dc.contributor.author |
Bokka, Yugandhar |
|
dc.contributor.author |
Jagan Mohan, R. N. V. |
|
dc.contributor.author |
Chandra Naik, M. |
|
dc.date.accessioned |
2024-03-10T17:24:09Z |
|
dc.date.available |
2024-03-10T17:24:09Z |
|
dc.date.issued |
2024-03-10 |
|
dc.identifier.issn |
2210-142X |
|
dc.identifier.uri |
https://journal.uob.edu.bh:443/handle/123456789/5512 |
|
dc.description.abstract |
Developmental disorders such as autism spectrum disorder (ASD) result from differences in brain development influenced
by genetic, environmental, and prenatal factors. Early indicators of ASD include repetitive behaviors and social communication
deficiencies. While gestational risk factors do not cause ASD, they can influence children’s interactions and potentially affect ASD
development. Changes in lipid levels at birth are linked to autism, with individuals with ASD often showing abnormal cholesterol and
triglyceride levels compared to healthy controls. However, the predictive value of blood lipid profiles for ASD remains unclear. This
study investigates the role of infant lipid levels in ASD development, considering maternal gestational risk factors. We developed a
machine learning model using combined parental and childhood lipid levels to predict ASD. The model was validated with independent
cohorts and tested against infant lipid profiles, employing various statistical approaches and multiple classifiers. Routine blood lipid
levels were analyzed in 50 infants, with 77 youngers than six months and 73 older than six months. This analysis showed no statistical
difference in total cholesterol or LDL cholesterol between infants under six months and older children over six months. However,
significant differences were observed in HDL-cholesterol levels between the ≤6 and >6 month age groups. The analysis using linear
spline mixed models showed a positive association between total cholesterol and maternal levels. The XGBoost model outperformed
all other classifiers, achieving an AUC of 0.920, an accuracy of 0.9666, a specificity of 1.0, a sensitivity of 0.8888, an F1-score of
0.9767, and a precision of 0.9545. These findings suggest that specific lipid profiles at birth could serve as potential biomarkers for ASD. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
University of Bahrain |
en_US |
dc.subject |
Maternal dyslipidemia, Gestational dyslipidemia, Lipid levels, Early childhood development Infant health, Longitudinal study. |
en_US |
dc.title |
Maternal Dyslipidemia During Pregnancy Correlates with Elevated Lipid Levels in One-Year-Old Infants |
en_US |
dc.identifier.doi |
http://dx.doi.org/10.12785/ijcds/1601104 |
|
dc.volume |
16 |
en_US |
dc.issue |
1 |
en_US |
dc.pagestart |
1413 |
en_US |
dc.pageend |
1424 |
en_US |
dc.contributor.authorcountry |
India |
en_US |
dc.contributor.authorcountry |
India |
en_US |
dc.contributor.authorcountry |
India |
en_US |
dc.contributor.authoraffiliation |
CSE, GIET University |
en_US |
dc.contributor.authoraffiliation |
CSE, SRKR Engineering College |
en_US |
dc.contributor.authoraffiliation |
CSE, GIET University |
en_US |
dc.source.title |
International Journal of Computing and Digital Systems |
en_US |
dc.abbreviatedsourcetitle |
IJCDS |
en_US |