Medicine and Health Sciences Commons^™

Data Mining Of Pancreatic Cancer Protein Databases, Peter Revesz, Christopher Assi

CSE Conference and Workshop Papers

Data mining of protein databases poses special challenges because many protein databases are non- relational whereas most data mining and machine learning algorithms assume the input data to be a type of rela- tional database that is also representable as an ARFF file. We developed a method to restructure protein databases so that they become amenable for various data mining and machine learning tools. Our restructuring method en- abled us to apply both decision tree and support vector machine classifiers to a pancreatic protein database. The SVM classifier that used both GO term and PFAM families to characterize proteins gave …

An Automated Pathological Class Level Annotation System For Volumetric Brain Images, Thien Anh Dinh, Tomi Silander, C. C. Tchoyoson Lim, Tze-Yun Leong

Research Collection School Of Computing and Information Systems

We introduce an automated, pathological class level annotation system for medical volumetric brain images. While much of the earlier work has mainly focused on annotating regions of interest in medical images, our system does not require annotated region level training data nor assumes perfect segmentation results for the regions of interest; the time and effort needed for acquiring training data are hence significantly reduced. This capability of handling high-dimensional noisy data, however, poses additional technical challenges, since statistical estimation of models for such data is prone to over-fitting. We propose a framework that combines a regularized logistic regression method and …

Bright Futures As-Is Assessment: How Child-Serving Practices, Health Systems, And The State Of Maine Use And Exchange Specific Clinical Data Related To Child Health Quality Measures, Kyra Chamberlain Ms, Rn, Martha Elbaum-Williamson Mpa, Jonathan Ives Mpm, Csm, Jin Liao M.Eng

Population Health & Health Policy

The purpose of the As Is assessment is to provide a description of Maine’s current HIT environment specifically pertaining to how EPSDT and other clinical data are entered, used, and exchanged electronically through information systems at pediatric practices, health systems, the State of Maine, and HIN. This information will inform plans currently under development by IHOC for electronic data exchange and child health measure calculation.

The Use Of Mobile Phone Cameras In Guiding Treatment Decisions For Laceration Care, Neal Sikka, Michael Pirri, Katrina Norbury Carlin, Ryan Strauss, Faisal Rahimi, Jesse M. Pines

Emergency Medicine Faculty Publications

Objectives: Mobile phone technology may be useful in helping to guide medical decisions for lacerations. We examined whether emergency department (ED) provider opinions on which lacerations require repair differed using mobile phone–generated images compared with in-person evaluations.

Subjects and Methods: Patients presenting to an urban ED for initial and follow-up laceration care were prospectively enrolled. Patients took four mobile phone pictures of their laceration and provided a medical history. Cases were reviewed by ED providers who assessed image quality and made a recommendation about whether the laceration needed repair. The same provider then assessed the patient in-person. Concordant decision-making between …

Optimizing Network Connectivity For Mobile Health Technologies In Sub-Saharan Africa, Mark J. Siedner, Alexander J. Lankowski, Derrick Musinga, Jonathan Jackson, Conrad Muzoora, Peter W. Hunt, Jeffrey N. Martin, David Bangsberg, Jessica E. Haberer

OHSU-PSU School of Public Health Faculty Publications and Presentations

Background: Mobile health (mHealth) technologies hold incredible promise to improve healthcare delivery in resourcelimited settings. Network reliability across large catchment areas can be a major challenge. We performed an analysis of network failure frequency as part of a study of real-time adherence monitoring in rural Uganda. We hypothesized that the addition of short messaging service (SMS+GPRS) to the standard cellular network modality (GPRS) would reduce network disruptions and improve transmission of data.

