Molecular stratification of frontotemporal dementia through multi-omics integration and machine learning
Year: 2026
Type: article
Abstract: Frontotemporal dementia (FTD) comprises clinically diverse behavioral, language, and motor-associated syndromes, while frontotemporal lobar degeneration (FTLD) refers to the underlying neuropathological spectrum. This distinction matters because similar clinical presentations can reflect different proteinopathies, and TDP-43 pathology also occurs in conditions such as limbic-predominant age-related TDP-43 encephalopathy. We critically review the evidence for molecular stratification across clinical phenotype, genetic etiology, neuropathological subtype, and disease stage, focusing on findings from longitudinal cohorts and genomic, transcriptomic, proteomic, and imaging studies. Studies in genetic FTD support serum neurofilament light chain as a marker of neuroaxonal injury and proximity to symptomatic conversion, although it does not identify the underlying proteinopathy. Cerebrospinal fluid (CSF) proteomic panels have shown encouraging discrimination of clinically defined FTD from controls or Alzheimer disease in independent cohorts, but reproducible differentiation of FTLD-tau from FTLD-TDP remains unresolved. Genetic and proteomic studies have also identified subtype-associated lysosomal, synaptic, RNA-processing, and inflammatory signatures, whose clinical specificity and prospective utility require further study. Machine learning can support feature selection and multimodal analysis, but matched evidence is limited that comprehensive multi-omics models outperform simpler biomarkers or clinical baselines in pathology-confirmed cohorts. We propose an evidence-based approach in which the intended use, biological compartment, disease stage, reference diagnosis, and external validation are specified before molecular stratification claims are made. This approach can guide the design of biomarker studies and genetically informed trials without treating molecular association, computational prediction, or target engagement as proof of pathological classification or treatment efficacy.
Source: Molecular Medicine
Authors: Mohammed Ageeli Hakami, Faez Iqbal Khan
Language: English
Subfield: Psychiatry and Mental health
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,190
Award: G9001400183
OpenAlex ID: W7237027031
