Robust Orientation Estimation from MEMS Magnetic, Angular Rate, and Gravity (MARG) Modules for Human-Computer Interaction.

While the availability of low-cost micro electro-mechanical systems (MEMS) accelerometers, gyroscopes, and magnetometers initially seemed to promise the possibility of using them to easily track the position and orientation of virtually any object that they could be attached to, this promise has not yet been fulfilled. Navigation-grade accelerometers and gyroscopes have long been the basis for tracking ships and aircraft, but the signals from low-cost MEMS accelerometers and gyroscopes are still orders of magnitude poorer in quality (e.g., bias stability). Therefore, the applications of MEMS inertial measurement units (IMUs), containing tri-axial accelerometers and gyroscopes, are currently not as extensive as they were expected to be. Even the addition of MEMS tri-axial magnetometers, to conform magnetic, angular rate, and gravity (MARG) sensor modules, has not fully overcome the challenges involved in using these modules for long-term orientation estimation, which would be of great benefit for the tracking of human-computer hand-held controllers or tracking of Internet-Of-Things (IoT) devices. Here, we present an algorithm, GMVDµK (or simply GMVDK), that aims at taking full advantage of all the signals available from a MARG module to robustly estimate its orientation, while preventing damaging overcorrections, within the context of a human-computer interaction application. Through experimental comparison, we show that GMVDK is more robust to magnetic disturbances than three other MARG orientation estimation algorithms in representative trials.

Different aspects of failing to recover from proactive semantic interference predicts rate of progression from amnestic mild cognitive impairment to dementia.

Introduction: This study investigated the role of proactive semantic interference (frPSI) in predicting the progression of amnestic Mild Cognitive Impairment (aMCI) to dementia, taking into account various cognitive and biological factors. Methods: The research involved 89 older adults with aMCI who underwent baseline assessments, including amyloid PET and MRI scans, and were followed longitudinally over a period ranging from 12 to 55 months (average 26.05 months). Results: The findings revealed that more than 30% of the participants diagnosed with aMCI progressed to dementia during the observation period. Using Cox Proportional Hazards modeling and adjusting for demographic factors, global cognitive function, hippocampal volume, and amyloid positivity, two distinct aspects of frPSI were identified as significant predictors of a faster decline to dementia. These aspects were fewer correct responses on a frPSI trial and a higher number of semantic intrusion errors on the same trial, with 29.5% and 31.6 % increases in the likelihood of more rapid progression to dementia, respectively. Discussion: These findings after adjustment for demographic and biological markers of Alzheimer's Disease, suggest that assessing frPSI may offer valuable insights into the risk of dementia progression in individuals with aMCI.

Plasma Alzheimer's biomarkers and brain amyloid in Hispanic and non-Hispanic older adults.

INTRODUCTION: Alzheimer's disease studies often lack ethnic diversity. METHODS: We evaluated associations between plasma biomarkers commonly studied in Alzheimer's (p-tau181, GFAP, and NfL), clinical diagnosis (clinically normal, amnestic MCI, amnestic dementia, or non-amnestic MCI/dementia), and Aß-PET in Hispanic and non-Hispanic older adults. Hispanics were predominantly of Cuban or South American ancestry. RESULTS: Three-hundred seventy nine participants underwent blood draw (71.9 ± 7.8 years old, 60.2% female, 57% Hispanic of which 88% were Cuban or South American) and 240 completed Aß-PET. P-tau181 was higher in amnestic MCI (p = 0.004, d = 0.53) and dementia (p < 0.001, d = 0.97) than in clinically normal participants and discriminated Aß-PET[+] and Aß-PET[-] (AUC = 0.86). P-tau181 outperformed GFAP and NfL. There were no significant interactions with ethnicity. Among amnestic MCI, Hispanics had lower odds of elevated p-tau181 than non-Hispanic (OR = 0.41, p = 0.006). DISCUSSION: Plasma p-tau181 informs etiological diagnosis of cognitively impaired Hispanic and non-Hispanic older adults. Hispanic ethnicity may relate to greater likelihood of non-Alzheimer's contributions to memory loss. HIGHLIGHTS: Alzheimer's biomarkers were measured in Hispanic and non-Hispanic older adults. Plasma p-tau181 related to amnestic cognitive decline and brain amyloid burden. AD biomarker associations did not differ between Hispanic and non-Hispanic ethnicity. Hispanic individuals may be more likely to have non-Alzheimer causes of memory loss.

