Open Access. Powered by Scholars. Published by Universities.®

Medicine and Health Sciences Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 9 of 9

Full-Text Articles in Medicine and Health Sciences

Vaxinsight: An Artificial Intelligence System To Access Large-Scale Public Perceptions Of Vaccination From Social Media, Jingcheng Du Dec 2019

Vaxinsight: An Artificial Intelligence System To Access Large-Scale Public Perceptions Of Vaccination From Social Media, Jingcheng Du

Dissertations & Theses (Open Access)

Vaccination is considered one of the greatest public health achievements of the 20th century. A high vaccination rate is required to reduce the prevalence and incidence of vaccine-preventable diseases. However, in the last two decades, there has been a significant and increasing number of people who refuse or delay getting vaccinated and who prohibit their children from receiving vaccinations. Importantly, under-vaccination is associated with infectious disease outbreaks. A good understanding of public perceptions regarding vaccinations is important if we are to develop effective vaccination promotion strategies. Traditional methods of research, such as surveys, suffer limitations that impede our understanding of …


Enhancing Clinical Concept Extraction With Contextual Embeddings., Yuqi Si, Jingqi Wang, Hua Xu, Kirk Roberts Nov 2019

Enhancing Clinical Concept Extraction With Contextual Embeddings., Yuqi Si, Jingqi Wang, Hua Xu, Kirk Roberts

Student and Faculty Publications

OBJECTIVE: Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and representations (eg, ELMo, BERT) have further pushed the state of the art in NLP, yet there are no common best practices for how to integrate these representations into clinical tasks. The purpose of this study, then, is to explore the space of possible options in utilizing these new models for clinical concept extraction, including comparing these to traditional word embedding methods (word2vec, GloVe, fastText).

MATERIALS AND METHODS: Both off-the-shelf, open-domain embeddings and …


Design And Architecture Of An Ontology-Driven Dialogue System For Hpv Vaccine Counseling, Amith Faheem Muhammad Aug 2019

Design And Architecture Of An Ontology-Driven Dialogue System For Hpv Vaccine Counseling, Amith Faheem Muhammad

Dissertations & Theses (Open Access)

Speech and conversational technologies are increasingly being used by consumers, with the inevitability that one day they will be integrated in health care. Where this technology could be of service is in patient-provider communication, specifically for communicating the risks and benefits of vaccines. Human papillomavirus (HPV) vaccine, in particular, is a vaccine that inoculates individuals from certain HPV viruses responsible for adulthood cancers - cervical, head and neck cancers, etc. My research focuses on the architecture and development of speech-enabled conversational agent that relies on series of consumer-centric health ontologies and the technology that utilizes these ontologies. Ontologies are computable …


Utilizing Temporal Information In The Ehr For Developing A Novel Continuous Prediction Model, Kang Lin Hsieh Aug 2019

Utilizing Temporal Information In The Ehr For Developing A Novel Continuous Prediction Model, Kang Lin Hsieh

Dissertations & Theses (Open Access)

Type 2 diabetes mellitus (T2DM) is a nation-wide prevalent chronic condition, which includes direct and indirect healthcare costs. T2DM, however, is a preventable chronic condition based on previous clinical research. Many prediction models were based on the risk factors identified by clinical trials. One of the major tasks of the T2DM prediction models is to estimate the risks for further testing by HbA1c or fasting plasma glucose to determine whether the patient has or does not have T2DM because nation-wide screening is not cost-effective.

