Related Experiment Video
Updated: May 1, 2026
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
Published on: October 28, 2018
Risk groups in children under six months of age using self-organizing maps
A O C Schilithz1, P L Kale2, S G N Gama3
1PEB/UFRJ, Rio de Janeiro, Brazil.
Insights
This study identified distinct infant growth risk profiles in Rio de Janeiro. Infants in group 3 showed the worst health indicators, requiring urgent public health intervention.
Area of Science:
- Pediatrics
- Public Health
- Data Science
Background:
- Fetal and infant growth is irregular, especially in developing nations, influenced by living conditions and pregnancy complications.
- Identifying distinct risk profiles is crucial for targeted interventions in early childhood development.
- Rio de Janeiro provided the setting to examine growth patterns in a diverse urban population.
Purpose of the Study:
- To identify distinct risk profiles for growth development among infants under six months.
- To apply cluster analysis for grouping infants based on health and birth characteristics.
- To inform public health policies for improved infant outcomes.
Main Methods:
- Employed unsupervised learning, specifically self-organizing maps (SOM) and K-means clustering.
- Analyzed data from 904 infants (496 girls, 508 boys) from 27 primary health care units.
- Utilized maternal interviews and child health card reviews for data collection.
Main Results:
- Four distinct infant groups emerged based on growth and health indicators.
- Group 1: Cesarean births, multiparous mothers, high prematurity/low birthweight, high exclusive breastfeeding, low hospitalization.
- Group 2: Best perinatal/infant health indicators.
- Group 3: Worst perinatal/infant health indicators, requiring urgent intervention.
- Group 4: Higher birthweight, low exclusive breastfeeding, higher hospitalization rates.
Conclusions:
- Self-organizing maps effectively identified infant groups with shared characteristics.
- Infants in group 3 present the highest risk, necessitating immediate public health attention and policy adjustments.
- While groups were identified, no significant differences in postnatal weight adequacy were observed across all groups.
Abstract:
Fetal and infant growth tends to follow irregular patterns and, particularly in developing countries, these patterns are greatly influenced by unfavorable living conditions and interactions with complications during pregnancy. The aim of this study was to identify groups of children with different risk profiles for growth development. The study sample comprised 496 girls and 508 boys under six months of age from 27 pediatric primary health care units in the city of Rio de Janeiro, Brazil. Data were obtained through interviews with the mothers and by reviewing each child's health card. An unsupervised learning, know as a self-organizing map (SOM) and a K-means algorithm were used for cluster analysis to identify groups of children. Four groups of infants were identified. The first (139) consisted of infants born exclusively by cesarean delivery, and their mothers were exclusively multiparous; the highest prevalences of prematurity and low birthweight, a high prevalence of exclusive breastfeeding and a low proportion of hospitalization were observed for this group. The second (247 infants) and the third (298 infants) groups had the best and worst perinatal and infant health indicators, respectively. The infants of the fourth group (318) were born heavier, had a low prevalence of exclusive breastfeeding, and had a higher rate of hospitalization. Using a SOM, it was possible to identify children with common features, although no differences between groups were found with respect to the adequacy of postnatal weight. Pregnant women and children with characteristics similar to those of group 3 require early intervention and more attention in public policy.