Free-water imaging reveals unique brain microstructural deficits in hispanic individuals with Dementia.

Prior evidence suggests that Hispanic and non-Hispanic individuals differ in potential risk factors for the development of dementia. Here we determine whether specific brain regions are associated with cognitive performance for either ethnicity along various stages of Alzheimer's disease. For this cross-sectional study, we examined 108 participants (61 Hispanic vs. 47 Non-Hispanic individuals) from the 1Florida Alzheimer's Disease Research Center (1Florida ADRC), who were evaluated at baseline with diffusion-weighted and T1-weighted imaging, and positron emission tomography (PET) amyloid imaging. We used FreeSurfer to segment 34 cortical regions of interest. Baseline Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) were used as measures of cognitive performance. Group analyses assessed free-water measures (FW) and volume. Statistically significant FW regions based on ethnicity x group interactions were used in a stepwise regression function to predict total MMSE and MoCA scores. Random forest models were used to identify the most predictive brain-based measures of a dementia diagnosis separately for Hispanic and non-Hispanic groups. Results indicated elevated FW values for the left inferior temporal gyrus, left middle temporal gyrus, left banks of the superior temporal sulcus, left supramarginal gyrus, right amygdala, and right entorhinal cortex in Hispanic AD subjects compared to non-Hispanic AD subjects. These alterations occurred in the absence of different volumes of these regions in the two AD groups. FW may be useful in detecting individual differences potentially reflective of varying etiology that can influence cognitive decline and identify MRI predictors of cognitive performance, particularly among Hispanics.

Graph neural networks in EEG spike detection.

OBJECTIVE: This study develops new machine learning architectures that are more adept at detecting interictal epileptiform discharges (IEDs) in scalp EEG. A comparison of results using the average precision (AP) metric is made with the proposed models on two datasets obtained from Baptist Hospital of Miami and Temple University Hospital. METHODS: Applying graph neural networks (GNNs) on functional connectivity (FC) maps of different frequency sub-bands to yield a novel architecture we call FC-GNN. Attention mechanism is applied on a complete graph to let the neural network select its important edges, hence bypassing the extraction of features, a model we refer to as CA-GNN. RESULTS: On the Baptist Hospital dataset, the results were as follows: Vanilla Self-Attention →0.9029±0.0431, Hierarchical Attention →0.8546±0.0587, Vanilla Visual Geometry Group (VGG) →0.92±0.0618, Satelight →0.9219±0.046, FC-GNN →0.9731±0.0187, and CA-GNN →0.9788±0.0125. In the same order, the results on the Temple University Hospital dataset are 0.9692, 0.9113, 0.97, 0.9575, 0.963, and 0.9879. CONCLUSION: Based on the good results they yield, GNNs prove to have a strong potential in detecting epileptogenic activity. SIGNIFICANCE: This study opens the door for the discovery of the powerful role played by GNNs in capturing IEDs, which is an essential step for identifying the epileptogenic networks of the affected brain and hence improving the prospects for more accurate 3D source localization.

Semantic intrusion errors are associated with plasma Ptau-181 among persons with amnestic mild cognitive impairment who are amyloid positive.

Introduction: Semantic intrusion errors (SI) have distinguished between those with amnestic Mild Cognitive Impairment (aMCI) who are amyloid positive (A+) versus negative (A-) on positron emission tomography (PET). Method: This study examines the association between SI and plasma - based biomarkers. One hundred and twenty-eight participants received SiMoA derived measures of plasma pTau-181, ratio of two amyloid-ß peptide fragments (Aß42/Aß40), Neurofilament Light protein (NfL), Glial Fibrillary Acidic Protein (GFAP), ApoE genotyping, and amyloid PET imaging. Results: The aMCI A+ (n = 42) group had a higher percentage of ApoE ɛ4 carriers, and greater levels of pTau-181 and SI, than Cognitively Unimpaired (CU) A- participants (n = 25). CU controls did not differ from aMCI A- (n = 61) on plasma biomarkers or ApoE genotype. Logistic regression indicated that ApoE ɛ4 positivity, pTau-181, and SI were independent differentiating predictors (Correct classification = 82.0%; Sensitivity = 71.4%; Specificity = 90.2%) in identifying A+ from A- aMCI cases. Discussion: A combination of plasma biomarkers, ApoE positivity and SI had high specificity in identifying A+ from A- aMCI cases.

