Search for: All records

Prodromal detection of Alzheimer’s Disease(AD) is a substantial challenge in the research community. Among the tools used in AD diagnosis, cognitive exams are standard in most procedures. However, the barrage of cognitive examinations is both time and resource consuming. With the use of Machine Learning, Feature Elimination (FE) can be combined with classification algorithms to determine which cognitive exams are best suited for diagnosis. Using the results of FE, it can be determined if subsections of different composite scores can be combined to create a new enhanced and exhaustive exam. This paper implements a Recursive Feature Elimination with Cross Validation (RFECV) machine learning algorithm to determine which cognitive exams perform best for AD classification tasks. Out of 119 features, an average of 16 features were selected as optimal. These optimal features average 75% Accuracy, 70% Precision, and 75% Recall and an F1 Weighted score of 71% in classification. 

The Standard Uptake Value (SUV) is conventionally calculated using the ratio of the injected PET radiotracer dose and subject body weight (Binj) . SUVs are used to obtain SUV ratios (SUVr), an important metric in many Alzheimer's Disease (AD) neuroimaging studies. However, SUVr can be obtained using only neuroimaging data, bypassing the need for Binj . This paper proposes the SUVr-LightWeight (SUVr-LW) algorithm which is not reliant on clinical data and instead focuses on PET intensity values. The SUVr-LW was evaluated using the Centiloid Project Florebetaben (FBB) subject cohort and reached a linear regression slope of 0.98, while the healthy control subjects produced a slope of 0.87. 

Analyzing the hippocampus in the brain through magnetic resonance imaging (MRI) plays a crucial role in diagnosing and making treatment decisions for several neurological diseases. Hippocampus atrophy is among the most informative early diagnostic biomarkers of Alzheimer's disease (AD), yet its automatic segmentation is extremely difficult given the anatomical structure of the brain and the lack of any contrast in between its different regions. The gold standard remains manual segmentation and the use of brain atlases. In this study, we use a well-known image segmentation model, UNet++, and introduce an attention mechanism called the Convolutional Block Attention Module (CBAM) to the UNet++ model. This integrated model improves the feature weights of our region of interest, and hence increases the accuracy in segmenting the hippocampus. Results show averages of 0.8715, 0.8107, 0.8872, and 0.9039 for the metrics of Dice, Jaccard, Precision, and Recall, respectively. 

Epilepsy is a brain disorder that causes seizures, affecting nearly half a million children in the US alone. In this study, we aimed to use a nonlinear driven method to characterize scalp EEG recordings of pediatric epilepsy patients (PE: n=7 ) compared to pediatric control subjects (PC: n=7 ) in a clinical environment. A time-varying approach was used to construct functional connectivity networks (FCNs) of all subjects. Next, the FCNs are mapped into the form of undirected graphs that are subjected to the extraction of graph theory-based features. An unsupervised clustering technique based on K-mean is used to delineate the PE from the PC group. Our findings show a statistically significant difference in the mean FCNs between PC and PE groups (t(340)=−15.9899,p<<0.0001) . Performance results showed an accuracy of 92.5% with a sensitivity of 90% and a specificity of 95.3%. This approach can help improve and validate the early diagnosis of PE by applying non-invasive scalp EEG signals. 

Early diagnosis of Alzheimer’s Disease (AD) is challenging due to its progressive nature. This study proposes a comprehensive comparison of four classifiers combined with different dimensionality reduction methods to discriminate normal controls (CN) from pre-mild cognitive impairment (pMCI) and early MCI (EMCI) using multimodal datasets including MRIs, PETs, SUVr, clinician amyloid visual reads, and subjects demographics. The most robust classifier for CN vs. MCI is the Mutual Information Best Percentile - Bagging Classifier combination, with 73.91% accuracy and a 4.82% standard deviation (SD). The best performance of 65.23% (11.84% SD) accuracy for CN vs. EMCI was DTC with ANOVA. In comparing CN with pMCI the best classification accuracy was ANOVA-DTC 51.06% (14.19% SD). An accuracy of 56.34% (10.67% SD) was achieved by bagging with ANOVA for multiclass classification ofCN vs. pMCI vs. EMCI. 

In spring of 2020, almost all campuses across the United States abruptly closed and shifted to remote instruction due to the COVID-19 pandemic. Students and faculty rapidly adjusted how they engaged in learning in a time of great social and economic upheaval. In this paper, we use the lens of equity-oriented student engagement to examine how computing departments facilitated student participation in educationally engaging activities during the campus closures. The National Science Foundation-funded INCLUDES Alliance, the Computing Alliance of Hispanic-Serving Institutions (CAHSI), is a network of computing departments dedicated to increasing the representation of Hispanics in computing education and careers. We present results from a survey administered in spring 2020 to over 900 CAHSI students in 14 computing departments at Hispanic-Serving Institutions and interviews with 30 faculty, department chairs, and leaders. Though students reported increased financial and mental health struggles, they reflected on the myriad ways that faculty and peers supported their learning and sustained their engagement in coursework and co-curricular opportunities. In response to the pandemic, faculty and student leaders structured supports, such as peer-led team learning sessions and student clubs, to operate effectively in remote environments to promote student engagement. 

We propose a novel pipeline for the real-time detection of myocardial infarction from a single heartbeat of a 12-lead electrocardiograms. We do so by merging a real-time R-spike detection algorithm with a deep learning Long-Short Term Memory (LSTM) network-based classifier. A comparative assessment of the classification performance of the resulting system is performed and provided. The proposed algorithm achieves an inter-patient classification accuracy of 95.76% (with a 95% Confidence Interval (CI) of ±2.4%), a recall of 96.67% (±2.4% 95% CI), specificity of 93.64% (±5.7% 95% CI), and the average J-Score is 90.31% (±6.2% 95% CI). These state-of-the-art myocardial infarction detection metrics are extremely promising and could pave the wave for the early detection of myocardial infarctions. This high accuracy is achieved with a processing time of 40 milliseconds, which is most appropriate for online classification as the time between fast heartbeats is around 300 milliseconds. 

Using electroencephalography (EEG) data from epileptic patients 1 , we investigated and compared functional connectivity networks of three various types of epileptiform discharges (ED; single, complex & repetitive spikes) in 4 regions of the brain. Our results showed different connectivity patterns among three ED types within-and between-brain regions. The one-way ANOVA test indicated significant differences between the mean of the average connectivity matrices (ACMs) of the single spike, which characterize focal epilepsy, and the other two ED types (complex & repetitive) which characterize generalized epilepsy. The interictal EEG segments, through the connectivity patterns they yield, could be considered as one of the key indicators for the diagnosis of focal or generalized epilepsy.