Electrical and Computer Engineering Commons^™

Multiple Imputation For Robust Cluster Analysis To Address Missingness In Medical Data, Arnold Harder, Gayla R. Olbricht, Godwin Ekuma, Daniel B. Hier, Tayo Obafemi-Ajayi

Mathematics and Statistics Faculty Research & Creative Works

Cluster Analysis Has Been Applied To A Wide Range Of Problems As An Exploratory Tool To Enhance Knowledge Discovery. Clustering Aids Disease Subtyping, I.e. Identifying Homogeneous Patient Subgroups, In Medical Data. Missing Data Is A Common Problem In Medical Research And Could Bias Clustering Results If Not Properly Handled. Yet, Multiple Imputation Has Been Under-Utilized To Address Missingness, When Clustering Medical Data. Its Limited Integration In Clustering Of Medical Data, Despite The Known Advantages And Benefits Of Multiple Imputation, Could Be Attributed To Many Factors. This Includes Methodological Complexity, Difficulties In Pooling Results To Obtain A Consensus Clustering, Uncertainty Regarding …

Blood Biomarkers For Mild Traumatic Brain Injury: A Selective Review Of Unresolved Issues, Daniel B. Hier, Tayo Obafemi-Ajayi, Matthew S. Thimgan, Gayla R. Olbricht, Sima Azizi, Blaine Allen, Bassam A. Hadi, Donald C. Wunsch

Biological Sciences Faculty Research & Creative Works

Background: The use of blood biomarkers after mild traumatic brain injury (mTBI) has been widely studied. We have identified eight unresolved issues related to the use of five commonly investigated blood biomarkers: neurofilament light chain, ubiquitin carboxy-terminal hydrolase-L1, tau, S100B, and glial acidic fibrillary protein. We conducted a focused literature review of unresolved issues in three areas: mode of entry into and exit from the blood, kinetics of blood biomarkers in the blood, and predictive capacity of the blood biomarkers after mTBI.

Findings: Although a disruption of the blood brain barrier has been demonstrated in mild and severe traumatic brain …

An Explainable And Statistically Validated Ensemble Clustering Model Applied To The Identification Of Traumatic Brain Injury Subgroups, Dacosta Yeboah, Louis Steinmeister, Daniel B. Hier, Bassam Hadi, Donald C. Wunsch, Gayla R. Olbricht, Tayo Obafemi-Ajayi

Electrical and Computer Engineering Faculty Research & Creative Works

We present a framework for an explainable and statistically validated ensemble clustering model applied to Traumatic Brain Injury (TBI). The objective of our analysis is to identify patient injury severity subgroups and key phenotypes that delineate these subgroups using varied clinical and computed tomography data. Explainable and statistically-validated models are essential because a data-driven identification of subgroups is an inherently multidisciplinary undertaking. In our case, this procedure yielded six distinct patient subgroups with respect to mechanism of injury, severity of presentation, anatomy, psychometric, and functional outcome. This framework for ensemble cluster analysis fully integrates statistical methods at several stages of …

Evaluation Of Standard And Semantically-Augmented Distance Metrics For Neurology Patients, Daniel B. Hier, Jonathan Kopel, Steven U. Brint, Donald C. Wunsch, Gayla R. Olbricht, Sima Azizi, Blaine Allen

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.

Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by …

Handling Missing Data For Unsupervised Learning With An Application On A Fitbir Traumatic Brain Injury (Tbi) Dataset, Louis Steinmeister, Dacosta Yeboah, Gayla Olbricht, Tayo Obafemi-Ajayi, Bassam Hadi, Daniel Hier, Donald C. Wunsch

Mathematics and Statistics Faculty Research & Creative Works

"The problem of missing data and imputation have been widely discussed amongst specialists. However, many data scientists and applied statisticians fail to appropriately consider this issue. Often, it seems intuitive to discard observations containing missing data or simply to substitute means. This can lead to disastrous consequences, particularly in an era of exponentially increasing data volumes. In the following, we show how inappropriate handling of missing data and an insufficient analysis of the censoring mechanism can lead to a bias, overconfidence in the estimation of parameters, could challenge the reproducibility of obtained results, and may distort the structure of the …

A Multi-Step Nonlinear Dimension-Reduction Approach With Applications To Bigdata, R. Krishnan, V. A. Samaranayake, Jagannathan Sarangapani

Mathematics and Statistics Faculty Research & Creative Works

In this paper, a multi-step dimension-reduction approach is proposed for addressing nonlinear relationships within attributes. In this work, the attributes in the data are first organized into groups. In each group, the dimensions are reduced via a parametric mapping that takes into account nonlinear relationships. Mapping parameters are estimated using a low rank singular value decomposition (SVD) of distance covariance. Subsequently, the attributes are reorganized into groups based on the magnitude of their respective singular values. The group-wise organization and the subsequent reduction process is performed for multiple steps until a singular value-based user-defined criterion is satisfied. Simulation analysis is …

Direct Error Driven Learning For Deep Neural Networks With Applications To Bigdata, R. Krishnan, Jagannathan Sarangapani, V. A. Samaranayake

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, generalization error for traditional learning regimes-based classification is demonstrated to increase in the presence of bigdata challenges such as noise and heterogeneity. To reduce this error while mitigating vanishing gradients, a deep neural network (NN)-based framework with a direct error-driven learning scheme is proposed. To reduce the impact of heterogeneity, an overall cost comprised of the learning error and approximate generalization error is defined where two NNs are utilized to estimate the costs respectively. To mitigate the issue of vanishing gradients, a direct error-driven learning regime is proposed where the error is directly utilized for learning. It …

Steam Flooding Screening And Eor Prediction By Using Clustering Algorithm And Data Visualization, Na Zhang

Masters Theses

"Enhanced Oil Recovery (EOR) techniques are vitally important in the oil industry because these techniques could not only extend the life of wells, but also produce 10% to 30% additional oil from the reservoir. However, selecting the most suitable EOR techniques for unknown reservoirs is not easy for decision making. Based on literature, EOR screening criteria could help to find the best candidates for unknown projects, which is classified into two categories: conventional EOR screening and advanced EOR screening. In this research, an artificial intelligent (AI) method, hierarchical clustering algorithm, is adapted to analyze both steam flooding projects and worldwide …

Multiple Lebesgue Integration On Time Scales, Gusein Sh. Guseinov, Martin Bohner

Mathematics and Statistics Faculty Research & Creative Works

We study the process of multiple Lebesgue integration on time scales. The relationship of the Riemann and the Lebesgue multiple integrals is investigated.