Methods: Participants were enrolled in a study of real-time adherence monitoring in southwest Uganda. In June 2011, we began using Wisepill devices that transmit data each time the …

Machine Learning Approach To Extract Diagnostic And Prognostic Thresholds: Application In Prognosis Of Cardiovascular Mortality, Luis J. Mena, Eber E. Orozco, Vanessa G. Felix, Rodolfo Ostos, Jesus D. Melgarejo, Gladys E. Maestre

School of Medicine Publications and Presentations

Machine learning has become a powerful tool for analysing medical domains, assessing the importance of clinical parameters, and extracting medical knowledge for outcomes research. In this paper, we present a machine learning method for extracting diagnostic and prognostic thresholds, based on a symbolic classification algorithm called REMED. We evaluated the performance of our method by determining new prognostic thresholds for well-known and potential cardiovascular risk factors that are used to support medical decisions in the prognosis of fatal cardiovascular diseases. Our approach predicted 36% of cardiovascular deaths with 80% specificity and 75% general accuracy. The new method provides an innovative …

Meaningful Use And Meaningful Curricula: A Survey Of Health Informatics Programs In The U.S., Kai Koong, Madison Ngafeeson, Lai Lui

Journal Articles

The introduction of the US government’s Meaningful Use criteria carries with it many implications including the training curriculum of healthcare personnel. This study examines 108 health informatics degree programmes across the USA. First, the courses offered are identified and classified into generic classes. Next, these generic groupings are mapped to two important frameworks: the Learning to Manage Health Information (LMHI) academic framework; and the Meaningful Use criteria policy framework. Results suggest that while current curricula seemed acceptable in addressing Meaningful Use Stage 1 objective, there was insufficient evidence that these curricula could support Meaningful Use Stage 2 and …

Intra-Industry Effects Of Information Security Breaches On Firm Performance, Humayun Zafar, Myung Ko, Kweku-Muata Osei-Bryson

Humayun Zafar

Instances of information security breaches are wide ranging, and can affect companies of different industries and sizes. We investigate the impact of publicly announced information security breaches of public organizations on their competitors that are comparable in size and operate in the same industry. This is called intra-industry information transfer, and has not been subject to extensive research in IS. We use matched-sampling methodology to measure the difference in firm performance using financial ratios, and interpret the results using paired samples t and Wilcoxon matched pair tests. Our results present a departure from intuition regarding the efficacy of security breaches …

Technical Desiderata For The Integration Of Genomic Data Into Electronic Health Records., Daniel R Masys, Gail P Jarvik, Neil F Abernethy, Nicholas R Anderson, George J Papanicolaou, Dina N Paltoo, Mark A Hoffman, Isaac S Kohane, Howard P Levy

Manuscripts, Articles, Book Chapters and Other Papers

The era of "Personalized Medicine," guided by individual molecular variation in DNA, RNA, expressed proteins and other forms of high volume molecular data brings new requirements and challenges to the design and implementation of Electronic Health Records (EHRs). In this article we describe the characteristics of biomolecular data that differentiate it from other classes of data commonly found in EHRs, enumerate a set of technical desiderata for its management in healthcare settings, and offer a candidate technical approach to its compact and efficient representation in operational systems.

High Acceptability For Cell Phone Text Messages To Improve Communication Of Laboratory Results With Hiv-Infected Patients In Rural Uganda: A Cross-Sectional Survey Study, Mark J. Siedner, Jessica E. Haberer, Mwebesa B. Bwana, Norma C. Ware, David Bangsberg

OHSU-PSU School of Public Health Faculty Publications and Presentations

Background: Patient-provider communication is a major challenge in resource-limited settings with large catchment areas. Though mobile phone usership increased 20-fold in Africa over the past decade, little is known about acceptability of, perceptions about disclosure and confidentiality, and preferences for cell phone communication of health information in the region.

