Cognitive Enhancement in Mice: a Data Driven Predictive Model for Evaluating Anxiolytic Effects of Diazepam using Supervised Machinelearning Approach

Abstract

In the discipline of pharmacology, where it is vital to investigate natural substances for therapeutic benefits, this study investigates the topic of cognitive enhancement in mice with a focus on the anxiolytic characteristics of diazepam. We present a novel approach to predict and assess the anxiolytic potential of diazepam by combining pharmacology with supervised machine learning and making use of the power of modern data analysis techniques.Machine learning is frequently used to build mathematical models that explain or predict data driven based on previous observations. The support vector regressor, Linear Regression, and naïve Bayesian classifier are perhaps among the most popular supervised algorithms. Behavioral pharmacology, which assesses the behavior of experimental subjects after being injected with various chemicals to see if they have positive or negative effects, is an area of possible application. Diazepam (0.5 and 2 mg/kg) was tested in the elevated plus maze (EPM) in the current investigation to determine its effects. Machine learning techniques (SVR Algorithm) was applied. The results showed an effective anxiolytic effect of the 2 mg/kg dose of diazepam when compared with the control group. The findings of the research using conventional statistical methods indicate that progesterone, at a dose of 2 mg/kg, has an impact that is similar to anxiolytics. The variables that provide additional information to distinguish the experimental groups are automatically identified via machine learning.