Related Experiment Video
Updated: Aug 12, 2025
Home-Based Monitor for Gait and Activity Analysis
Published on: August 8, 2019
Prediction of early-wheelchair dependence in multiple system atrophy based on machine learning algorithm: A
Lingyu Zhang1, Yanbing Hou1, Xiaojing Gu1
1Department of Neurology, Laboratory of Neurodegenerative Disorders, Rare Diseases Center, National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China.
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.
Insights
Predictors for wheelchair dependence in multiple system atrophy (MSA) include disease duration, age, and plasma neurofilament light chain (NFL) levels. These factors aid in early identification and intervention strategies for MSA patients.
Area of Science:
- Neurology
- Biomarkers
- Clinical Research
Background:
- Predictive factors for wheelchair dependence in multiple system atrophy (MSA) remain unclear.
- Early identification of wheelchair dependence is crucial for timely intervention in MSA patients.
Purpose of the Study:
- To explore predictive factors for early wheelchair dependence in MSA patients.
- To identify clinical features and blood biomarkers that predict wheelchair dependence.
Main Methods:
- Prospective cohort study including 100 probable MSA patients.
- Random forest (RF) model used to establish a predictive model for early wheelchair dependence.
- Model performance evaluated using accuracy, sensitivity, specificity, and AUC.
Main Results:
- Higher baseline plasma neurofilament light chain (NFL) levels were observed in patients with wheelchair dependence.
- Key predictive factors identified: disease duration, age of onset, UMSARS-II, NFL, UMSARS-I, CRP, and NLR.
- RF model achieved 72.29% accuracy, 70.82% sensitivity, 74.55% specificity, and 0.72 AUC.
Conclusions:
- Baseline NFL, CRP, and NLR are potential predictive biomarkers for early wheelchair dependence in MSA.
- Clinical features and blood biomarkers offer insights for early intervention trials in MSA.
