Development and Validation of a Predictive Model for Depression Risk in Patients with Amyotrophic Lateral Sclerosis

Man Liu^1,2Tongyang Niu^1,2Xinyi Zhang^1,2Ziyao Zhang^1,2Luqi Zhao^1,2Jiaqi Li^1,2Siyu Fu^1,2Meiqi Han^1,2Rui Li^1,2Hui Dong^1,2*Yaling Liu^1,2*

• ¹The Second Hospital of Hebei Medical University Department of Neurology, Shijiazhuang, China
• ²The Second Hospital of Hebei Medical University Key Laboratory of Neurology of Hebei Province, Shijiazhuang, China

Introduction: Depression is a severe neuropsychiatric manifestation in patients with amyotrophic lateral sclerosis (ALS), substantially impacting their quality of life and exacerbating caregiver burden, due to the need for different approaches in clinical care. However, a predictive model for the risk of depression in patients with ALS is lacking. This study aimed to develop and validate a predictive model using routinely accessible clinical and laboratory indicators to identify patients at high risk of depression. Methods: Patients with ALS who were hospitalized in the Department of Neurology at the Second Hospital of Hebei Medical University between March 2017 and December 2024 were included. Basic clinical data, laboratory test results, and relevant questionnaire scores were collected, and patients were divided into depressed and non-depressed groups. The least absolute shrinkage and selection operator regression and multivariate logistic regression analyses were applied for variable selection and model construction. Model performance was evaluated using the area under the receiver operating characteristic curve, calibration curves, decision curve analysis, and clinical impact curves, with internal validation performed via bootstrap resampling. Results: Depression was observed in 33.9% of patients. Significant predictors included educational level, sleep disorders, anxiety, Revised Amyotrophic Lateral Sclerosis Functional Rating Scale total scores, C-reactive protein levels, and the Systemic Inflammation Response Index. The final model demonstrated good predictive accuracy and clinical applicability. A depression risk scoring table was further developed based on the coefficients of the logistic regression. Conclusions: The nomogram and the scoring table offer a reliable and practical approach for clinicians to identify patients with ALS who are at high risk for depression and enable early psychological intervention in clinical settings.