An official website of the United States government
Abstract Alzheimer’s disease (AD) is a neurogenerative condition characterized by sharp cognitive decline with no confirmed effective treatment or cure. This makes it critically important to identify the symptoms of Alzheimer’s disease in its early stages before significant cognitive deterioration has taken hold and even before any brain morphology and neuropathology are noticeable. In this study, five different multimodal deep neural networks (MDNN), with different architectures, in search of an optimal model for predicting the cognitive test scores for the Mini-Mental State Examination (MMSE) and the modified Alzheimer’s Disease Assessment Scale (ADAS-CoG13) over a span of 60 months (5 years). The multimodal data utilized to train and test the proposed models were obtained from the Alzheimer’s Disease Neuroimaging Initiative study and includes cerebrospinal fluid (CSF) levels of tau and beta-amyloid, structural measures from magnetic resonance imaging (MRI), functional and metabolic measures from positron emission tomography (PET), and cognitive scores from the neuropsychological tests (Cog). The models developed herein delve into two main issues: (1) application merits of single-task vs. multitask for predicting future cognitive scores and (2) whether time-varying input data are better suited than specific timepoints for optimizing prediction results. This model yields a high of 90.27% (SD = 1.36) prediction accuracy (correlation) at 6 months after the initial visit to a lower 79.91% (SD = 8.84) prediction accuracy at 60 months. The analysis provided is comprehensive as it determines the predictions at all other timepoints and all MDNN models include converters in the CN and MCI groups (CNc, MCIc) and all the unstable groups in the CN and MCI groups (CNun and MCIun) that reverted to CN from MCI and to MCI from AD, so as not to bias the results. The results show that the best performance is achieved by a multimodal combined single-task long short-term memory (LSTM) regressor with an input sequence length of 2 data points (2 visits, 6 months apart) augmented with a pretrained Neural Network Estimator to fill in for the missing values.
more »
« less
A Deep-Learning Approach for the Prediction of Mini-Mental State Examination Scores in a Multimodal Longitudinal Study
This study introduces a new multimodal deep regression method to predict cognitive test score in a 5-year longitudinal study on Alzheimer’s disease (AD). The proposed model takes advantage of multimodal data that includes cerebrospinal fluid (CSF) levels of tau and beta-amyloid, structural measures from magnetic resonance imaging (MRI), functional and metabolic measures from positron emission tomography (PET), and cognitive scores from neuropsychological tests (Cog), all with the aim of achieving highly accurate predictions of future Mini-Mental State Examination (MMSE) test scores up to five years after baseline biomarker collection. A novel data augmentation technique is leveraged to increase the numbers of training samples without relying on synthetic data. With the proposed method, the best and most encompassing regressor is shown to achieve better than state-of-the-art correlations of 85.07%(SD=1.59) for 6 months in the future, 87.39% (SD =1.48) for 12 months, 84.78% (SD=2.66) for 18 months, 85.13% (SD=2.19) for 24 months, 81.15% (SD=5.48) for 30 months, 81.17% (SD=4.44) for 36 months, 79.25% (SD=5.85) for 42 months, 78.98% (SD=5.79) for 48 months, 78.93%(SD=5.76) for 54 months, and 74.96% (SD=7.54) for 60 months.
more »
« less
- PAR ID:
- 10275892
- Date Published:
- Journal Name:
- 2020 International Conference on Computational Science and Computational Intelligence (CSCI)
- Page Range / eLocation ID:
- 761 to 766
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Objective: The current cross-sectional study examined cognition and performance-based functional abilities in a continuing care senior housing community (CCSHC) that is comparable to other CCSHCs in the US with respect to residents’ demographic characteristics. Method: Participants were 110 older adult residents of the independent living unit. We assessed sociodemographics, mental health, neurocognitive functioning, and functional capacity. Results: Compared to normative samples, participants performed at or above expectations in terms of premorbid functioning, attention span and working memory, processing speed, timed set-shifting, inhibitory control, and confrontation naming. They performed below expectation in verbal fluency and verbal and visual learning and memory, with impairment rates [31.4% (>1 SD below the mean) and 18.49% (>1.5 SD below the mean)] well above the general population (16% and 7%, respectively). Within the cognitive test battery, two tests of delayed memory were most predictive of a global deficit score. Most cognitive test scores correlated with performance-based functional capacity. Conclusions: Overall, results suggest that a subset of older adults in the independent living sector of CCSHCs are cognitively and functionally impaired and are at risk for future dementia. Results also argue for the inclusion of memory tests in abbreviated screening batteries in this population. We suggest that CCSHCs implement regular cognitive screening procedures to identify and triage those older adults who could benefit from interventions and, potentially, a transition to a higher level of care.more » « less
-
