Multiomic Enriched Blood-Derived Digital Signatures Reveal Mechanistic and Confounding Disease Clusters for Differential Diagnosis

Abstract: Understanding disease relationships through blood biomarkers offers a pathway toward data driven taxonomy and precision medicine. We constructed a digital blood twin from 103 disease signatures comprising longitudinal hematological and biochemical analytes. Profiles were standardized into a unified disease analyte matrix, and pairwise Pearson correlations were computed to assess similarity. Hierarchical clustering revealed robust grouping of hematopoietic disorders, while metabolic, endocrine, and respiratory diseases were more heterogeneous, reflecting weaker cohesion. To evaluate structure, the tree was cut at a stringent threshold, yielding 16 groups. Enrichment of the largest heterogeneous cluster (Cluster 9) showed convergence on cytokine-signaling pathways, indicating shared immunological and inflammatory mechanisms across clinical boundaries. Dimensionality reduction with PCA and UMAP corroborated these results, consistently separating hematological diseases. Random Forest feature selection identified neutrophils, mean corpuscular volume, red blood cell count, and platelets as the most discriminative analytes, reinforcing hematopoietic markers as key drivers. Collectively, these findings show that blood-derived digital signatures can recover clinically meaningful clusters while revealing mechanistic overlaps across categories. The coherence of hematological diseases contrasts with the dispersion of systemic and metabolic disorders, underscoring both the promise and limits of blood-based classification. This framework highlights the potential of integrating routine laboratory data with computational methods to refine disease ontology, map comorbidities, and advance precision diagnostics.