Proteomic profiles of incident mild cognitive impairment and Alzheimer's disease among adults with Down syndrome

Hall

et al. 2021

Alzheimer's & Dementia

Self Cite

Introduction: No large-scale characterizations of neurofilament light chain (NfL) have been conducted in diverse populations. Methods: Baseline data were analyzed among n = 890 Mexican Americans and n = 813 non-Hispanic Whites from the multi-ethnic Health & Aging Brain among Latino Elders (HABLE) study. Plasma NfL was measured on the Simoa platform.Results: In unadjusted models, NfL was significantly associated with age (P < .001), hypertension (P < .001), dyslipidemia (P = .02), and diabetes (P < .001). Covarying for age and sex, NfL was associated with neurodegeneration (P < .001) and global amyloid burden levels (P = .02) in a subset with available data. NfL levels were significantly associated with diagnostic groups (Normal Cognition [NC], mild cognitive impairment [MCI], Dementia; P < .001); however, there was no cut-score that yielded acceptable diagnostic accuracy. NfL levels produced a sensitivity of 0.60 and specificity of 0.78 with negative predictive value of 89% for detecting amyloid positivity.Discussion: Plasma NfL levels are significantly impacted by age and medical comorbidities that are common among older adults, which complicate its utility as a diagnostic biomarker

Section: Introductionmentioning

confidence: 99%

Characterizing plasma NfL in a community‐dwelling multi‐ethnic cohort: Results from the HABLE study

O’Bryant

Hall

et al. 2021

Alzheimer's & Dementia

Self Cite

“…Niklas et al binarized the AT(N) markers (A: CSF Aβ42 and amyloid-PET; T: CSF phosphorylated tau and tau PET; and N: hippocampal volume, temporal cortical thickness, and CSF neurofilament light (NfL)) and found that using different AT(N) variants might cause important prognostic information to be lost because they were not interchangeable, and that optimal variants differ by clinical stage [ 5 ]. Blood-based biomarkers represent a significant alternative to a primary care-based screening algorithm for AD, given the high prevalence of the disease [ 3 , 6 , 7 , 8 , 9 , 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

“…Most AD biomarker identification is conducted using only one type of blood fraction [ 3 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ]. Although both serum and plasma have been used in developing blood-based biomarker profiles, serum has been used more frequently and has demonstrated higher sensitivity in AD detection [ 6 , 7 , 8 , 9 , 10 , 11 ] than plasma. Combined assays from each of the blood fractions has not been used in blood-based biomarker profiling.…”

Section: Introductionmentioning

confidence: 99%

Combination of Serum and Plasma Biomarkers Could Improve Prediction Performance for Alzheimer’s Disease

Zhang

Johnson

et al. 2022

Genes

Alzheimer’s disease (AD) can be predicted either by serum or plasma biomarkers, and a combination may increase predictive power, but due to the high complexity of machine learning, it may also incur overfitting problems. In this paper, we investigated whether combining serum and plasma biomarkers with feature selection could improve prediction performance for AD. 150 D patients and 150 normal controls (NCs) were enrolled for a serum test, and 100 patients and 100 NCs were enrolled for the plasma test. Among these, 79 ADs and 65 NCs had serum and plasma samples in common. A 10 times repeated 5-fold cross-validation model and a feature selection method were used to overcome the overfitting problem when serum and plasma biomarkers were combined. First, we tested to see if simply adding serum and plasma biomarkers improved prediction performance but also caused overfitting. Then we employed a feature selection algorithm we developed to overcome the overfitting problem. Lastly, we tested the prediction performance in a 10 times repeated 5-fold cross validation model for training and testing sets. We found that the combined biomarkers improved AD prediction but also caused overfitting. A further feature selection based on the combination of serum and plasma biomarkers solved the problem and produced an even higher prediction performance than either serum or plasma biomarkers on their own. The combined feature-selected serum–plasma biomarkers may have critical implications for understanding the pathophysiology of AD and for developing preventative treatments.

“…This number is projected to nearly triple by 2060 ( Prevention, 2021 ). Machine Learning (ML) methods for AD and AD Related Dementias (ADRDs) is growing faster than ever before ( Waring et al, 2008 ; Magnin et al, 2009 ; O'Bryant et al, 2011a ; O'Bryant et al, 2011b ; O'Bryant et al, 2013 ; O'Bryant et al, 2014 ; Weiner et al, 2015 ; O'Bryant et al, 2016 ; O'Bryant et al, 2017 ; Grassi et al, 2018 ; Hampel et al, 2018 ; O'Bryant et al, 2018 ; Stamate et al, 2019 ; Zetterberg and Burnham, 2019 ; Zhang and Sejdić, 2019 ; Franzmeier et al, 2020 ; O'Bryant et al, 2020 ; Rodriguez et al, 2021 ). A PubMed search using keywords of AD and ML showed that the number of publications related to ML for AD has increased by 146 percent from just two in 2006 to 294 in 2020.…”

Section: Introductionmentioning

confidence: 99%

“…A PubMed search using keywords of AD and ML showed that the number of publications related to ML for AD has increased by 146 percent from just two in 2006 to 294 in 2020. For example, O'Bryant et al developed a Support Vector Machine (SVM) model with 398 plasma samples obtained from adults with Down syndrome to predict incident mild cognitive impairment (MCI) (AUC = 0.92) and incident AD (AUC = 0.88) ( O'Bryant et al, 2020 ). O’Bryant et al also developed a precision medicine model for targeted NSAID therapy in AD based on data collected from a previously conducted clinical trial.…”

Section: Introductionmentioning

confidence: 99%

Accelerating Hyperparameter Tuning in Machine Learning for Alzheimer’s Disease With High Performance Computing

Zhang

Johnson

et al. 2021

Front. Artif. Intell.

Self Cite

Driven by massive datasets that comprise biomarkers from both blood and magnetic resonance imaging (MRI), the need for advanced learning algorithms and accelerator architectures, such as GPUs and FPGAs has increased. Machine learning (ML) methods have delivered remarkable prediction for the early diagnosis of Alzheimer’s disease (AD). Although ML has improved accuracy of AD prediction, the requirement for the complexity of algorithms in ML increases, for example, hyperparameters tuning, which in turn, increases its computational complexity. Thus, accelerating high performance ML for AD is an important research challenge facing these fields. This work reports a multicore high performance support vector machine (SVM) hyperparameter tuning workflow with 100 times repeated 5-fold cross-validation for speeding up ML for AD. For demonstration and evaluation purposes, the high performance hyperparameter tuning model was applied to public MRI data for AD and included demographic factors such as age, sex and education. Results showed that computational efficiency increased by 96%, which helped to shed light on future diagnostic AD biomarker applications. The high performance hyperparameter tuning model can also be applied to other ML algorithms such as random forest, logistic regression, xgboost, etc.