Stability in cognitive classification as a function of severity of impairment and ethnicity: A longitudinal analysis.

OBJECTIVE: The interaction of ethnicity, progression of cognitive impairment, and neuroimaging biomarkers of Alzheimer's Disease remains unclear. We investigated the stability in cognitive status classification (cognitively normal [CN] and mild cognitive impairment [MCI]) of 209 participants (124 Hispanics/Latinos and 85 European Americans). METHODS: Biomarkers (structural MRI and amyloid PET scans) were compared between Hispanic/Latino and European American individuals who presented a change in cognitive diagnosis during the second or third follow-up and those who remained stable over time. RESULTS: There were no significant differences in biomarkers between ethnic groups in any of the diagnostic categories. The frequency of CN and MCI participants who were progressors (progressed to a more severe cognitive diagnosis at follow-up) and non-progressors (either stable through follow-ups or unstable [progressed but later reverted to a diagnosis of CN]) did not significantly differ across ethnic groups. Progressors had greater atrophy in the hippocampus (HP) and entorhinal cortex (ERC) at baseline compared to unstable non-progressors (reverters) for both ethnic groups, and more significant ERC atrophy was observed among progressors of the Hispanic/Latino group. For European Americans diagnosed with MCI, there were 60% more progressors than reverters (reverted from MCI to CN), while among Hispanics/Latinos with MCI, there were 7% more reverters than progressors. Binomial logistic regressions predicting progression, including brain biomarkers, MMSE, and ethnicity, demonstrated that only MMSE was a predictor for CN participants at baseline. However, for MCI participants at baseline, HP atrophy, ERC atrophy, and MMSE predicted progression.

A unique color-coded visualization system with multimodal information fusion and deep learning in a longitudinal study of Alzheimer's disease.

PURPOSE: Automated diagnosis and prognosis of Alzheimer's Disease remain a challenging problem that machine learning (ML) techniques have attempted to resolve in the last decade. This study introduces a first-of-its-kind color-coded visualization mechanism driven by an integrated ML model to predict disease trajectory in a 2-year longitudinal study. The main aim of this study is to help capture visually in 2D and 3D renderings the diagnosis and prognosis of AD, therefore augmenting our understanding of the processes of multiclass classification and regression analysis. METHOD: The proposed method, Machine Learning for Visualizing AD (ML4VisAD), is designed to predict disease progression through a visual output. This newly developed model takes baseline measurements as input to generate a color-coded visual image that reflects disease progression at different time points. The architecture of the network relies on convolutional neural networks. With 1123 subjects selected from the ADNI QT-PAD dataset, we use a 10-fold cross-validation process to evaluate the method. Multimodal inputs* include neuroimaging data (MRI, PET), neuropsychological test scores (excluding MMSE, CDR-SB, and ADAS to avoid bias), cerebrospinal fluid (CSF) biomarkers with measures of amyloid beta (ABETA), phosphorylated tau protein (PTAU), total tau protein (TAU), and risk factors that include age, gender, years of education, and ApoE4 gene. FINDINGS/RESULTS: Based on subjective scores reached by three raters, the results showed an accuracy of 0.82 ± 0.03 for a 3-way classification and 0.68 ± 0.05 for a 5-way classification. The visual renderings were generated in 0.08 msec for a 23 × 23 output image and in 0.17 ms for a 45 × 45 output image. Through visualization, this study (1) demonstrates that the ML visual output augments the prospects for a more accurate diagnosis and (2) highlights why multiclass classification and regression analysis are incredibly challenging. An online survey was conducted to gauge this visualization platform's merits and obtain valuable feedback from users. All implementation codes are shared online on GitHub. CONCLUSION: This approach makes it possible to visualize the many nuances that lead to a specific classification or prediction in the disease trajectory, all in context to multimodal measurements taken at baseline. This ML model can serve as a multiclass classification and prediction model while reinforcing the diagnosis and prognosis capabilities by including a visualization platform.

Scenic routing navigation using property valuation.