Methods: We performed structured interviews of fifty patients at the Immune Suppression Syndrome clinic in Mbarara, Uganda to assess four domains of health-related communication: a) cell phone use practices and literacy, b) preferences for laboratory results communication, c) privacy and confidentiality, and d) acceptability of and preferences for text messaging to …

Provider And Patient Satisfaction With The Use Of Telemedicine In The Delivery Of Healthcare, Rohit Dhingra

Honors Theses

The objective of this thesis was to look at provider and patient satisfaction with the use of telemedicine in the delivery of healthcare. From the literature, it is clear that the providers and patients find different aspects of telemedicine to be appealing but have noted certain limitations with its use. Each study that was reviewed in the literature explored a different type of telemedicine, but in no way covered all of its current applications. In my study, I interviewed three patients and three providers. The patients all use a homecare telemedicine unit in which they can self-measure basic vital signs, …

Problems And Issues In Implementing Innovative Curriculum In The Developing Countries: The Pakistani Experience, Syeda Kauser Ali, Lubna A. Baig

Department for Educational Development

Background: The Government of Pakistan identified 4 medical Colleges for introduction of COME, one from each province. Curriculum was prepared by the faculty of these colleges and launched in 2001 and despite concerted efforts could not be implemented. The purpose of this research was to identify the reasons for delay in implementation of the COME curriculum and to assess the understanding of the stakeholders about COME.

Methods: Mixed methods study design was used for data collection. In-depth interviews, mail-in survey questionnaire, and focus group discussions were held with the representatives of federal and provincial governments, Principals of medical colleges, faculty …

Ehrs Connect Research And Practice: Where Predictive Modeling, Artificial Intelligence, And Clinical Decision Support Intersect, Casey C. Bennett, Thomas W. Doub, Rebecca Selove

Center for Prevention Research Publications

Objectives

Electronic health records (EHRs) are only a first step in capturing and utilizing health-related data—the challenge is turning that data into useful information. Furthermore, EHRs are increasingly likely to include data relating to patient outcomes, functionality such as clinical decision support, and genetic information as well, and, as such, can be seen as repositories of increasingly valuable information about patients’ health conditions and responses to treatment over time.

Methods

We describe a case study of 423 patients treated by Centerstone within Tennessee and Indiana in which we utilized electronic health record data to generate predictive algorithms of individual patient …

Flowcell Systems For Single Molecule Detection, John G. K. Williams, Gregory R. Bashford, Jiyan Chen, Dan Draney, Nara Narayanan, Bambi L. Reynolds, Pamela Sheaff

Biomedical Imaging and Biosignal Analysis Laboratory

The present invention provides compounds, methods and systems for sequencing nucleic acid using single molecule detection. Using labeled NPs that exhibit charge-switching behavior, single-molecule DNA sequencing in a microchannel sorting system is realized. In operation, sequencing products are detected enabling real-time sequencing as successive detectable moieties flow through a detection channel. By electrically sorting charged molecules, the cleaved product molecules are detected in isolation without interference from unincorporated NPs and without illuminating the polymerase-DNA complex.

Health Information Privacy In The Correctional Environment, Melissa M. Goldstein

Health Policy and Management Faculty Publications

Information technology is considered a transformative element in health care because it facilitates the transparency and sharing of health information, which have always been central to the practice of medicine and the delivery of high-quality care. The widespread use of electronic health records (EHRs) and electronic health information exchange, among other technologies, is considered essential to improving the quality of care, reducing medical errors, reducing health disparities, and advancing the delivery of patient-centered medical care.

Computer Physician Order Entry And Clinical Decision Support Systems: Benefits And Concerns, Joseph Shaffer, Alberto Coustasse

Management Faculty Research

Computerized Physician Order Entry has emerged as the greatest potential to decrease medications errors and improve efficiency. A literature review was conducted in systematic stages that included the research data from the last 25 years. Efficiencies were found with a decrease in overall workload of nurses, pharmacists and clerical workers. This led to decreased operating expenses. A secure way of transferring physician orders electronically will help hospitals and physicians practice a more efficient and higher quality of care in the US healthcare system.

Financial Position And Adoption Of Electronic Health Records: A Retrospective Longitudinal Study, Jay J. Shen, Gregory O. Ginn

Public Health Faculty Publications

AIM: Financial barriers are a major factor of slow electronic health record (EHR) adoption among US hospitals. All existing literature focuses on relationships between current or short-term financial position and EHR adoption. This study examines relationship between financial position in previous years and the current level of EHR adoption.