Alzheimer's disease (AD) is a neurodegenerative disorder with slow onset, which could result in the deterioration of the duration of persistent neurological dysfunction. How to identify the informative longitudinal phenotypic neuroimaging markers and predict cognitive measures are crucial to recognize AD at early stage. Many existing models related imaging measures to cognitive status using regression models, but they did not take full consideration of the interaction between cognitive scores. In this paper, we propose a robust low-rank structured sparse regression method (RLSR) to address this issue. The proposed model simultaneously selects effective features and learns the underlying structure between cognitive scores by utilizing novel mixed structured sparsity inducing norms and low-rank approximation. In addition, an efficient algorithm is derived to solve the proposed non-smooth objective function with proved convergence. Empirical studies on cognitive data of the ADNI cohort demonstrate the superior performance of the proposed method.more » « less
-
With the advances in machine learning for the diagnosis of Alzheimer’s disease (AD), most studies have focused on either identifying the subject’s status through classification algorithms or on predicting their cognitive scores through regression methods, neglecting the potential association between these two tasks. Motivated by the need to enhance the prospects for early diagnosis along with the ability to predict future disease states, this study proposes a deep neural network based on modality fusion, kernelization, and tensorization that perform multiclass classification and longitudinal regression simultaneously within a unified multitask framework. This relationship between multiclass classification and longitudinal regression is found to boost the efficacy of the final model in dealing with both tasks. Different multimodality scenarios are investigated, and complementary aspects of the multimodal features are exploited to simultaneously delineate the subject’s label and predict related cognitive scores at future timepoints using baseline data. The main intent in this multitask framework is to consolidate the highest accuracy possible in terms of precision, sensitivity, F1 score, and area under the curve (AUC) in the multiclass classification task while maintaining the highest similarity in the MMSE score as measured through the correlation coefficient and the RMSE for all time points under the prediction task, with both tasks, run simultaneously under the same set of hyperparameters. The overall accuracy for multiclass classification of the proposed KTMnet method is 66.85 ± 3.77. The prediction results show an average RMSE of 2.32 ± 0.52 and a correlation of 0.71 ± 5.98 for predicting MMSE throughout the time points. These results are compared to state-of-the-art techniques reported in the literature. A discovery from the multitasking of this consolidated machine learning framework is that a set of hyperparameters that optimize the prediction results may not necessarily be the same as those that would optimize the multiclass classification. In other words, there is a breakpoint beyond which enhancing further the results of one process could lead to the downgrading in accuracy for the other.more » « less
-
null (Ed.)Engineering Projects in Community Service (EPICS) is a middle and high school program, with a focus on the engineering design process and delivering real solutions to community partners. In order to evaluate the efficacy of the program, a pre-post test design was implemented to examine changes in attitudinal and behavioral measures. Pre-data were collected at the beginning of the school year, and paralleled the program’s registration process to ensure high response rates; post- data were then collected at the end of the school year. Demographic data demonstrate that of all 2018 - 2019 registered EPICS participants (N = 414), 41 percent were female; 66.6 percent were non-white; and 30 percent held first generation student status. Importantly, 68.5 percent of participants reported that neither parent or guardian is an engineer, and 65.7 percent of participants reported that they “definitely will attend” a four-year university. These data suggest that the current sample is ideal for evaluating EPICS as a pre-college engineering education program, because most participants are not experiencing engineering in the home and may be less susceptible to parental pressures for choosing engineering as a college major and potential career, but have salient intentions to attend college. In addition to collecting demographic information, participants completed a series of measures designed to capture attitudes and behaviors toward engineering as a potential career field. The main measures of interest include Engineering Identity and Doing Engineering. Engineering Identity scores reflect participants’ personal and professional identities as engineers; Doing Engineering scores indicate participants’ prior experience with engineering and its related technical skills. Baseline data on the sample reveal average engineering identities (M = 38.41, SD = 6.44, 95% CI [37.77, 39.05]). A series of t-tests was conducted to examine gender differences in these measures. Men reported significantly higher engineering identities (M = 37.65, SD = 6.58) compared to women (M = 39.54, SD = 6.09), t(360) = 2.95, p = .003, F = .037. Men reported stronger and more frequent experiences with engineering, indicated by their higher Doing Engineering scores (M = 13.75, SD = 5.16), compared to women (M = 15.31, SD = 4.69), t(368) = 3.13, p = .002, F = .003. Interestingly, first generation students reported higher engineering identities (M = 37.45, SD = 6.53) compared to non-first generation students (M = 39.66, SD = 5.99), t(375) = 3.46, p = .001, F = 1.39. To examine the relationship between Engineering Identity and Doing Engineering, a correlation analysis was conducted and a moderate, positive relationship emerged, such that as students’ experience with engineering increased, their engineering identities also increased (R = .463, p > .000).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/CSCI51800.2020.00144