Extensive prior work has provided methods for the optimization of routing based on weights assigned to travel duration, and/or travel cost, and/or the distance traveled. Routing can be in various modalities, such as by car, on foot, by bicycle, via public transit, or by boat. A typical method of routing involves building a graph comprised of street segments, assigning a normalized weighted value to each segment, and then applying the weighted-shorted path algorithm to the graph in order to find the best route. Some users desire that the routing suggestion include consideration pertaining to the scenic-architectural quality of the path. For example, a user may seek a leisure walk via what they might deem as visually attractive architecture. Here, we are proposing a method to quantify such user preferences and scenic quality and to augment the standard routing methods by giving weight to the scenic quality. That is, instead of suggesting merely the time and cost-optimal route, we will find the best route that is tailored towards the user's scenic quality preferences as an additional criterion to the time and cost. The proposed method uniquely weighs the scenic interest or residential street segments based on the property valuation data.

Benchmarking Dataset of Signals from a Commercial MEMS Magnetic-Angular Rate-Gravity (MARG) Sensor Manipulated in Regions with and without Geomagnetic Distortion.

In this paper, we present the FIU MARG Dataset (FIUMARGDB) of signals from the tri-axial accelerometer, gyroscope, and magnetometer contained in a low-cost miniature magnetic-angular rate-gravity (MARG) sensor module (also known as magnetic inertial measurement unit, MIMU) for the evaluation of MARG orientation estimation algorithms. The dataset contains 30 files resulting from different volunteer subjects executing manipulations of the MARG in areas with and without magnetic distortion. Each file also contains reference ("ground truth") MARG orientations (as quaternions) determined by an optical motion capture system during the recording of the MARG signals. The creation of FIUMARGDB responds to the increasing need for the objective comparison of the performance of MARG orientation estimation algorithms, using the same inputs (accelerometer, gyroscope, and magnetometer signals) recorded under varied circumstances, as MARG modules hold great promise for human motion tracking applications. This dataset specifically addresses the need to study and manage the degradation of orientation estimates that occur when MARGs operate in regions with known magnetic field distortions. To our knowledge, no other dataset with these characteristics is currently available. FIUMARGDB can be accessed through the URL indicated in the conclusions section. It is our hope that the availability of this dataset will lead to the development of orientation estimation algorithms that are more resilient to magnetic distortions, for the benefit of fields as diverse as human-computer interaction, kinesiology, motor rehabilitation, etc.

Association of longitudinal cognitive decline with diffusion MRI in Gray Matter, Amyloid, and Tau deposition.

Extracellular amyloid plaques in gray matter are the earliest pathological marker for Alzheimer's disease (AD), followed by abnormal tau protein accumulation. The link between diffusion changes in gray matter, amyloid and tau pathology, and cognitive decline is not well understood. We first performed cross-sectional analyses on T1-weighted imaging, diffusion MRI, and amyloid and tau PETs from the ADNI 2/3 database. We evaluated cortical volume, free-water, fractional anisotropy (FA), and amyloid and tau SUVRs in 171 cognitively normal, 103 MCI, and 44 AD individuals. When the 3 groups were combined, increasing amyloid burden was associated with reduced extracellular free-water in the entorhinal cortex and hippocampus in those with amyloid-negative status whereas increasing tau burden was associated with increased extracellular free-water regardless of amyloid status. Next, we found that for the MCI subjects, diffusion measures (free-water, FA) alone predicted MMSE score 2 years later with a high r-square value (87%), as compared to tau SUVRs (27%), T1 volume (36%), and amyloid SUVRs (75%). Diffusion measures represent a potent non-invasive marker for predicting cognitive decline.

A Novel Computerized Cognitive Test for the Detection of Mild Cognitive Impairment and Its Association with Neurodegeneration in Alzheimer's Disease Prone Brain Regions.

During the prodromal stage of Alzheimer's disease (AD), neurodegenerative changes can be identified by measuring volumetric loss in AD-prone brain regions on MRI. Cognitive assessments that are sensitive enough to measure the early brain-behavior manifestations of AD and that correlate with biomarkers of neurodegeneration are needed to identify and monitor individuals at risk for dementia. Weak sensitivity to early cognitive change has been a major limitation of traditional cognitive assessments. In this study, we focused on expanding our previous work by determining whether a digitized cognitive stress test, the Loewenstein-Acevedo Scales for Semantic Interference and Learning, Brief Computerized Version (LASSI-BC) could differentiate between Cognitively Unimpaired (CU) and amnestic Mild Cognitive Impairment (aMCI) groups. A second focus was to correlate LASSI-BC performance to volumetric reductions in AD-prone brain regions. Data was gathered from 111 older adults who were comprehensively evaluated and administered the LASSI-BC. Eighty-seven of these participants (51 CU; 36 aMCI) underwent MR imaging. The volumes of 12 AD-prone brain regions were related to LASSI-BC and other memory tests correcting for False Discovery Rate (FDR). Results indicated that, even after adjusting for initial learning ability, the failure to recover from proactive semantic interference (frPSI) on the LASSI-BC differentiated between CU and aMCI groups. An optimal combination of frPSI and initial learning strength on the LASSI-BC yielded an area under the ROC curve of 0.876 (76.1% sensitivity, 82.7% specificity). Further, frPSI on the LASSI-BC was associated with volumetric reductions in the hippocampus, amygdala, inferior temporal lobes, precuneus, and posterior cingulate.

