Springer eBooks, Journal Year: 2023, Volume and Issue: unknown, P. 253 - 266
Published: Jan. 1, 2023
Language: Английский
Diagnostics, Journal Year: 2025, Volume and Issue: 15(4), P. 434 - 434
Published: Feb. 11, 2025
Artificial intelligence (AI) has emerged as a transformative force in psychiatry, improving diagnostic precision, treatment personalization, and early intervention through advanced data analysis techniques. This review explores recent advancements AI applications within focusing on EEG ECG analysis, speech natural language processing (NLP), blood biomarker integration, social media utilization. EEG-based models have significantly enhanced the detection of disorders such depression schizophrenia spectral connectivity analyses. ECG-based approaches provided insights into emotional regulation stress-related conditions using heart rate variability. Speech frameworks, leveraging large (LLMs), improved cognitive impairments psychiatric symptoms nuanced linguistic feature extraction. Meanwhile, analyses deepened our understanding molecular underpinnings mental health disorders, analytics demonstrated potential for real-time surveillance. Despite these advancements, challenges heterogeneity, interpretability, ethical considerations remain barriers to widespread clinical adoption. Future research must prioritize development explainable models, regulatory compliance, integration diverse datasets maximize impact care.
Language: Английский
Citations
3
Deleted Journal, Journal Year: 2024, Volume and Issue: 3(2)
Published: July 3, 2024
Abstract Extended reality (XR) technologies have experienced cycles of development—“summers” and “winters”—for decades, but their overall trajectory is one increasing uptake. In recent years, immersive extended (IXR) applications, a kind XR that encompasses virtual (VR) augmented (AR) environments, become especially prevalent. The European Union (EU) exploring regulating this type technology, article seeks to support endeavor. It outlines safety privacy harms associated with IXR, analyzes what extent the existing EU framework for digital governance—including General Data Protection Regulation, Product Safety Legislation, ePrivacy Directive, Digital Markets Act, Services AI Act—addresses these harms, offers some recommendations legislators on how fill regulatory gaps improve current approaches governance IXR.
Language: Английский
Citations
12
Journal of Alzheimer s Disease, Journal Year: 2024, Volume and Issue: 99(1), P. 1 - 20
Published: April 16, 2024
Alzheimer's disease (AD) is a chronic neurodegenerative disorder with global impact. The past few decades have witnessed significant strides in comprehending the underlying pathophysiological mechanisms and developing diagnostic methodologies for AD, such as neuroimaging approaches. Neuroimaging techniques, including positron emission tomography magnetic resonance imaging, revolutionized field by providing valuable insights into structural functional alterations brains of individuals AD. These imaging modalities enable detection early biomarkers amyloid-β plaques tau protein tangles, facilitating precise diagnosis. Furthermore, emerging technologies encompassing blood-based neurochemical profiling exhibit promising results identification specific molecular signatures integration machine learning algorithms artificial intelligence has enhanced predictive capacity these tools when analyzing complex datasets. In this review article, we will highlight not only some most used approaches neurodegeneration research but focus much more on new like intelligence, emphasizing their application realm advancements hold immense potential intervention, thereby paving way personalized therapeutic strategies ultimately augmenting quality life affected
Language: Английский
Citations
11
Journal of the American Heart Association, Journal Year: 2024, Volume and Issue: 13(2)
Published: Jan. 16, 2024
ABSTRACT Most research using digital technologies builds on existing methods for staff‐administered evaluation, requiring a large investment of time, effort, and resources. Widespread use personal mobile devices provides opportunities continuous health monitoring without active participant engagement. Home‐based sensors show promise in evaluating behavioral features near real time. Digital across these methodologies can detect precise measures cognition, mood, sleep, gait, speech, motor activity, behavior patterns, additional relevant to health. As neurodegenerative condition with insidious onset, Alzheimer disease other dementias (AD/D) represent key target advances symptoms. Studies date the predictive power inconsistent approaches characterize measures. Comparison between different collection supports passive settings which engagement are not feasible. Additional studies that analyze how multiple data streams together improve prediction cognitive impairment early‐stage AD needed. Given long timeline progression from normal diagnosis, will more easily make extended longitudinal follow‐up possible. Through American Heart Association–funded Strategically Focused Research Network, Boston University investigative team deployed platform involving wide range address gaps practice. Much is needed thoroughly evaluate limitations monitoring. Multidisciplinary collaborations establish legal ethical frameworks ensuring be conducted at scale while protecting privacy security, especially vulnerable populations.
