Pseudomonas aeruginosa, a multidrug-resistant organism with clinical significance, complicates the treatment of critically ill patients. Since traditional susceptibility testing takes at least 24 hours, timely identification and treatment are crucial in the face of rising Antimicrobial Resistance (AMR). In this study, we present the development of ANTIBIOLOG, a cutting-edge Machine Learning (ML) model. This model predicts P. aeruginosa antibiotic susceptibility based on patient demographics and antibiotic susceptibility testing results, using a dataset of 49 patient samples from IMS & SUM Hospital. Multinomial logistic regression was selected for dealing with multiple classes and providing probabilistic interpretations. The performance of the model is evaluated using various metrics such as accuracy, precision, recall, specificity, F1 score, and MCC. Through a user-friendly web interface, it simplifies resistance prediction and guides empirical antibiotic treatment. Unlike generic tools, it focuses on P. aeruginosa and provides accurate therapy selection. ANTIBIOLOG predicted antibiotic susceptibility with a promising 77.77% accuracy. This ML-based tool enables healthcare professionals to combat multidrug-resistant P. aeruginosa infections and address AMR issues.