A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer's disease.

Early detection of Alzheimer's disease (AD) during the Mild Cognitive Impairment (MCI) stage could enable effective intervention to slow down disease progression. Computer-aided diagnosis of AD relies on a sufficient amount of biomarker data. When this requirement is not fulfilled, transfer learning can be used to transfer knowledge from a source domain with more amount of labeled data than available in the desired target domain. In this study, an instance-based transfer learning framework is presented based on the gradient boosting machine (GBM). In GBM, a sequence of base learners is built, and each learner focuses on the errors (residuals) of the previous learner. In our transfer learning version of GBM (TrGB), a weighting mechanism based on the residuals of the base learners is defined for the source instances. Consequently, instances with different distribution than the target data will have a lower impact on the target learner. The proposed weighting scheme aims to transfer as much information as possible from the source domain while avoiding negative transfer. The target data in this study was obtained from the Mount Sinai dataset which is collected and processed in a collaborative 5-year project at the Mount Sinai Medical Center. The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset was used as the source domain. The experimental results showed that the proposed TrGB algorithm could improve the classification accuracy by 1.5 and 4.5% for CN vs. MCI and multiclass classification, respectively, as compared to the conventional methods. Also, using the TrGB model and transferred knowledge from the CN vs. AD classification of the source domain, the average score of early MCI vs. late MCI classification improved by 5%.

The association of depression and apathy with Alzheimer's disease biomarkers in a cross-cultural sample.

Cross-cultural differences in the association between neuropsychiatric symptoms and Alzheimer's disease (AD) biomarkers are not well understood. This study aimed to (1) compare depressive symptoms and frequency of reported apathy across diagnostic groups of participants with normal cognition (CN), mild cognitive impairment (MCI), and dementia, as well as ethnic groups of Hispanic Americans (HA) and European Americans (EA); (2) evaluate the relationship between depression and apathy with Aß deposition and brain atrophy. Statistical analyses included ANCOVAs, chi-squared, nonparametric tests, correlations, and logistic regressions. Higher scores on the Geriatric Depression Scale (GDS-15) were reported in the MCI and dementia cohorts, while older age corresponded with lower GDS-15 scores. The frequency of apathy differed across diagnoses within each ethnicity, but not when comparing ethnic groups. Reduced volume in the rostral anterior cingulate cortex (ACC) significantly correlated with and predicted apathy for the total sample after applying false discovery rate corrections (FDR), controlling for covariates. The EA group separately demonstrated a significant negative relationship between apathy and superior frontal volume, while for HA, there was a relationship between rostral ACC volume and apathy. Apathy corresponded with higher Aß levels for the total sample and for the CN and HA groups.

A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer's Disease.

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.

A study of the longitudinal changes in multiple cerebrospinal fluid and volumetric magnetic resonance imaging biomarkers on converter and non-converter Alzheimer's disease subjects with consideration for their amyloid beta status.

