Leevans6357

Alzheimer's Disease (AD) is a common type of dementia, affecting human memory, language ability and behavior. Hippocampus is an important biomarker for AD diagnosis. Previous hippocampus-based biomarker analyses mainly focused on volume, texture and shape of the bilateral hippocampus. 3D convolutional neural networks (CNNs) can understand and extract complex morphology features from Magnetic resonance imaging (MRI) and have recently been developed for hippocampus-based AD classification. However, existing CNN models often have highly complex structures and require large amounts of training data. Here we propose an accurate and lightweight Densely Connected 3D convolutional neural network (DenseCNN) for AD classification based on hippocampus segments. DenseCNN was trained on 746 and tested on 187 pairs of hippocampus from Alzheimer's Disease Neuroimaging Initiative (ADNI) databases. DenseCNN has an average accuracy of 0.898, sensitivity of 0.985, specificity of 0.852, and area under curve (A UC) of0.979, which are better than or comparable to state-of-art approaches.In the electronic health record, the majority of clinically relevant information is stored within clinical notes. Most clinical notes follow a set organizational structure composed of canonicalized section headers that facilitate clinical review and information gathering. Standardized section header terminologies such as the SecTag terminology permit the identification and standardization of headers to a canonicalized form. Although the SecTag terminology has been evaluated extensively for history & physical notes, the coverage of canonical section header terms has not been assessed across other note types. For this pilot study, we conducted a coverage study and characterization of canonical section headers across 5 common, clinical note types and a generalizability study of canonical section headers detected within two types of clinical notes from Penn Medicine.COVID-19 is threatening the health of the entire human population. In order to control the spread of the disease, epidemiological investigations should be conducted, to trace the infection source of each confirmed patient and isolate their close contacts. However, the analysis on a mass of case reports in epidemiological investigation is extremely time-consuming and labor-intensive. This paper presents an end-to-end framework for automatic epidemiological case report analysis and inference, in which a Tuple-based Multi-Task Neural Network (TMT-NN) is designed and implemented for jointly recognizing epidemiological entities and relations from case reports, and an epidemiological knowledge graph and its corresponding inference engine are built to uncover the infection modes, sources and pathways. Preliminary experiments demonstrate the promising results, and we published a real data set of COVID-19 epidemiological investigation corpora at Github, as well as contributing our COVID-19 epidemiological knowledge graph to the open community OpenKG.cn.Allergy mention normalization is challenging because of the wide range of possible allergens including medications, foods, plants, animals, and consumer products. This paper describes the process of mapping free-text allergy information from an electronic health record (EHR) system in a university hospital to standard terminologies and migration of those data into an enterprise EHR system. The review, mapping, and migration revealed interesting issues and challenges with the free-text allergy information and the mapping in preparation for implementation in the new EHR system. α-cyano-4-hydroxycinnamic solubility dmso These findings provide insights that can form the basis of guidelines for future mapping and migration efforts involving free-text allergy data. As part of this process, we generate and make freely available AllergyMap, a mapping between free-text entered allergy medication to standard non-proprietary ontologies. To our knowledge, this is the first such mapping available and could serve as a public resource for allergy mention normalization and system evaluation.Nursing home (NH) patients are extensive users of emergency department (ED) services. Problematically, poor information sharing and incomplete access to information complicates the delivery of care in EDs for NH patients. Paper-based transfer forms can support information sharing, but have significant limitations. Standards-based automated transfer-forms that leverage health information exchange data may address the limitations of paper-based forms and better support care delivery. This study developed a prototype SMART on FHIR automated transfer form for NH patients using priority data elements identified through individual interviews, a review of existing transfer forms, a targeted survey of end users, and a design workshop. Analyses were grounded in the 5 Rights of clinical decision support framework. The most valuable data elements included emergency contact/healthcare proxy, current medication list, reason for transfer to the ED, baseline neurological state, and relevant diagnoses / medical history. The working prototype was successfully deployed within an Amazon Web Service environment.

Recruiting older adults (OA) into research is challenging.

To assess the feasibility of using two crowdsourcing platforms, Amazon's Mechanical Turk (MTurk) and Prolific Academic (ProA), as efficient and low-cost venues for recruiting survey participants aged 65 and older.

We developed an online survey to investigate and compare the demographics, technology use, and motivations for research participation of OA on MTurk and ProA. Qualitative responses, response time, word count, and recruitment costs were analyzed.

