1,720,957 research outputs found
Emith
No full textThe author submitted this entry in the Fictional Short Story category (Amateur division) for the 2023 On My Own Time (OMOT) Art Show.I guess the story is merely a reflection of my own life experiences and personal encounters with these technologies. It intertwines my own imperfections and limitations, presenting a relatable almost protagonist craft, driven by an authentic yearning to assist others and contribute to the improvement of our world. For me, the tale is the canvas in which I can explore the possibilities that lie beyond reality's boundaries
Predicting Heart Disease Through Supervised Machine Learning Algorithms
No full textLightning talk presentation at Texas Health Informatics Alliance (THIA) 2022.The 2022 Texas Health Informatics Alliance Conference was held at the University of Texas at Arlington on September 9, 2022.INTRODUCTION: Heart disease may present in a variety of forms including rhythm-disturbances, pump-failure, silent ischemia, angina, and sudden death among others. Early diagnosis is a crucial step to decrease serious cardiac events. Machine Learning (ML) is a promising tool to improve healthcare diagnostics and risk prediction in highly relevant and common illnesses such as cardiovascular disease.
OBJECTIVE: To develop and evaluate three effective machine learning-supervised models to diagnose heart disease based on individual features.
METHODS: We developed three machine learning models (Elastic net, logistic regression, and random forest) to identify individuals with heart disease. The discovery dataset used for model development included 303 subjects (138 with heart disease and 165 controls) and 14 predictor variables (including traditional cardiovascular risk factors). The outcome variable was the diagnosis of heart disease. The discovery dataset was split into training (70%), validation (10%), and testing (20%) subsets. Model development for elastic net and random forest was accomplished using the training and validation splits, whereas logistic regression was fit using only the training split. We selected hyperparameters for the elastic net model through cross validation and selected the predictors for logistic regression by backward stepwise selection. We calculated predictions using the testing split and evaluated the performance of the classifier based on the area under the receiver-operating-characteristic curve (AUC). Lastly, we used an external validation dataset (n=295, 107 cases and 188 controls) to make predictions.
RESULTS: In the testing dataset, the elastic net model achieved AUC of 90% and accuracy of 86%; the logistic regression AUC was 95% and accuracy of 90%. For the random forest model, the Out-of-Box error was 25.21%; the number of variables used at each split were 3 and the accuracy in the testing test was 83%. When the model was confronted with an external validation dataset, the accuracy was 77%.
CONCLUSION: We developed three models to evaluate ML performance with a discrete dataset. The logistic regression model outperformed the other models with an accuracy of 90% and an AUC of 95%. The final model included 6 variables: Sex, heart rate, exercise induced ST depression, and typical and atypical anginal pain and non-anginal pain. Future work on boosting techniques is required to improve the accuracy of the predictive model. Additionally, developing a comparison analysis between these ML models and conventional clinical approaches may help elucidate the net benefit
Post-Migraine Awareness
Get PDFI've been visited by migraines for as long as I can remember, an inheritance passed down from my mother, and from her mother before her, like a quiet heirloom engraved in my genetic code. Through the years, I found solace in art, like a sanctuary of color and form where the pain could soften, where I could meet it with brushes and ink instead of resistance. In some strange, sacred way, art taught me to live alongside the ache, to texture it into my being rather than fight it. And then, after a severe migraine episode, when my body is still humming with the ghost of pain, when the echoes haven't quite faded, I find myself intensely present. Every detail around me sharpens, as though the universe has turned up the contrast, as though I've been reminded of time itself, of what it means to be human, finite, fragile. In that threshold, where suffering has just loosened its grip, I'm overcome by a strange, glowing gratitude. Not just for the relief, but for the very act of feeling. And in that moment, there's nothing I want more than to create, to write, to draw, as if expression is the only true language left, as the only offering that makes sense in the quiet after the storm
Capturing Clinical Red Flags for Secondary Headaches: A Guideline-Based Ontology Approach
No full textPoster session at the 2025 Texas Regional CTSCA Consortium Conference in San Antonio, Texas.The 2025 Texas Regional CTSCA Consortium Conference was held at the University of Texas at San Antonio in San Antonio, Texas, on June 12-13, 2025.INTRODUCTION: Headache is one of the most common neurological complaints, affecting approximately 90% of people in the U.S. during their lifetime. While most headaches are benign, secondary headaches, those caused by underlying medical conditions such as vascular, neoplastic, infectious, or intracranial pressure-related disorders can be serious and require urgent evaluation1. Prompt identification is critical. We propose the development of a guideline-based decision support tool to help clinicians quickly recognize and triage potential secondary headaches based on signs and symptoms that warrant immediate attention.