METHODS: Retrospective longitudinal data were extracted from (1) the 2009 American Hospital Association (AHA) EHR implementation survey; (2) the 2002 and 2006 Centers for Medicare & Medicaid Cost Reports; and (3) the 2002 and 2006 AHA Annual Survey containing organizational and operational data. The final sample was 2,701 acute care hospitals …

Integrating An Automated Diabetes Management System Into The Family Management Of Children With Type 1 Diabetes: Results From A 12-Month Randomized Controlled Technology Trial., Tammy Toscos Phd, Stephen W Ponder, Barbara J Anderson, Mayer B Davidson, Martin L Lee, Elaine Montemayor-Gonzalez, Patricia Reyes, Eric Link, Kevin L Mcmahon

Health Services and Informatics Research

OBJECTIVE: The study objective was to evaluate how the use of a pervasive blood glucose monitoring (BGM) technology relates to glycemic control, report of self-care behavior, and emotional response to BGM of children with type 1 diabetes and their parents.

RESEARCH DESIGN AND METHODS: Forty-eight children aged less than 12 years (mean 8.8 years) with type 1 diabetes were randomly assigned to one of two study groups, a control group (conventional care without technology) or an experimental group (conventional care with technology), and followed for 12 months. Families in the experimental group were given the Automated Diabetes Management System (ADMS), …

Benefits And Constraints Of Telepsychiatry Utilization In The United States, Bruce A. Stec, Alberto Coustasse

Management Faculty Research

This conference presentation describes the benefits and constraints of utilizing telemedicine primarily focusing on the field of psychiatry in the United States with the current system of healthcare. The utilization of telemedicine in the field of psychiatry is believed to provide better access, quality and care to the patients who necessitate psychiatric care in their overall medical care. Telemedicine has been a successfully integrated program into psychiatric facilities reaching rural, prisons or city facilities based on that it has increased the volume of patients in which physicians can reach out to and diagnose, as well as treat patients with limitations …

Finding The Medicine For Healthcare, Singapore Management University

Perspectives@SMU

Singapore’s healthcare system is lauded internationally as a model that has managed to restrain costs while delivering excellent health outcomes. The country spends below four per cent of its GDP on healthcare and was ranked 6th out of 191 countries on overall health system performance by the World Health Organisation in 2000.

The Emergence And Potential Impact Of Medicine 2.0 In The Healthcare Industry, Terra Stump, Sarah Zilch, Alberto Coustasse

Management Faculty Research

Medicine 2.0 has emerged within healthcare information technology to enable more defined relationships among providers and patients. Physicians, hospitals, and patients are using Medicine 2.0 through social networking to maintain their foothold in the evolution of medical technologies. The authors’ purpose was to determine potential improvements that Medicine 2.0 has on communication and collaboration of healthcare information. Research has shown that Medicine 2.0 has integrated into the healthcare industry and is enabling an increase in communication in healthcare matters. The provider-patient relationship is improving through the use of Medicine 2.0 and has positively impacted society so far.

Lassa: Emotion Detection Via Information Fusion, Ning Yu, Sandra Kübler, Joshua Herring, Yu-Yin Hsu, Ross Israel, Charese Smiley

Information Science Faculty Publications

Due to the complexity of emotions in suicide notes and the subtle nature of sentiments, this study proposes a fusion approach to tackle the challenge of sentiment classification in suicide notes: leveraging WordNet-based lexicons, manually created rules, character-based n-grams, and other linguistic features. Although our results are not satisfying, some valuable lessons are learned and promising future directions are identified.

