month-olds, n = 10 8-month-olds) and head-mounted cameras in naturalistic home environments (N = 10 18-29-month-olds). Benchmarking these algorithms against manual annotations revealed that YOLOv11Face (M) and RetinaFace consistently outperformed others in terms of precision and recall, exhibiting strong concordance with manual ratings, lower error, reduced systematic deviation and robust rank-order correlations with manual annotations. To facilitate broader adoption, we introduce an accessible face detection tool (TinyExplorer Detection App), promoting efficiency, scalability, and innovation in developmental science by widening access to machine learning.
5 May 2026
Read appraisal →PloS one
Caregivers' early stimulation behaviors on early child development outcomes in Northern Ghana
Despite the government prioritizing Early Childhood Development (ECD) in Ghana, data on responsive caregiving is limited. This study examined the type and extent of Early Stimulation Activities (ESAs) practiced by mothers, and other caregivers and the associations between ESAs and children's development by caregiver type in Northern Ghana. Data were from a cluster-randomized controlled trial with mother-child dyads that evaluated the impact of an integrated maternal mental health and early childhood intervention program. The primary outcome was measured by the Developmental Milestone Checklist (DMC-II). Covariates included maternal report of ESAs performed by herself, child's father, and other caregivers. Linear regression analyses with cluster-adjusted standard errors were performed. Nearly 15% of mother-participants (n = 313) reported 4 + ESAs in the past 3 days. Within the last 3 days, on average, women reported 2.5 activities for themselves, 1.2 activities by the child's father, and 2 activities by other caregivers. The associations between ESAs and children's development varied by caregiver type. Maternal stimulation was positively associated with children's total development and personal-social development, early stimulation by other caregivers was positively associated with children's total development and language development, and paternal stimulation was not associated with any development domain. Other associations included receipt of postnatal care and presence of household toys. While maternal stimulation seemed particularly important, findings regarding non-primary caregivers suggest that ECD programming could also benefit from their inclusion.
5 Apr 2026
Read appraisal →