Academic achievement is a student's educational standing at the end of a certain study period, expressed in grades. Thus, understanding and predicting students' academic performance in the biological and medical sciences is essential for educational institutions to provide effective support and intervention. It is crucial because certain programs impose strict admission criteria such as CGPA, necessitating proactive measures to ensure students can fulfil these requirements. Determining the factors influencing students' CGPA can provide valuable insights for educators and policymakers to improve the quality of education and student outcomes. This paper aims to explore predictive modelling methods for forecasting CGPA among CFSIIUM biological and medical sciences students. The study utilizes competencies in foundational science courses, such as biology, chemistry, mathematics, and physics, based on exam scores as predictors for academic performance. Multiple linear regression was utilized to develop predictive modelling to determine which exam scores are the best indicators of a student's CGPA. According to the results, students' academic performance can be strongly predicted by biology, mathematics and physics. Therefore, academic advisors must consider these two courses as potential indicators for the intervention process.