Alzheimer’s disease and related dementias (ADRD) are among the leading causes of disability and mortality among the older population worldwide and a costly public health issue, yet there is still no treatment for prevention or cure. Clinical trials are available, but successful recruitment has been a longstanding challenge. One strategy to improve recruitment is conducting eligibility prescreening, a resource-intensive process where clinical research staff manually go through electronic health records to identify potentially eligible patients. Natural language processing (NLP), an informatics approach used to extract relevant data from various structured and unstructured data types, may improve eligibility prescreening for ADRD clinical trials. Guided by the Fit between Individuals, Task, and Technology framework, this dissertation research aims to optimize eligibility prescreening for ADRD clinical research by evaluating the sociotechnical factors influencing the adoption of NLP-driven tools. A systematic review of the literature was done to identify NLP systems that have been used for eligibility prescreening in clinical research. Following this, three NLP-driven tools were evaluated in ADRD clinical research eligibility prescreening: Criteria2Query, i2b2, and Leaf. We conducted an iterative mixed-methods usability evaluation with twenty clinical research staff using a cognitive walkthrough with a think-aloud protocol, Post-Study System Usability Questionnaire, and a directed deductive content analysis. Moreover, we conducted a cognitive task analysis with sixty clinical research staff to assess the impact of cognitive complexity on the usability of NLP systems and identify the sociotechnical gaps and cognitive support needed in using NLP systems for ADRD clinical research eligibility prescreening. The results show that understanding the role of NLP systems in improving eligibility prescreening is critical to the advancement of clinical research recruitment. All three systems are generally usable and accepted by a group of clinical research staff. The cognitive walkthrough and a think-aloud protocol informed iterative system refinement, resulting in high system usability. Cognitive complexity has no significant effect on system usability; however, the system, order of evaluation, job position, and computer literacy are associated with system usability. Key recommendations for system development and implementation include improving system intuitiveness and overall user experience through comprehensive consideration of user needs and task completion requirements; and implementing a focused training on database query to improve clinical research staff’s aptitude in eligibility prescreening and advance workforce competency. Finally, this study contributes to our understanding of the conduct of electronic eligibility prescreening for ADRD clinical research by clinical research staff. Findings from this study highlighted the importance of leveraging human-computer collaboration in conducting eligibility prescreening using NLP-driven tools, which provide an opportunity to identify and enroll participants of diverse backgrounds who are eligible for ADRD clinical research and accelerate treatment development.

Diabetes is a disease with a deleterious pathology that currently impacts 4.5 million individuals within the United States. This study examined the ability of a specific neuropsychological battery to identify and classify dementia type, investigated the impact of diabetes on cognition and analyzed the ability of the memory measures of the 7 Minute Screen (7MS) and the Rey-Osterrieth Recall to correctly categorize dementia type when not used in combination with a full battery. The battery in addition to exhaustive patient history, medical chart review and pertinent tests were used in initial diagnosis. Results indicated the battery was sufficient in the identification and classification of dementia type. Within the sample, diabetes did not appear to significantly impact overall battery results whereby only two measures were minimally affected by diabetes. Finally, the memory measures of the 7MS and the Rey-Osterrieth Recall were sufficient to predict membership into the Alzheimer's (AD) and vascular dementia (VD) groups with 86.4% accuracy. The classification percentage dropped to 68.3% with addition of the mild cognitive impairment category. The full battery correctly classified AD and VD dementia 87.5% and appeared to be the most robust.