INTRODUCTION: This study aims to determine whether newly introduced biomarkers Visinin-like protein-1 (VILIP-1), chitinase-3-like protein 1 (YKL-40), synaptosomal-associated protein 25 (SNAP-25), and neurogranin (NG) in cerebrospinal fluid are useful in evaluating the asymptomatic and early symptomatic stages of Alzheimer's disease (AD). It further aims to shed new insight into the differences between stable subjects and those who progress to AD by associating cerebrospinal fluid (CSF) biomarkers and specific magnetic resonance imaging (MRI) regions with disease progression, more deeply exploring how such biomarkers relate to AD pathology. METHODS: We examined baseline and longitudinal changes over a 7-year span and the longitudinal interactions between CSF and MRI biomarkers for subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We stratified all CSF (140) and MRI (525) cohort participants into five diagnostic groups (including converters) further dichotomized by CSF amyloid beta (Aß) status. Linear mixed models were used to compare within-person rates of change across diagnostic groups and to evaluate the association of CSF biomarkers as predictors of magnetic resonance imaging (MRI) biomarkers. CSF biomarkers and disease-prone MRI regions are assessed for CSF proteins levels and brain structural changes. RESULTS: VILIP-1 and SNAP-25 displayed within-person increments in early symptomatic, amyloid-positive groups. CSF amyloid-positive (Aß+) subjects showed elevated baseline levels of total tau (tTau), phospho-tau181 (pTau), VILIP-1, and NG. YKL-40, SNAP-25, and NG are positively intercorrelated. Aß+ subjects showed negative MRI biomarker changes. YKL-40, tTau, pTau, and VILIP-1 are longitudinally associated with MRI biomarkers atrophy. DISCUSSION: Converters (CNc, MCIc) highlight the evolution of biomarkers during the disease progression. Results show that underlying amyloid pathology is associated with accelerated cognitive impairment. CSF levels of Aß42, pTau, tTau, VILIP-1, and SNAP-25 show utility to discriminate between mild cognitive impairment (MCI) converter and control subjects (CN). Higher levels of YKL-40 in the Aß+ group were longitudinally associated with declines in temporal pole and entorhinal thickness. Increased levels of tTau, pTau, and VILIP-1 in the Aß+ groups were longitudinally associated with declines in hippocampal volume. These CSF biomarkers should be used in assessing the characterization of the AD progression.

Addressing the missing data challenge in multi-modal datasets for the diagnosis of Alzheimer's disease.

BACKGROUND: One of the challenges facing accurate diagnosis and prognosis of Alzheimer's disease, beyond identifying the subtle changes that define its early onset, is the scarcity of sufficient data compounded by the missing data challenge. Although there are many participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, many of the observations have a lot of missing features which often leads to the exclusion of potentially valuable data points in many ongoing experiments, especially in longitudinal studies. NEW METHODS: Motivated by the necessity of examining all participants, even those with missing tests or imaging modalities, this study draws attention to the Gradient Boosting (GB) algorithm which has an inherent capability of addressing missing values. The four groups considered include: Cognitively Normal (CN), Early Mild Cognitive Impairment (EMCI), Late Mild Cognitive Impairment (LMCI) and Alzheimer's Disease (AD). Prior to applying state of the art classifiers such as Support Vector Machine (SVM) and Random Forest (RF), the impact of imputing (i.e., replacing) data in common datasets with numerical techniques has been investigated and compared with the GB algorithm. Empirical evaluations show that the GB performance is highly resilient to missing values in comparison to SVM and RF algorithms. These latter algorithms can however be improved when coupled with more sophisticated imputation technique such as soft-impute or K-Nearest Neighbors (KNN) algorithm assuming low extent of data incompleteness. RESULTS: The classification accuracy has been improved by up to 3% in the multiclass classification of all four classes of subjects when all the samples including the incomplete ones are considered during the model generation and testing phases. COMPARISON WITH EXISTING METHODS: Unlike other methods, the proposed approach addresses the challenging multiclass classification of the ADNI dataset in the presence of different levels of missing data points. It also provides a comparative study on effects of existing imputation techniques on a block-wise missing data. Results of the proposed method are validated against gold standard methods used for AD classification.

Association of Cognitive Impairment With Free Water in the Nucleus Basalis of Meynert and Locus Coeruleus to Transentorhinal Cortex Tract.

