Allergic rhinitis (AR) has been rising globally in recent years, now affecting between 10-30% of the population. The condition frequently coexists with asthma, with up to 40% of AR patients experiencing asthma symptoms and 80% of asthmatics reporting symptomatic AR. The presence of co-occurring AR exacerbates asthma, leading to increased risks of asthma attacks, emergency visits, and hospitalizations. This study aims to identify key biomarkers for assessing AR comorbidities in asthmatic patients to improve treatment and management strategies. We categorized subjects into three groups: healthy controls (n=4,032), asthma patients (n=21,506), and asthma patients with rhinitis (n=3,881). We applied a naive Bayesian machine learning algorithm to evaluate routine blood examinations and specific indicators. The ROC curve analysis was conducted to distinguish between normal, asthma, and asthma with AR states, revealing BAS%, ALB, NEUT%, and HB as key biomarkers with high diagnostic accuracy (AUCs of 0.722, 0.712, 0.680, and 0.711, respectively). Our findings indicate significant correlations between these biomarkers and disease states. In asthma with AR patients, lower levels of NEUT% and EOS% were observed compared to healthy and asthma-only groups. Gender differences were also noted, with a higher prevalence of asthma combined with AR in males. The analysis underscores the utility of BAS%, ALB, NEUT%, and HB in predictive modeling, providing a more accurate and early diagnosis crucial for effective disease management. This study highlights the potential of integrating biochemical indicators into advanced predictive models to enhance diagnostic precision and treatment outcomes for asthma and AR. Future research should validate these findings in larger cohorts and explore the integration of these biomarkers into clinical practice for better disease management and patient care.