International Journal of Scientific Research and Engineering Development

The current accelerated development of healthcare technologies resulted in the paradigm shift in the traditional generalized treatment methods into the personalized medicine where medical choices are made based on the idiosyncrasy of the individual. Personalized medicine uses genetic data, clinical data and lifestyle habits to create treatment plans that are optimized hence enhancing the effectiveness of the therapy and also minimizing adverse drug reactions. In this regard, in this paper a gene-based personalized medicine recommendation system is proposed which uses sophisticated machine learning methods to predict diseases as well as to give an individualized treatment recommendation. The suggested system will combine heterogeneous data processing, such as genetic markers, patient symptoms, medical history, and demographic data, to make precise predictions and recommendations. Random Forest algorithm and Support Vector machine are the machine learning algorithms that detect the hidden patterns and correlations of high-dimensional biomedical data. These models are trained and tested on structured sets to guarantee the solid performance of models in the task of disease prediction and treatment recommendations. The system does not only forecast the risk of certain diseases but also prescribes appropriate drug prescriptions, diets, precautions, and lifestyle changes based on the genetic and physiological make-up of a patient. The system is deployed as a scalable web application in the MERN stack, including MongoDB as a database, Express.js and Node.js as the back-end, and React.js as an interactive user interface to boost the usability and accessibility. The architecture allows processing real time data, ensures smooth communication among system components and effective processing of high volume of data. Moreover, it can be considered user-friendly and easy to use, enabling patients and medical workers to communicate with the system and get valuable results. The experimental findings suggest that the presented system has high accuracy and reliability in the disease prediction in contrast to the traditional methods. Moreover, the combination of machine learning with pharmacogenomics proves to be very promising in enhancing clinical decision-making and patient outcomes. This study shows the potential and efficacy of AI based personalized healthcare systems, despite the issue of data privacy, model interpretability, and limitations on the dataset. On the whole, the work makes a contribution to the development of intelligent healthcare solutions through introducing a multifaceted, scalable, and data-intensive model of the recommendation of personalized medicine based on the genes. The proposed system highlights the disruptive nature of merging machine learning with genomic data to transition to a more accurate, effective, and patient-centered healthcare delivery.

Madhu Choudhary, Dushyant Singh Bhati, Ganesh Sharma, Dharm Singh,"Gene-Based Personalized Medicine Prediction System" International Journal of Scientific Research and Engineering Development, V9(2): Page(1631-1638) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.