OPTIMIZING DRUG DOSAGE AND HALF-LIFE PREDICTION FOR ADHD TREATMENT IN ADULTS AND CHILDREN USING BIG DATA ANALYTICAL BASED DEEP LEARNING APPROACH

Abstract

Attention Deficit Hyperactivity Disorder (ADHD), a common neuro-developmental condition affects both adults and children. Choosing the right medication dose level, considering individual variability and drug half-life, is an important part of treating ADHD. In this article, we propose a thorough strategy for optimizing medication dose levels for treating ADHD utilizing a Deep Convolve NeuroNet (DCNN) with cutting-edge feature extraction and data pre-processing methods. Our database contains clinical records of individuals with ADHD, together with information on their age, gender and drug response. Using the Map-Reduce method, we can arrange the data displayed in the datasets. After the pre-processed data has been extracted, linear discriminant analysis (LDA) is used to find pertinent information, minimize dimensionality and facilitate classification. Finding the most important factors is one of the biggest obstacles in selecting the right medicine dose. Our model is more effective because of the use of Correlation-based Feature Selection (CFS), which chooses the most informative properties. We employ a DCNN architecture trained to predict the optimal drug dosage level for each patient. This deep learning approach is well-suited for handling complex relationships in the data, enabling accurate and personalized dosage recommendations. We aim to provide healthcare professionals with a valuable tool for tailoring drug dosages to individual patients, enhancing treatment efficacy and minimizing side effects.