The Bayesian network (BN) formalism is a powerful representation for encoding domains characterised by uncertainty. However, before it can be used it must first be constructed, which is a major challenge for any real-life problem. There are two broad approaches, namely the hand-crafted approach, which relies on a human expert, and the data-driven approach, which relies on data. The former approach is useful, however issues such as human bias can introduce errors into the model. We have conducted a literature review of the expert-driven approach, and we have cherry-picked a number of common methods, and engineered a framework to assist non-BN experts with expert-driven construction of BNs. The latter construction approach uses algorithms to construct the model from a data set. However, construction from data is provably NP-hard. To solve this problem, approximate, heuristic algorithms have been proposed; in particular, algorithms that assume an order between the nodes, therefore reducing the search space. However, traditionally, this approach relies on an expert providing the order among the variables --- an expert may not always be available, or may be unable to provide the order. Nevertheless, if a good order is available, these order-based algorithms have demonstrated good performance. More recent approaches attempt to ''learn'' a good order then use the order-based algorithm to discover the structure. To eliminate the need for order information during construction, we propose a search in the entire space of Bayesian network structures --- we present a novel approach for carrying out this task, and we demonstrate its performance against existing algorithms that search in the entire space and the space of orders. Finally, we employ the hand-crafting framework to construct models for the task of diagnosis in a ''real-life'' medical domain, dementia diagnosis. We collect real dementia data from clinical practice, and we apply the data-driven algorithms developed to assess the concordance between the reference models developed by hand and the models derived from real clinical data.

Although not all persons with mild cognitive impairment (MCI) go on to develop Alzheimer's disease (AD), MCI is recognized as an early stage of AD. The effects of AD are devastating to all concerned. Research has identified that recognition of AD in its earliest stages and institution of known treatment modalities can forestall the ultimate outcome. Identification of the first subtle signs of MCI can assist in the recognition of this prodromal phase, and allow for institution of therapy while still in the initial stages. Unfortunately, the development of MCI is insidious in nature, thus making it difficult to detect. The purpose of this study was to identify areas of functional decline that occur in MCI in an effort to improve its early identification. A mixed-methods design that combined qualitative and quantitative methods was used. Fifty-three participants with memory complaints were interviewed using a semi structured interview technique with open-ended questions, the Montreal Cognitive Assessment (MoCA), the Geriatric Depression Scale (GDS) and a list of eighty-five items previously identified as indicative of functional decline. Twenty-nine persons were divided into two groups: 1) those identified as probable MCI (consensus diagnosis) (n=15) and possible MCI (based on screening examination) (n=14) and 2) those identified as Normal (no cognitive impairment) (n=10), and their subjective functional deficits compared. The findings suggest that there were certain areas of functional decline more commonly experienced by persons in the MCI group than by unimpaired. These include difficulty recalling details of information and forgetting conversations. There were also other changes identified, such as adaptations on the part of persons with MCI (an increased dependence on memory aids, for example, lists and calendars) and a dec rease in social activities leading to an increase in social isolation. Additionally identified were functional activities that appear to remain intact in persons with early MCI. This study highlights the subtlety with which MCI assaults the functional abilities of individuals, thus making its early identification problematic. The results of this study will contribute by providing information that will help professionals who are assessing persons experiencing memory issues for the possible presence of MCI. Additionally, it is hoped that these findings will assist in the development of a measurement tool designed to assess for possible MCI. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2015. / FAU Electronic Theses and Dissertations Collection