Language: Английский
Citations
7
Journal of Alzheimer s Disease, Journal Year: 2024, Volume and Issue: 98(3), P. 793 - 823
Published: March 10, 2024
Background: The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer’s disease (AD), the most common type dementia, become frequent too. Objective: goals this work are present state-of-the-art studies focused on automatic diagnosis prognosis AD its early stages, mainly mild cognitive impairment, predicting how research topic may change future. Methods: Articles found existing literature needed fulfill several selection criteria. Among others, their classification methods were based artificial neural networks (ANNs), including deep learning, data not from brain signals or neuroimaging techniques used. Considering our criteria, 42 articles published last decade finally selected. Results: medically significant results shown. Similar quantities shallow ANNs found. Recurrent transformers with speech longitudinal studies. Convolutional (CNNs) popular gait combined others modular approaches. Above one third cross-sectional utilized multimodal data. Non-public datasets frequently used studies, whereas opposite ones. databases indicated, which will be helpful for future researchers field. Conclusions: introduction CNNs superb did negatively affect usage other modalities. In fact, new ones emerged.
Language: Английский
Citations
6
Journal of Chemical Education, Journal Year: 2024, Volume and Issue: 101(6), P. 2466 - 2474
Published: May 26, 2024
Instructors use of Artificial Intelligence (AI) language models (i.e., chatbots) as an educational resource will require understanding students' AI literacy, namely their ability to critically reflect on the relevance, trustworthiness, and quality these tools in context chemistry. This study sought describe literacy via open-ended surveys general chemistry I students upper-level elective. Thematic analysis was used create a deeper when considering chatbots. Based responses, they were categorized either with reservations toward chatbots or without Thematically, tended reason utility/benefit tool concern accuracy tool. Results suggest that are more range between two extremes. new can support instructional practices inform future research efforts literacy.
Language: Английский
Citations
5
Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring, Journal Year: 2022, Volume and Issue: 14(1)
Published: Jan. 1, 2022
Language: Английский
Citations
21
Frontiers in Neurology, Journal Year: 2024, Volume and Issue: 15
Published: April 4, 2024
Objective Early detection of cognitive impairment in the elderly is crucial for diagnosis and appropriate care. Brief, cost-effective screening instruments are needed to help identify individuals who require further evaluation. This study presents preliminary data on a new technology using automated voice recording analysis software Spanish population. Method Data were collected from 174 Spanish-speaking clinically diagnosed as cognitively normal (CN, n = 87) or impaired (mild [MCI], 63; all-cause dementia, 24). Participants recorded performing four common language tasks (Animal fluency, alternating fluency [sports fruits], phonemic “F” Cookie Theft Description). Recordings processed via text-transcription digital-signal processing techniques capture neuropsychological variables audio characteristics. A training sample 122 subjects with similar demographics across groups was used develop an algorithm detect impairment. Speech task features five independent machine learning (ML) models compute scores between 0 1, final constructed repeated cross-validation. socio-demographically balanced subset 52 participants test algorithm. Analysis covariance (ANCOVA), covarying demographic characteristics, predict logistically-transformed scores. Results Mean logit significantly different testing ( p < 0.01). Comparisons CN (MCI + dementia) MCI resulted AUC 0.93/0.90, overall accuracy 88.4%/87.5%, sensitivity 87.5/83.3, specificity 89.2/89.2, respectively. Conclusion Findings provide initial support utility this speech tool speakers. Additional validate larger more diverse clinical populations.
Language: Английский
Citations
4
Mayo Clinic Proceedings Digital Health, Journal Year: 2025, Volume and Issue: unknown, P. 100205 - 100205
Published: March 1, 2025
Language: Английский
Citations
0
Computer Speech & Language, Journal Year: 2023, Volume and Issue: 81, P. 101514 - 101514
Published: March 15, 2023
Language: Английский
Citations
10