OBJECTIVE: To develop a custom, guideline-informed interoperable ontology for secondary headache computable phenotype identification.
METHODS: We manually reviewed 10 clinical guidelines from U.S. and North American sources focused on the diagnosis, management, and referral of secondary headaches. From decision trees, algorithms, and narrative text, we extracted 141 unique features associated with secondary headaches, particularly red flag symptoms. We analyzed the overlap among guidelines to identify consistently flagged features, with "focal neurological deficit" emerging as a common indicator. Using this insight, we built a custom ontology, mapping features to SNOMED CT concepts. We further queried each concept to extract associated synonyms, abbreviations, related symptoms, and anatomical associations, organizing them under semantic relationships such as: "has_laterality", "Is_a", "associated_with", or "affects_anatomical_site".
DISCUSSION: Our ontology provides a standardized, evidence-based framework derived from clinical guidelines, allowing for classifying secondary headache phenotypes based on red flag symptoms in the Electronic Health record (EHR). By embedding this ontology into clinical documentation and decision support workflows, clinicians can be guided toward appropriate next steps such as ordering neuroimaging (Magnetic Resonance versus Computerized Tomography) or refer to a specialist, based on the presence of high-risk features.
CONCLUSION: This project builds on prior efforts using ontology-based models to encode domain knowledge for CDS2 and represents preliminary work in building an advanced clinical decision support system. Future work will involve integrating the ontology into the EHR and developing Natural Language Processing tools for referral triage, information transfer for referrals, documentation management recommendations, and cohort definition for secondary research.
REFERENCES: (1) Robbins MS. Diagnosis and Management of Headache: A Review. Jama. May 11 2021;325(18):1874-1885. doi:10.1001/jama.2021.1640 (2) Rousseau JF, Oliveira E, Tierney WM, Khurshid A. Methods for development and application of data standards in an ontology-driven information model for measuring, managing, and computing social determinants of health for individuals, households, and communities evaluated through an example of asthma. Journal of Biomedical Informatics. 2022/12/01/ 2022;136:104241. doi:https://doi.org/10.1016/j.jbi.2022.10424
Building and Deploying a Cloud Environment for Hosting Custom Application Development Services Within an Academic Tertiary Center
No full textPoster session at the Texas Health Informatics Alliance (THIA) 2023.The 2023 Texas Health Informatics Alliance Conference was hosted by the UT Houston School of Biomedical Health Informatics in Houston, Texas, on September 15, 2023.SIGNIFICANCE: The 21st Century Cures Act (Cures Act) is designed to help accelerate medical product development and bring new innovations and advances to patients who need them faster and more efficiently. Patients can now access their health information including radiology or pathology reports in near real-time. However, a few tools exist to allow patients to interpret these findings.
OBJECTIVE: To design an application that enhances patient understanding of diagnostic descriptions by translating medical reports into lay terms. As well as, building and hosting an environment for custom application development services in our academic center.
METHODS: We developed a web-based application in java that utilizes open AI to translate medical reports to layman terms. Posteriorly, we deployed our application within Microsoft Azure by building a static web app resource. Subsequently, through Visual Studio Code which was connected to our GitHub account. We downloaded an extension specifically designed to work with Azure to build and deploy static apps. By doing so, we were able to set up an authentication function that only allows access within our hospital network.
RESULTS: The application can successfully translate medical jargon into layman terms and the deployment in azure enabled us to implement real-time changes whenever we pushed modifications in GitHub.
CONCLUSIONS: The project was a proof of concept to demonstrate the possibilities of leveraging our organization's cloud services for development and hosting purposes. This demonstration serves as an illustration of the broader potential we have for building and hosting applications that can drive development towards a more patient-focused healthcare system within our hospital. By doing so, we facilitated a playground for medical professionals to develop meaningful tools that can bridge the gap between patients understanding and diagnostic information.
KEYWORDS: Web-based applications; cloud services; digital technologies
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