Feasibility And Compliance With Daily Home Ecg Monitoring Of The Qt Interval In Heart Transplant Recipients, Erik V. Carter, Kathleen T. Hickey, David M. Pickham, Lynn V. Doering, Belinda Chen, Patricia R. E. Harris, Barbara J. Drew

Collected Faculty and Staff Scholarship

About 13% of adult heart transplant recipients do not survive to one year and a major cause of death is acute cellular allograft rejection.^1,2 According to the 2009 annual United States data published from the International Society for Heart Lung Transplantation Registry, acute rejection occurs in 25 – 35% of transplant recipients within the first year following transplant surgery.³ In order to detect the early stages of rejection so that more aggressive and early immunosuppressant therapy can be initiated, frequent biopsies of heart tissue are performed (typically, weekly or every other week in the first 3 months and …

Two-Dimensional Blood Flow Velocity Estimation Using Apparent Speckle Pattern Angle Dependence On Scan Velocity, Tiantian Xu, Gregory R. Bashford

Biomedical Imaging and Biosignal Analysis Laboratory

An algorithm which measures the lateral component of blood flow velocity was developed in our previous studies based on the increase in speckle size due to relative motion between moving scatterers and spatial rate of scanner A-line acquisition (scan velocity). In this paper, the apparent dominant angle of the speckle pattern in a straight vessel was investigated and a new method of two-dimensional blood flow velocity estimation is introduced. Different scan velocities were used for data acquisition from blood flow traveling at an angle relative to the ultrasound beam. The apparent angle of the speckle pattern changes with different scan …

Monitoring Cerebral Hemodynamics With Transcranial Doppler Ultrasound During Cognitive And Exercise Testing In Adults Following Unilateral Stroke, Brian P. Watt, Judith M. Burnfield, Edward J. Truemper, Thad W. Buster, Gregory R. Bashford

Biomedical Imaging and Biosignal Analysis Laboratory

An observational study was performed as a preliminary investigation into the use of transcranial Doppler ultrasound (TCD) for recording cerebral hemodynamic changes during multiple tasks. TCD is a method of measuring cerebral blood flow (CBF) using ultrasound transducers in contact with the surface of the head. Using the maximum flow envelope of the Doppler spectrum returning from the middle cerebral artery (MCA), standard clinical flow indices can be calculated and displayed in real time providing information concerning perturbations in CBF and their potential cause. These indices as well as flow velocity measurements have been recognized as useful in measuring changes …

Genetic Studies Of Complex Human Diseases: Characterizing Snp-Disease Associations Using Bayesian Networks, Bing Han, Xue-Wen Chen, Zohreh Talebizadeh, Hua Xu

Wayne State University Associated BioMed Central Scholarship

Abstract

Background

Detecting epistatic interactions plays a significant role in improving pathogenesis, prevention, diagnosis, and treatment of complex human diseases. Applying machine learning or statistical methods to epistatic interaction detection will encounter some common problems, e.g., very limited number of samples, an extremely high search space, a large number of false positives, and ways to measure the association between disease markers and the phenotype.

Results

To address the problems of computational methods in epistatic interaction detection, we propose a score-based Bayesian network structure learning method, EpiBN, to detect epistatic interactions. We apply the proposed method to both simulated datasets and …

Information Literacy And Nnra, Nkiru Opara Jarlath

Nkiru Opara

Information literacy enables one to master content and extend investigation,become more self-directed, and assume greater control over search for information.

Dss Dynamic Change Iom Rwj Project, Christine T. Kovner, Chuo H. Lee, Edward J. Lusk, Carina Catigbak, Nellie Selander

Edward J. Lusk

No abstract provided.

Dynamic Change Dss Manual Iom Rwj-Project, Edward J. Lusk, Chuo H. Lee, Christine T. Kovner, Carina Catigbak, Nellie Selander

Edward J. Lusk

No abstract provided.

Function-­Preserving Filters For Sampling In Biological Networks, Kathryn Dempsey Cooper, Sanjukta Bhowmick, Hesham Ali

Interdisciplinary Informatics Faculty Publications

Assays created to study systems of disease and aging can offer a whole new set of therapeutic targets. However, with experiments of this immense volume, data becomes unmanageable for many traditional analyses. Enter the biological network, a tool for modeling relationships among high-throughput data that is quickly rising in popularity. Small networks (in the order of hundreds to few thousands of nodes) use relationships between network structure to infer biological function; this relationship has been confirmed and used in many studies to advance the study of model organisms. Networks built for assessing entire genomes, or entire protein repertoires, however, tend …