• Ananya Udupa
• Vrushali A Poojary
• Prof. Madhusudhan S
• Prof. Daya Naik

Drug–drug interactions (DDIs) are a serious threat to patient safety, treatment outcomes, and healthcare expenditures, particularly with rising polypharmacy. Conventional DDI discovery—static databases and manual investigation—is labor-intensive, cost-prohibitive, and non-scalable. We overcome this by creating a machine-learning-based predictive model based on SMILES strings and molecular descriptors for a Random Forest classifier to predict potential DDIs automatically. This provides scalability and efficiency, saves labor, and improves patient safety by curbing adverse reactions. It also facilitates personalized medicine and cost-effective data-driven decision-making for improved clinical outcomes.

AI-based skincare system for Indian skin types offering personalized routines using facial analysis, product data, and holistic tips.

"PREDICTING DRUG-DRUG INTERACTIONS USING MACHINE LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.723-728, July-2025, Available :http://www.jetir.org/papers/JETIRGX06135.pdf

"PREDICTING DRUG-DRUG INTERACTIONS USING MACHINE LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp723-728, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06135.pdf