Abstract
Objective. This study aims to develop and evaluate a nomogram for predicting the risk of chronic fatigue syndrome (CFS)‐like symptoms in university students diagnosed with infectious mononucleosis (IM), using clinical characteristics and laboratory findings as predictive variables. The nomogram will be designed to assist healthcare providers in assessing the likelihood of CFS‐like symptoms developing post‐IM, rather than providing a definitive diagnosis of CFS. Methods. Clinical data and laboratory findings were collected from university students with IM. The variables included age, gender, smoking and drinking habits, relationship status, university grade, residence registration, number of symptoms and signs (NSS), body mass index (BMI), C‐reactive protein (CRP) level, neutrophil–lymphocyte ratio (NLR), platelet–lymphocyte ratio (PLR), monocyte–lymphocyte ratio (MLR), aspartate aminotransferase to alanine aminotransferase ratio (AST/ALT, DeRitis), basophil percentage (Baso%), eosinophil percentage (Eos%), and albumin‐to‐globulin ratio (ALB/GLO). LASSO regression analysis was employed to identify significant predictors of CFS‐like symptoms. A nomogram model was constructed based on these predictors and evaluated using performance metrics such as the concordance index (C‐index), area under the curve (AUC), calibration curves, and decision curve analysis. Results. The LASSO regression analysis identified the NSS, CRP, NLR, and MLR as significant predictors of CFS‐like symptoms in university students with IM. The nomogram demonstrated robust predictive performance, with a C‐index of 0.846 (95% CI: 0.790–0.902) in the training set and 0.867 (95% CI: 0.8–0.954) in the validation set. High AUC values indicated excellent overall predictive accuracy. Calibration curves revealed a close match between predicted and observed probabilities. Additionally, decision curve analysis showed positive net benefits across a broad spectrum of threshold probabilities, underscoring the nomogram’s clinical applicability. Conclusion. The nomogram developed in this study serves as a valuable predictive tool for assessing the risk of CFS‐like symptoms in university students with IM. The identified predictors, including NLR, the NSS, CRP, and MLR, can assist clinicians in evaluating individual risk profiles and inform decision‐making processes. This nomogram model advances personalized risk assessment for the development of CFS‐like symptoms in IM‐affected university students.