• Umang Pahuja
• Charu Kavadia
• Silky Vyas
• Mohit Joshi
• Mayank Patel

This paper introduces a new machine learning algorithm for tailoring influenza medication choice and dosage adjustment according to patient-specific genetic markers and clinical features. Growing evidence for pharmacogenomic effects on antiviral activity requires a more personalized treatment of influenza. We constructed a two-stage machine learning system that initially chooses the best medication class (neuraminidase inhibitors, endonuclease inhibitors, or supportive care) and then computes individualized dosage suggestions. Our model includes key genetic elements such as CYP2D6 enzyme activity variants, IFITM3 polymorphisms, and IL17 expression levels, in addition to routine clinical measures. The classifier for medication recommendation had 92.7% accuracy, and the dosage prediction model showed an R² of 0.89, indicating strong potential for clinical use. This study is an important advance toward precision medicine in the treatment of infectious diseases, although clinical validation will be necessary before its application in clinical practice.

Influenza, machine learning, pharmacogenomics, personalized medicine, drug dosage optimization, random forest classifiers, CYP2D6, IFITM3

"PERSONALIZED INFLUENZA MEDICATION AND DOSAGE RECOMMENDATIONS BASED ON GENETIC AND CLINICAL FACTORS: A MACHINE LEARNING APPROACH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.154-161, June-2025, Available :http://www.jetir.org/papers/JETIRGW06026.pdf

"PERSONALIZED INFLUENZA MEDICATION AND DOSAGE RECOMMENDATIONS BASED ON GENETIC AND CLINICAL FACTORS: A MACHINE LEARNING APPROACH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. pp154-161, June-2025, Available at : http://www.jetir.org/papers/JETIRGW06026.pdf