Magnetic Resonance Imaging (MR Imaging, or MRI) offers superior soft-tissue contrast compared to other medical imaging modalities. However, access to MRI across developing countries ranges from prohibitive to scarcely available. The lack of educational facilities and the excessive costs involved in imparting technical training have resulted in a lack of skilled human resources required to operate MRI systems in developing countries. While diagnostic medical imaging improves the utilization of facility-based rural health services and impacts management decisions, MRI requires technical expertise to set up the patient, acquire, visualize, and interpret data. The availability of such local expertise in underserved geographies is challenging. Inefficient workflows and usage of MRI result in challenges related to financial and temporal access in countries with higher scanner densities than the global average of 5.3 per million people. MRI is routinely employed for neuroimaging and, in particular, for dementia screening. Dementia affected 50 million people worldwide in 2018, with an estimated economic impact of US $1 trillion a year, and Alzheimer’s Disease (AD) accounts for up to 60–80% of dementia cases. However, AD-imaging using MRI is time-consuming, and protocol optimization to accelerate MR Imaging requires local expertise since each pulse sequence involves multiple configurable parameters that need optimization for acquisition time, image contrast, and image quality. The lack of this expertise contributes to the highly inefficient utilization of MRI services, diminishing their clinical value. Augmenting human capabilities can tackle these challenges and standardize the practice. Autonomous and time-efficient acquisition, reconstruction, and visualization schemes to maximize MRI hardware usage and solutions that reduce reliance on human operation of MRI systems could alleviate some of the challenges associated with the requirement/absence of skilled human resources. We first present a preliminary demonstration of AMRI that simplifies the end-to-end MRI workflow of registering the subject, setting up and invoking an imaging session, acquiring and reconstructing the data, and visualizing the images. Our initial implementation of AMRI separates the required intelligence and user interaction from the acquisition hardware. AMRI performs intelligent protocolling and intelligent slice planning. Intelligent protocolling optimizes contrast value while satisfying signal-to-noise ratio and acquisition time constraints. We acquired data from four healthy volunteers across three experiments that differed in acquisition time constraints. AMRI achieved comparable image quality across all experiments despite optimizing for acquisition duration, therefore indirectly optimizing for MR Value – a metric to quantify the value of MRI. We believe we have demonstrated the first Autonomous MRI of the brain. We also present preliminary results from a deep learning (DL) tool for generating first-read text-based radiological reports directly from input brain images. It can potentially alleviate the burden on radiologists who experience the seventh-highest levels of burnout among all physicians, according to a 2015 survey. Next, we accelerate the routine brain imaging protocol employed at the Columbia University Irving Medical Center and leverage DL methods to boost image quality via image-denoising. Since MR physics dictates that the volume of the object being imaged influences the amount of signal received, we also demonstrate subject-specific image-denoising. The accelerated protocol resulted in a factor of 1.94 gain in imaging throughput, translating to a 72.51% increase in MR Value. We also demonstrate that this accelerated protocol can potentially be employed for AD imaging. Finally, we present ArtifactID – a DL tool to identify Gibbs ringing in low-field (0.36 T) and high-field (1.5 T and 3.0 T) brain MRI. We train separate binary classification models for low-field and high-field data, and visual explanations are generated via the Grad-CAM explainable AI method to help develop trust in the models’ predictions. We also demonstrate detecting motion using an accelerometer in a low-field MRI scanner since low-field MRI is prone to artifacts. In conclusion, our novel contributions in this work include: i) a software framework to demonstrate an initial implementation of autonomous brain imaging; ii) an end-to-end framework that leverages intelligent protocolling and DL-based image-denoising that can potentially be employed for accelerated AD imaging; and iii) a DL-based tool for automated identification of Gibbs ringing artifacts that may interfere with diagnosis at the time of radiological reading. We envision AMRI augmenting human expertise to alleviate the challenges associated with the scarcity of skilled human resources and contributing to globally accessible MRI.

Estudamos os achados da espectroscopia de prótons no córtex parietal-cíngulo posterior e das escalas MEEM, BRDS e FAST em pacientes com doença de Alzheimer - DA, comprometimento cognitivo amnéstico - CCA e controles normais - CN. Apenas as razões NAA/Cr e MI/NAA diferenciaram (p < 0.002) os grupos DA e CN. Houve correlação significativa do NAA/Cr e do MI/NAA com o BRDS (pontuação total - PT; atividades cotidianas - AC) e FAST, e do MI/NAA com o MEEM. Houve acréscimo de 5% na especificidade (CN x DA; CN x CCA), e de 2.4% (CN x DA) e 3.4% (CN x CCA) na acurácia diagnóstica, ao adicionar as razões NAA/Cr e MI/NAA às escalas BRDS (PT e AC) e FAST, aumentando a detecção de indivíduos com CCA e DA / We studied the findings of proton spectroscopy of the posterior parietal-cingulate cortex, and of MMSE, BRDS and FAST scales in subjects with Alzheimer disease - AD, amnestic mild cognitive impairment - MCI-A and normal controls - NC. Only NAA/Cr and MI/NAA differentiated (p < 0.002) the AD and NC groups. Significant correlation was found between NAA/Cr and MI/NAA with BRDS (total score - TS; everyday activities - EA) and FAST scales, and between MI/NAA and MMSE. Specificity increased in 5% (NC x AD; NC x MCI-A) and diagnostic accuracy in 2.4% (NC x AD) and 3.4% (NC x MCI-A) when NAA/Cr and MI/NAA ratios were added up to BRDS (TS & EA) and FAST scales, increasing MCI-A and AD detectability