Those models had substantial limitations on data quality, such as missing values. In this dissertation, I …


Molecular Consequences Of High Taz Expression In Gliomas, Visweswaran Ravikumar Aug 2019

Molecular Consequences Of High Taz Expression In Gliomas, Visweswaran Ravikumar

Dissertations & Theses (Open Access)

Diffuse high grade gliomas are complex and lethal neoplasms of the adult central nervous system that are driven by a range of genetic and epigenetic alterations. Molecular classification of these tumors has identified different transcriptional subtypes, the most notable being Proneural (PN) and Mesenchymal (MES) classes. The most aggressive forms of the disease have a Mesenchymal expression signature, with reported PN-to-MES transition occurring with tumor progression. Master regulatory analysis has identified the transcriptional co-activator TAZ (WWTR1) as a major driver of the MES transition. Overexpression of this single protein in glioma stem cells has been shown to drive a transition …


P53r245w Mutation Elicits Metastatic Phenotype In Pten Deficient Prostate Cancer, Ky Pham Aug 2019

P53r245w Mutation Elicits Metastatic Phenotype In Pten Deficient Prostate Cancer, Ky Pham

Dissertations & Theses (Open Access)

Trp53 mutations are the most frequent genetic alterations in prostate cancer and are associated with more aggressive disease and worse overall survival. The majority of Trp53 mutations in prostate cancer are missense mutations, resulting in amino acid substitutions with profound effect. In addition to the loss of wild type function, missense mutations in Trp53 result in a gain-of-function (GOF) phenotype. This GOF phenotype confers biologic advantages to the tumor cells, enabling them to metastasize and invade distant organs. In this study, we generated mice carrying a conditional prostate-specific p53R245W mutant and Pten deletion to access the role of this common …


Computational Genomic Models For Spatio-Temporal Investigation Of Early Lung Cancer Pathology, Smruthy Sivakumar May 2019

Computational Genomic Models For Spatio-Temporal Investigation Of Early Lung Cancer Pathology, Smruthy Sivakumar

Dissertations & Theses (Open Access)

Lung cancer, of which non-small cell lung cancer (NSCLC) is the most common form, is the second most prevalent cancer and the leading cause of cancer-related deaths. NSCLCs primarily comprise adenocarcinomas (LUAD) and squamous cell carcinomas (LUSC). Advances in early detection and prevention have been limited by the lack of early-stage biomarkers and targets. A comprehensive molecular characterization of premalignant lesions and tumor-adjacent normal tissue can aid in better understanding NSCLC pathogenesis. However, these investigations are further challenged by limited tissue availability and low cellular fractions of detectable somatic mutations.

Therefore, there is a dearth of knowledge about the pathogenesis …


Data Collection Curated With An Application Ontology Describes The Methods And Results Upon Performing An Ex-Vivo Voltage-Clamp Assay On Outer Hair Cells Of The Mammalian Cochlea, Brenda Farrell, Jason Bengtson Jan 2019

Data Collection Curated With An Application Ontology Describes The Methods And Results Upon Performing An Ex-Vivo Voltage-Clamp Assay On Outer Hair Cells Of The Mammalian Cochlea, Brenda Farrell, Jason Bengtson

Research Data

This data collection describes the electrical properties of outer hair cells isolated from the mammalian cochlea of the domestic guinea pig. This data was obtained by performing whole-cell patch clamp voltage clamp assay on cells and monitoring the electrical admittance during a DC voltage ramp. The membrane capacitance was then calculated at each membrane potential from this admittance, and the voltage-independent and voltage-dependent membrane capacitance was determined upon further analysis. In some case the DC conductance was also measured by interrogation of the cell with voltage-step function which was calculated from the change in the mean steady-state current with respect …


Deep Patient Representation Of Clinical Notes Via Multi-Task Learning For Mortality Prediction., Yuqi Si, Kirk Roberts Jan 2019

Deep Patient Representation Of Clinical Notes Via Multi-Task Learning For Mortality Prediction., Yuqi Si, Kirk Roberts

Student and Faculty Publications

We propose a deep learning-based multi-task learning (MTL) architecture focusing on patient mortality predictions from clinical notes. The MTL framework enables the model to learn a patient representation that generalizes to a variety of clinical prediction tasks. Moreover, we demonstrate how MTL enables small but consistent gains on a single classification task (e.g., in-hospital mortality prediction) simply by incorporating related tasks (e.g., 30-day and 1-year mortality prediction) into the MTL framework. To accomplish this, we utilize a multi-level Convolutional Neural Network (CNN) associated with a MTL loss component. The model is evaluated with 3, 5, and 20 tasks and is …