Prediction of early-wheelchair dependence in multiple system atrophy based on machine learning algorithm: A prospective cohort study

Abstract

Objective

The predictive factors for wheelchair dependence in patients with multiple system atrophy (MSA) are unclear. We aimed to explore the predictive factors for early-wheelchair dependence in patients with MSA focusing on clinical features and blood biomarkers.

Methods

This is a prospective cohort study. This study included patients diagnosed with MSA between January 2014 and December 2019. At the deadline of October 2021, patients met the diagnosis of probable MSA were included in the analysis. Random forest (RF) was used to establish a predictive model for early-wheelchair dependence. Accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of the model.

Results

Altogether, 100 patients with MSA including 49 with wheelchair dependence and 51 without wheelchair dependence were enrolled in the RF model. Baseline plasma neurofilament light chain (NFL) levels were higher in patients with wheelchair dependence than in those without (P = 0.037). According to the Gini index, the five major predictive factors were disease duration, age of onset, Unified MSA Rating Scale (UMSARS)-II score, NFL, and UMSARS-I score, followed by C-reactive protein (CRP) levels, neutrophil-to-lymphocyte ratio (NLR), UMSARS-IV score, symptom onset, orthostatic hypotension, sex, urinary incontinence, and diagnosis subtype. The sensitivity, specificity, accuracy, and AUC of the RF model were 70.82 %, 74.55 %, 72.29 %, and 0.72, respectively.

Conclusion

Besides clinical features, baseline features including NFL, CRP, and NLR were potential predictive biomarkers of early-wheelchair dependence in MSA. These findings provide new insights into the trials regarding early intervention in MSA.