Estudamos os achados da espectroscopia de prótons no córtex parietal-cíngulo posterior e das escalas MEEM, BRDS e FAST em pacientes com doença de Alzheimer - DA, comprometimento cognitivo amnéstico - CCA e controles normais - CN. Apenas as razões NAA/Cr e MI/NAA diferenciaram (p < 0.002) os grupos DA e CN. Houve correlação significativa do NAA/Cr e do MI/NAA com o BRDS (pontuação total - PT; atividades cotidianas - AC) e FAST, e do MI/NAA com o MEEM. Houve acréscimo de 5% na especificidade (CN x DA; CN x CCA), e de 2.4% (CN x DA) e 3.4% (CN x CCA) na acurácia diagnóstica, ao adicionar as razões NAA/Cr e MI/NAA às escalas BRDS (PT e AC) e FAST, aumentando a detecção de indivíduos com CCA e DA / We studied the findings of proton spectroscopy of the posterior parietal-cingulate cortex, and of MMSE, BRDS and FAST scales in subjects with Alzheimer disease - AD, amnestic mild cognitive impairment - MCI-A and normal controls - NC. Only NAA/Cr and MI/NAA differentiated (p < 0.002) the AD and NC groups. Significant correlation was found between NAA/Cr and MI/NAA with BRDS (total score - TS; everyday activities - EA) and FAST scales, and between MI/NAA and MMSE. Specificity increased in 5% (NC x AD; NC x MCI-A) and diagnostic accuracy in 2.4% (NC x AD) and 3.4% (NC x MCI-A) when NAA/Cr and MI/NAA ratios were added up to BRDS (TS & EA) and FAST scales, increasing MCI-A and AD detectability

Indiana University-Purdue University Indianapolis (IUPUI) / Alzheimer's disease (AD) is the most common form of dementia defined by loss in memory and cognitive abilities severe enough to interfere significantly with daily life activities. Amnestic mild cognitive impairment (MCI) is a clinical condition in which an individual has memory deficits not normal for the individual's age, but not severe enough to interfere significantly with daily functioning. Every year, approximately 10-15% of individuals with MCI will progress to dementia. Currently, there is no treatment to slow or halt AD progression, but research studies are being conducted to identify causes that can lead to its earlier diagnosis and treatment. Genetic variation plays a key role in the development of AD, but not all genetic factors associated with the disease have been identified. Copy number variants (CNVs), a form of genetic variation, are DNA regions that have added genetic material (duplications) or loss of genetic material (deletions). The regions may overlap one or more genes possibly affecting their function. CNVs have been shown to play a role in certain diseases. At the start of this work, only one published study had examined CNVs in late-onset AD and none had examined MCI. In order to determine the possible involvement of CNVs in AD and MCI susceptibility, genome-wide CNV analyses were performed in participants from three cohorts: the ADNI cohort, the NIA-LOAD/NCRAD Family Study cohort, and a unique cohort of clinically characterized and neuropathologically verified individuals. Only participants with DNA samples extracted from blood/brain tissue were included in the analyses. CNV calls were generated using genome-wide array data available on these samples. After detailed quality review, case (AD and/or MCI)/control association analyses including candidate gene and genome-wide approaches were performed. Although no excess CNV burden was observed in cases compared to controls in the three cohorts, gene-based association analyses identified a number of genes including the AD candidate genes CHRFAM7A, RELN and DOPEY2. Thus, the present work highlights the possible role of CNVs in AD and MCI susceptibility warranting further investigation. Future work will include replication of the findings in independent samples and confirmation by molecular validation experiments.