Frontotemporal dementia: a systematic review of artificial intelligence approaches in differential diagnosis

Frontiers in Aging Neuroscience, Journal Year: 2025, Volume and Issue: 17

Published: April 10, 2025

Frontotemporal dementia (FTD) is a neurodegenerative disorder characterized by progressive degeneration of the frontal and temporal lobes, leading to significant changes in personality, behavior, language abilities. Early accurate differential diagnosis between FTD, its subtypes, other dementias, such as Alzheimer's disease (AD), crucial for appropriate treatment planning patient care. Machine learning (ML) techniques have shown promise enhancing diagnostic accuracy identifying complex patterns clinical neuroimaging data that are not easily discernible through conventional analysis. This systematic review, following PRISMA guidelines registered PROSPERO, aimed assess strengths limitations current ML models used differentiating FTD from neurological disorders. A comprehensive literature search 2013 2024 identified 25 eligible studies involving 6,544 patients with dementia, including 2,984 3,437 AD, 103 mild cognitive impairment (MCI) 20 Parkinson's or probable Lewy bodies (PDD/DLBPD). The review found Support Vector Machines (SVMs) were most frequently technique, often applied electrophysiological data. Deep methods, particularly convolutional neural networks (CNNs), also been increasingly adopted, demonstrating high distinguishing dementias. integration multimodal data, neuroimaging, EEG signals, neuropsychological assessments, has suggested enhance accuracy. showed strong potential improving diagnosis, but challenges like small sample sizes, class imbalance, lack standardization limit generalizability. Future research should prioritize development standardized protocols, larger datasets, explainable AI facilitate ML-based tools into real-world practice. https://www.crd.york.ac.uk/PROSPERO/view/CRD42024520902.

Language: Английский

---

Metal Toxicity and Dementia Including Frontotemporal Dementia: Current State of Knowledge

Antioxidants, Journal Year: 2024, Volume and Issue: 13(8), P. 938 - 938

Published: Aug. 1, 2024

Frontotemporal dementia (FTD) includes a number of neurodegenerative diseases, often with early onset (before 65 years old), characterized by progressive, irreversible deficits in behavioral, linguistic, and executive functions, which are difficult to diagnose due their similar phenotypic characteristics other dementias psychiatric disorders. The genetic contribution is utmost importance, although environmental risk factors also play role its pathophysiology. In fact, some metals known produce free radicals, which, accumulating the brain over time, can induce oxidative stress, inflammation, protein misfolding, all these being key features FTD conditions. Therefore, present review aims summarize current evidence about FTD-mainly dealing toxic metal exposure-since identification such potential lead diagnosis promotion policies interventions. This would allow us, reducing exposure pollutants, potentially affect society at large positive manner, decreasing burden conditions on affected individuals overall. Future perspectives, including application Artificial Intelligence principles field, related found so far, introduced.

Language: Английский

---

Machine learning for medical image classification

Academia Medicine, Journal Year: 2024, Volume and Issue: 1(4)

Published: Dec. 23, 2024

This review article focuses on the application of machine learning (ML) algorithms in medical image classification. It highlights intricate process involved selecting most suitable ML algorithm for predicting specific conditions, emphasizing critical role real-world data testing and validation. navigates through various methods utilized healthcare, including Supervised Learning, Unsupervised Self-Supervised Deep Neural Networks, Reinforcement Ensemble Methods. The challenge lies not just selection an but identifying appropriate one a task as well, given vast array options available. Each unique dataset requires comparative analysis to determine best-performing algorithm. However, all available is impractical. examines performance recent studies, focusing their applications across different imaging modalities diagnosing conditions. provides summary these offering starting point those seeking select conditions modalities.

Language: Английский

---

Diffusion Tensor Imaging Analysis Along the Perivascular Space (DTI-ALPS) in Normal Pressure Hydrocephalus: A Review of Recent Advances

Cureus, Journal Year: 2025, Volume and Issue: unknown

Published: April 7, 2025

Glymphatic dysfunction is linked to neurodegenerative diseases, and imaging markers of this may aid in diagnosis prognosis. has been proposed as a key mechanism the pathogenesis normal pressure hydrocephalus (NPH). Advanced magnetic resonance techniques, especially diffusion tensor imaging, have used evaluate glymphatic function. Diffusion analysis along perivascular space (DTI-ALPS) noninvasive metric that correlates with function recently studied variety diseases. We aim summarize studies evaluating association between DTI-ALPS index values NPH outcomes. Current suggest lower patients compared healthy controls. The correlated other imaging-based clinical endpoints. However, limitations current literature include small cohort sizes; future are needed larger, heterogeneous cohorts validate these trends. Thus, shows promise valuable tool for diagnosing NPH, predicting treatment response, assessing disease progression.

Language: Английский

---

Resistance Exercise Training as a New Trend in Alzheimer’s Disease Research: From Molecular Mechanisms to Prevention

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(13), P. 7084 - 7084

Published: June 27, 2024

Alzheimer's disease is a pathology characterized by the progressive loss of neuronal connections, which leads to gray matter atrophy in brain. most prevalent type dementia and has been classified into two types, early onset, associated with genetic factors, late environmental factors. One greatest challenges regarding high economic cost involved, why number studies aimed at prevention treatment have increased. possible approach use resistance exercise training, given that it shown neuroprotective effects disease, such as increasing cortical hippocampal volume, improving neuroplasticity, promoting cognitive function throughout life cycle. However, how training specifically prevents or ameliorates not fully characterized. Therefore, aim this review was identify molecular basis could prevent treat disease.

Language: Английский

---