Early Prediction of Central Precocious Puberty Using ANN+VGG16 Model

Girls who show secondary sexual traits before the age of eight and
boys who do so before the age of nine are said to have precocious puberty. It is
associated with accelerated growth, premature reproductive maturation, and sub
stantial psychological and physiological transformations. Kids who go through
puberty early are more likely to get type 2 diabetes, heart disease, depression, die
young, and girls are more likely to get breast cancer. These health issues show
how important it is to find and treat problems quickly. This work employs machine
learning and deep learning techniques to forecast central precocious puberty. Our
approach combines luteinizing hormone (LH) data with pelvic ultrasound imag
ing utilizing an integrated Artificial Neural Network (ANN) and VGG16 model.
The suggested ANN+VGG16 model did better than previous benchmark models,
with an accuracy of 92.87% and a precision of 94.26%. This framework offers
a dependable way to forecast early puberty, which helps doctors make decisions
and improve long-term health outcomes