An Improved Neural Network Logic for Identifying Cerebral Palsy Disease to Assist Healthcare Field Using Artificial Intelligence Technique

When brain development is disrupted or damaged, it can lead to a group of conditions collectively known as cerebral palsy (CP). The child's movement, stability, and posture are all impacted. When it comes to childhood motor disabilities, CP is by far the most prevalent culprit. The development of early treatments for cerebral palsy depends on its early discovery in children, when they are still in the early stages of the disorder. To aid in the diagnosis of brain pathologies, several medical imaging techniques are at one's disposal. The high resolution of magnetic resonance imaging makes it a popular choice for medical imaging. Better prediction accuracy, quicker progress in brain illness identification from MRI, and generalized acknowledgment of deep learning as a subset of AI are all outcomes of deep learning's growing profile in medical diagnostics. We present Improved Learning with Neural Classification Principle (ILNCP), a new deep learning strategy for intense CP identification, and we cross-validate it with the traditional Naive Bayes (NB) method to measure its efficacy. Finding a way to detect cerebral palsy that combines an ILNCP model with a data augmentation technique is the goal of this research. To that end, we propose a computerized automated diagnostic model that makes use of deep learning to aid in early identification of cerebral palsy in infants and to assist doctors in identifying the limitations caused by these disabilities.