Artificial intelligence and machine learning models are increasingly shaping diagnostic and therapeutic landscapes across diseases. Novel AI approaches predict breast cancer risk using biochemical biomarkers and guide precise use of azithromycin in pediatric diarrheal diseases. Machine learning improves detection of physician fatigue from clinical notes, supporting clinical workforce management. Additionally, innovative Bayesian and radiomics models leverage imaging and biochemical data to anticipate lymph node spread in tongue squamous cell carcinoma and forecast outcomes in endometrial and cervical cancer, advancing personalized medicine potentials.