We recruited 97 OA survey participants on both MTurk and ProA. Participants were similar in terms ofdemographics, technology usage, and motivations for participation (topic interest and payment).

Both crowdsourcing platforms are useful for rapid and low-cost recruitment of OA. The OA recruitment process was more efficient with ProA. Crowdsourcing platforms are potential sources of OA research participants; however, the pool is limited to generally healthy, technologically active, and well-educated older adults.

Both crowdsourcing platforms are useful for rapid and low-cost recruitment of OA. The OA recruitment process was more efficient with ProA. Crowdsourcing platforms are potential sources of OA research participants; however, the pool is limited to generally healthy, technologically active, and well-educated older adults.Because they contain detailed individual-level data on various patient characteristics including their medical conditions and treatment histories, electronic health record (EHR) systems have been widely adopted as an efficient source for health research. Compared to data from a single health system, real-world data (RWD) from multiple clinical sites provide a larger and more generalizable population for accurate estimation, leading to better decision making for health care. However, due to concerns over protecting patient privacy, it is challenging to share individual patient-level data across sites in practice. To tackle this issue, many distributed algorithms have been developed to transfer summary-level statistics to derive accurate estimates. Nevertheless, many of these algorithms require multiple rounds of communication to exchange intermediate results across different sites. Among them, the One-shot Distributed Algorithm for Logistic regression (termed ODAL) was developed to reduce communication overhead while protecting patient privacy. In this paper, we applied the ODAL algorithm to RWD from a large clinical data research network-the OneFlorida Clinical Research Consortium and estimated the associations between risk factors and the diagnosis of opioid use disorder (OUD) among individuals who received at least one opioid prescription. The ODAL algorithm provided consistent findings of the associated risk factors and yielded better estimates than meta-analysis.Dental and medical providers require similar patient demographic and clinical information for the management of a mutual patient. Despite an overlap in information needs, medical and dental data are created and stored in multiple records and locations. Electronic health information exchange (HIE) bridge gaps in health data spread across various providers. Enabling exchange via query-based HIE may provide critical information at the point of care during a dental visit. The purpose of this study is to characterize query-based HIE use during dental visits at two Federally Qualified Health Centers (FQHCs) that provided on-site dental services. First, we determine the proportion of dental visits for which providers accessed the HIE. Next, site, patient and visit characteristics associated with query-based HIE use during dental visits are examined. Last, among dental visits with HIE use, the aspects of the HIE that are accessed most frequently are described. HIE use was low (0.17%) during dental visits, however our findings from this study extend the body of research examining HIE use by studying a less explored area of the care continuum.The objective was to re-tool the existing claims-based measure NQF2940 "Use of Opioids at High Dosage in Persons Without Cancer" to an electronic clinical quality measure (eCQM) for use by orthopedic practices to assess potentially inappropriate high-dose post-operative opioid prescribing practices. Measure specifications were revised based on stakeholder feedback, initial testing and a targeted review of the literature. The eCQM was developed and alpha tested on 9,108 opioid-naive patients who received an elective primary total hip or total knee arthroplasty at Mass General Brigham formerly Partners HealthCare System) from 2016 to 2018. Thirty-eight percent of patients were prescribed high doses (defined as an average daily dose ≥90 morphine milligram equivalents) for the duration of their post-operative opioid prescriptions, demonstrating that this is a meaningful performance measure with substantial opportunity for improvement. National implementation and reporting of this eCQM could be used to facilitate quality improvement to deliver standardized, safe and high-quality care.Chest radiographs are the most common diagnostic exam in emergency rooms and intensive care units today. Recently, a number of researchers have begun working on large chest X-ray datasets to develop deep learning models for recognition of a handful of coarse finding classes such as opacities, masses and nodules. In this paper, we focus on extracting and learning fine-grained labels for chest X-ray images. Specifically we develop a new method of extracting fine-grained labels from radiology reports by combining vocabulary-driven concept extraction with phrasal grouping in dependency parse trees for association of modifiers with findings. A total of457finegrained labels depicting the largest spectrum of findings to date were selected and sufficiently large datasets acquired to train a new deep learning model designed for fine-grained classification. We show results that indicate a highly accurate label extraction process and a reliable learning of fine-grained labels. The resulting network, to our knowledge, is the first to recognize fine-grained descriptions offindings in images covering over nine modifiers including laterality, location, severity, size and appearance.