Artificial Intelligence in Dementia with Lewy Bodies — Current Applications, Diagnostic Challenges, and Future Perspectives

Abstract

Dementia with Lewy bodies (DLB) is a clinically and biologically heterogeneous neurodegenerative disorder characterised by cognitive impairment together with variable combinations of cognitive fluctuations, recurrent visual hallucinations, rapid eye movement sleep behaviour disorder, parkinsonism, autonomic dysfunction, and other neurological and neuropsychiatric manifestations. Diagnostic uncertainty remains substantial because DLB overlaps clinically with Alzheimer’s disease (AD), Parkinson’s disease dementia, vascular cognitive impairment, and other neurodegenerative disorders, while mixed neuropathology is common. Artificial intelligence (AI), including machine-learning and deep-learning approaches, offers an opportunity to integrate heterogeneous clinical, neuropsychological, neuroimaging, molecular, electrophysiological, and longitudinal data. Current research has investigated AI for differential diagnosis, neuroimaging analysis, multimodal biomarker integration, prodromal risk prediction, prognosis, and digital monitoring. More recently, multimodal biomarker studies in mild cognitive impairment with Lewy bodies have suggested that combinations of MRI, EEG, and plasma markers may provide additional prognostic information beyond cognitive testing alone. However, these findings should not be interpreted as evidence that AI is ready for autonomous clinical diagnosis. Explainable AI may improve transparency and facilitate clinical interpretation, but explanations themselves require validation and should not be regarded as evidence of causality. Future research should prioritise large multicentre longitudinal cohorts, biologically informed reference standards, multimodal and federated learning, calibrated probabilistic prediction, digital biomarkers, and prospective evaluation of clinical utility.