BACKGROUND AND OBJECTIVES: The goal of this work was to determine the relationship between diffusion microstructure and early changes in Alzheimer disease (AD) severity as assessed by clinical diagnosis, cognitive performance, dementia severity, and plasma concentrations of neurofilament light chain. METHODS: Diffusion MRI scans were collected on cognitively normal participants (CN) and patients with early mild cognitive impairment (EMCI), late mild cognitive impairment, and AD. Free water (FW) and FW-corrected fractional anisotropy were calculated in the locus coeruleus to transentorhinal cortex tract, 4 magnocellular regions of the basal forebrain (e.g., nucleus basalis of Meynert), entorhinal cortex, and hippocampus. All patients underwent a battery of cognitive assessments; neurofilament light chain levels were measured in plasma samples. RESULTS: FW was significantly higher in patients with EMCI compared to CN in the locus coeruleus to transentorhinal cortex tract, nucleus basalis of Meynert, and hippocampus (mean Cohen d = 0.54; p fdr < 0.05). FW was significantly higher in those with AD compared to CN in all the examined regions (mean Cohen d = 1.41; p fdr < 0.01). In addition, FW in the hippocampus, entorhinal cortex, nucleus basalis of Meynert, and locus coeruleus to transentorhinal cortex tract positively correlated with all 5 cognitive impairment metrics and neurofilament light chain levels (mean r 2 = 0.10; p fdr < 0.05). DISCUSSION: These results show that higher FW is associated with greater clinical diagnosis severity, cognitive impairment, and neurofilament light chain. They also suggest that FW elevation occurs in the locus coeruleus to transentorhinal cortex tract, nucleus basalis of Meynert, and hippocampus in the transition from CN to EMCI, while other basal forebrain regions and the entorhinal cortex are not affected until a later stage of AD. FW is a clinically relevant and noninvasive early marker of structural changes related to cognitive impairment.

PET Imaging of Tau Pathology and Amyloid-ß, and MRI for Alzheimer's Disease Feature Fusion and Multimodal Classification.

BACKGROUND: Machine learning is a promising tool for biomarker-based diagnosis of Alzheimer's disease (AD). Performing multimodal feature selection and studying the interaction between biological and clinical AD can help to improve the performance of the diagnosis models. OBJECTIVE: This study aims to formulate a feature ranking metric based on the mutual information index to assess the relevance and redundancy of regional biomarkers and improve the AD classification accuracy. METHODS: From the Alzheimer's Disease Neuroimaging Initiative (ADNI), 722 participants with three modalities, including florbetapir-PET, flortaucipir-PET, and MRI, were studied. The multivariate mutual information metric was utilized to capture the redundancy and complementarity of the predictors and develop a feature ranking approach. This was followed by evaluating the capability of single-modal and multimodal biomarkers in predicting the cognitive stage. RESULTS: Although amyloid-ß deposition is an earlier event in the disease trajectory, tau PET with feature selection yielded a higher early-stage classification F1-score (65.4%) compared to amyloid-ß PET (63.3%) and MRI (63.2%). The SVC multimodal scenario with feature selection improved the F1-score to 70.0% and 71.8% for the early and late-stage, respectively. When age and risk factors were included, the scores improved by 2 to 4%. The Amyloid-Tau-Neurodegeneration [AT(N)] framework helped to interpret the classification results for different biomarker categories. CONCLUSION: The results underscore the utility of a novel feature selection approach to reduce the dimensionality of multimodal datasets and enhance model performance. The AT(N) biomarker framework can help to explore the misclassified cases by revealing the relationship between neuropathological biomarkers and cognition.

Real-time frequency-independent single-Lead and single-beat myocardial infarction detection.

This study proposes a novel real-time frequency-independent myocardial infarction detector for Lead II electrocardiograms. The underlying Deep-LSTM network is trained using the PTB-XL database, the largest to date publicly available electrocardiography dataset, and is tested over the same and the older PTB database. By testing the model over distinct datasets, collected under different conditions and from different patients, a more realistic measure of the performance can be gauged from the deployed system. The detector is trained over 3589 myocardial infarction (MI) patients and 7115 healthy controls (HC) while it is evaluated on 1076 MIs and 1840 HCs. The proposed algorithm, achieved an accuracy of 77.12%, recall/sensitivity of 75.85%, and a specificity of 83.02% over the entire PTB database; 85.07%, 81.54%, 87.31% over the PTB-XL validation set (fold 9), and 84.17%, 78.37%, 87.55% over the PTB-XL test set (fold 10). The model also achieves stable performance metrics over the frequency range of 202 Hz to 2.8 kHz. The processing time is dependent on the sampling frequency, ranging from 130 ms at 202 Hz to 1.8 s at 2.8 kHz. Such outcome is within the time required for real-time processing (less than 300 ms for fast heartbeats), between 202 Hz and 500 Hz making the algorithm practically real-time. Therefore, the proposed MI detector could be readily deployed onto existing wearable and/or portable devices and test instruments; potentially having significant societal and clinical impact in the lives of patients at risk for myocardial infarction.