Unveiling an ALS Blood Transcriptomic Signature: A Machine Learning Classifier Distinct from Neurodegenerative Controls.

The absence of accessible and reliable biomarkers constitutes a critical barrier for the early diagnosis and stratification of neurodegenerative diseases. While peripheral blood offers a minimally invasive window into systemic pathophysiology, identifying molecular signatures that survive biological heterogeneity and technical noise remains an unresolved challenge. In this study, this issue was addressed through a comparative systemic transcriptomic analysis of Amyotrophic Lateral Sclerosis (ALS), Alzheimer’s disease (AD), and Parkinson’s disease (PD) in whole blood, implementing a comprehensive workflow integrating unsupervised network analysis and supervised machine-learning methods. By employing LASSO regression and cross-validation across independent external cohorts, a stable and specific transcriptomic signature for ALS was identified, comprising key crosstalk genes involved in systemic immune dysregulation and microglial function, including CTSS, PTEN, IL18, PTPRC, and CSF1R. In contrast, AD and PD exhibited weak transcriptomic signatures with poor predictive reproducibility, suggesting a distinctive systemic pathology in ALS. In addition, the study confirms the superiority of linear modeling for this genomic signature: while complex non-linear algorithms, specifically Radial Basis Function (RBF) kernel Support Vector Machine (SVM) and Random Forest, displayed high initial performance, they collapsed due to overfitting during external validation. Conversely, the linear LASSO model demonstrated superior robustness and generalizability (AUC 0.74). In conclusion, this study not only defines a unique systemic immunotranscriptomic signature for ALS, distinguishable from other neurodegenerative pathologies, but also establishes interpretability and linear simplicity as essential factors for developing reproducible blood-based biomarkers with clinical translational potential.