Multi-feature computational framework for combined signatures of dementia in underrepresented settings

Objective: The differential diagnosis of behavioral variant frontotemporal dementia (bvFTD) and Alzheimer's disease (AD) remains challenging in underrepresented, underdiagnosed groups, including Latinos, as advanced biomarkers are rarely available. Recent guidelines for the study of dementia highlight the critical role of biomarkers. Thus, novel cost-effective complementary approaches are required in clinical settings. Approach: We developed a novel framework based on a gradient boosting machine learning classifier, tuned by Bayesian optimization, on a multifeature multimodal approach (combining demographic, neuropsychological, MRI, and EEG/fMRI connectivity data) to characterize neurodegeneration using site harmonization and sequential feature selection. We assessed 54 bvFTD and 76 AD patients and 152 healthy controls (HCs) from a Latin American consortium (ReDLat). Main results: The multimodal model yielded high AUC classification values (bvFTD patients vs. HCs: 0.93 (±0.01); AD patients vs. HCs: 0.95 (±0.01); bvFTD vs. AD patients: 0.92 (±0.01)). The feature selection approach successfully filtered noninformative multimodal markers (from thousands to dozens). Results proved robust against multimodal heterogeneity, sociodemographic variability, and missing data. Significance: The model accurately identified dementia subtypes using measures readily available in underrepresented settings, with a similar performance than advanced biomarkers. This approach, if confirmed and replicated, may potentially complement clinical assessments in developing countries.