A remote speech‐based AI system to screen for early Alzheimer's disease via smartphones

Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring, Journal Year: 2022, Volume and Issue: 14(1)

Published: Jan. 1, 2022

Language: Английский

---

Real-world prediction of preclinical Alzheimer’s disease with a deep generative model

Artificial Intelligence in Medicine, Journal Year: 2023, Volume and Issue: 144, P. 102654 - 102654

Published: Sept. 4, 2023

Amyloid positivity is an early indicator of Alzheimer's disease and necessary to determine the disease. In this study, a deep generative model utilized predict amyloid cognitively normal individuals using proxy measures, such as structural MRI scans, demographic variables, cognitive scores, instead invasive direct measurements. Through its remarkable efficacy in handling imperfect datasets caused by missing data or labels, imbalanced classes, outperforms previous studies widely used machine learning approaches with AUROC 0.8609. Furthermore, study illuminates model's adaptability diverse clinical scenarios, even when feature sets diagnostic criteria differ from training data. We identify brain regions variables that contribute most classification, including lateral occipital lobes, posterior temporal lobe, APOE ϵ4 allele. Taking advantage models, our approach can not only provide inexpensive, non-invasive, accurate diagnostics for preclinical disease, but also meet real-world requirements translation model, transferability interpretability.

Language: Английский

---

Plasma neurofilament light chain predicts Alzheimer's disease in patients with subjective cognitive decline and mild cognitive impairment: A cross‐sectional and longitudinal study

European Journal of Neurology, Journal Year: 2023, Volume and Issue: 31(1)

Published: Oct. 5, 2023

We aimed to evaluate the accuracy of plasma neurofilament light chain (NfL) in predicting Alzheimer's disease (AD) and progression cognitive decline patients with subjective (SCD) mild impairment (MCI).

Language: Английский

---

Automated Quality Evaluation Index for Arterial Spin Labeling Derived Cerebral Blood Flow Maps

Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: 60(6), P. 2497 - 2508

Published: Feb. 24, 2024

Background Arterial spin labeling (ASL) derived cerebral blood flow (CBF) maps are prone to artifacts and noise that can degrade image quality. Purpose To develop an automated objective quality evaluation index (QEI) for ASL CBF maps. Study Type Retrospective. Population Data from N = 221 adults, including patients with Alzheimer's disease (AD), Parkinson's disease, traumatic brain injury. Field Strength/Sequence Pulsed or pseudocontinuous acquired at 3 T using non‐background suppressed 2D gradient‐echo echoplanar imaging background 3D spiral spin‐echo readouts. Assessment The QEI was developed 101 rated as unacceptable, poor, average, excellent by two neuroradiologists validated 1) leave‐one‐out cross validation, 2) assessing if reproducibility in 53 cognitively normal adults correlates inversely QEI, 3) iterative discarding of low data improves the Cohen's d effect size differences between preclinical AD (N 27) controls 53), 4) comparing manual ratings 50 maps, 5) another metric. Statistical Tests Inter‐rater reliability vs. were quantified Pearson's correlation. P < 0.05 considered significant. Results correlation ( R 0.83, CI: 0.76–0.88) similar 0.56) inter‐rater 0.81, 0.73–0.87) data. correlated negatively −0.74, −0.84 −0.59) QEI. improved 0.72, 0.59–0.82) discarded iteratively. 0.86, 0.77–0.92) 0.09) 0.78, 0.64–0.87). 0.87, significantly better than did existing approach 0.54, 0.30–0.72). Conclusion Automated performed similarly provide scalable control. Evidence Level 2 Technical Efficacy Stage 1

Language: Английский

---

Blood Derived Amyloid Biomarkers for Alzheimer’s Disease Prevention

The Journal of Prevention of Alzheimer s Disease, Journal Year: 2021, Volume and Issue: unknown, P. 1 - 10

Published: Jan. 1, 2021

Language: Английский

---