Health Sciences – Page 12 – UROP Spring Symposium 2021

Health Sciences

Bioinformatics and Biochemical studies on cancer proteins

Protein sequence data is abundant, but ancestry information of those proteins and experimental analysis of the structure of those protein sequences are less available, and costly to produce. Thus, machine learning algorithms are being developed to predict protein structure. For structure prediction, available data is collected and parsed for the specific properties one’s algorithm requires, such as torsion angles for tertiary structure prediction. After an algorithm is trained against this data, the algorithm can be tested in its correctness of predicting protein structure. As a new algorithm is developed, an increase in accuracy and precision is expected.

Bioinformatics and Biochemical studies on cancer proteins Read More »

Machine Learning Methods for Robust ECG Beat Detection

This research was conducted to determine what types of machine learning algorithms were best to determine whether an individual is experiencing heart arrhythmias—such as atrial fibrillation, a type of arrhythmia that can lead to a number of fatal conditions such as blood clots, stroke, and heart failure. Using Python and the sklearn library, a number of machine learning models were tested for accuracy of ECG peak detection, which included Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbors, Classification and Regression Trees, Gaussian Naive Bayes, and Support Vector Machines. The accuracies varied based on the proportion of noise within the ECG file, so an introspective algorithm was developed to choose the optimal peak detection algorithm based on the estimated noise level measured in an ECG. This can be used in the future as a convenient way to accurately determine the presence of heart arrhythmias using wearable devices such as a smart watch.

Machine Learning Methods for Robust ECG Beat Detection Read More »

Machine Learning in Cardiovascular Medicine

Atrial fibrillation is the most common type of heart arrythmia in humans, and our goal is to develop a method of characterizing medical data signals to assist cardiologists to better manage atrial fibrillation. Predicting atrial fibrillation from ECG signals because ECG patterns may change from patient to patient, and include noise. In our study, we provide a comparison across different existing methods of classifying ECG time series using machine learning models. We tested two different machine learning models: a Fully Connected Neural Network and a Support Vector Machine, and compared their performance and accuracy on the Physionet Atrial Fibrillation Challenge Dataset (www.physionet.org). We found that although a Fully Connected Neural Network as a deep learning model is pretty robust when given large amounts of data, the Support Vector Machine method performed better than deep learning when limited data is available to use. Potential applications of this include live analysis of ECG signals that could assist cardiologists to perform diagnosis in real time.

Machine Learning in Cardiovascular Medicine Read More »

Prefrontal-Hippocampal Interactions Supporting Memory Consolidation During Sleep

In this research I will explore how short term memories are supported by the hippocampus and prefrontal cortex. For this project, I trained a cohort of rats on a trace fear conditioning task to evaluate hippocampal-dependent learning and memory. Trace fear conditioning is a hippocampus-dependent learning task that obligates the cohort of rats used to associate an auditory conditioned stimulus (CS) and a minor shock used as the unconditioned stimulus (US) that are separated by an empty trace interval time period. I am currently analyzing the behavior of this cohort through characteristics such as ultrasonic vocalizations (USVs), freezing, and other behavioral traits. With this preliminary data, this project will exploit the effective methods of chronic electrophysiological and calcium imaging recordings in the future. These techniques will be used to probe how sleep influences long-term changes in cortical neurons following learning of a trace fear-conditioning memory task.

Prefrontal-Hippocampal Interactions Supporting Memory Consolidation During Sleep Read More »

Study of Pandemic Publishing: How Scholarly Literature is Affected by COVID-19 Pandemic

Borui Zhang Pronouns: He/Him/His Research Mentor(s): Yulia Sevryugina, Chemistry Librarian/ Senior Associate Librarian Research Mentor School/College/Department: Library, Presentation Date: Thursday, April 22, 2021 Session: Session 4 (2pm-2:50pm) Breakout Room: Room 15 Presenter: 6 Event Link Abstract For privacy concerns this abstract cannot be published at this time. Authors: Borui Zhang Research Method: Library/Archival/Internet Research

Study of Pandemic Publishing: How Scholarly Literature is Affected by COVID-19 Pandemic Read More »

Developing an eHealth Yoga Program for Children

With the rise in popularity of children’s yoga and a greater emphasis on both mental and physical health it is important to establish potential benefits that are reliable and backed by evidence found with strong methodology. Recent systematic reviews, focusing on school aged yoga studies, concluded that methodological limitations such as not measuring fidelity of program implementation (FOI) make it difficult to provide trustworthy conclusions. A component of FOI assessment is establishing Inter-rater reliability for observational measures. This study will explore the potential benefits in children as a direct result of a virtual yoga program implemented into the school day, looking specifically at levels of physical activity, stress, and interoceptive awareness, as well as sleep patterns. Trained raters will identify whether children are on task or off task during the virtual yoga sessions. To measure outcome changes, parents/guardians will complete online surveys using valid and reliable scales. In order to limit statistical ambiguities between raters, they completed three rounds of trainings and practice using recorded yoga sessions. Percent agreement and Cohen’s kappa were established, and necessary adjustments were made to the coding system before the next round of practice. Agreement between the raters improved over the practice trials demonstrated by a change in Cohen’s kappa (k = 0.56 to 0.80). Having reliable participation data will allow the researchers to compare levels of participation with data collected from the parent/guardian surveys. Results will establish reliable new evidence for the field and have important applications for future yoga research in school-based settings.

Developing an eHealth Yoga Program for Children Read More »

A Comparison of Patient Knowledge and Satisfaction with Tele-neuropsychology Services vs. Standard Practice (pre-COVID Face-to-Face Appointments)

Introduction: COVID-19 has limited many patients to video-teleconference (VTC) as opposed to face-to-face (FTF) appointments. With this switch, clinicians hope to maintain the same level of patient satisfaction that was seen previously in a traditional FTF setting, including in the field of neuropsychology. Prior to the COVID-19 pandemic, studies suggested that many patients found VTC just as likable of an experience as FTF for tele-neuropsychology services. Factors such as convenience (staying in the comfort of one’s own home) and cost of travel (gas, flights) all contribute to patient satisfaction with VTC (Seritan et al 2019; Powell et al 2020). However, not all patients have the necessary equipment for telehealth appointments, such as a stable internet connection or a webcam. Additionally, some patients may be uncomfortable with technology and clinician-patient rapport may be difficult to establish (Wilkinson et al 2016). In this study, we investigate patients’ knowledge about neuropsychology prior to VTC and FTF appointments, level of comfort with the technology required for VTC visits, and level of satisfaction with the telehealth services.

A Comparison of Patient Knowledge and Satisfaction with Tele-neuropsychology Services vs. Standard Practice (pre-COVID Face-to-Face Appointments) Read More »

Examining Anxiety Outcomes following Cognitive Behavioral Therapy for Insomnia

Data collected from a randomized controlled noninferiority trial testing cognitive behavior therapy for insomnia (CBTi) delivered face to face versus telemedicine was used to examine the relationship between insomnia and anxiety. Measurements of general anxiety disorder (GAD) and insomnia severity index (ISI) were collected from 65 adults with chronic insomnia before CBTi treatment, immediately post-treatment, and again 12 weeks post-treatment. ISI scores were measured using a seven- item test with higher scores indicating more severe insomnia. Anxiety was measured using the GAD-7 (General Anxiety Disorder – 7), a seven-item survey that measures anxiety severity with higher scores representing more severe insomnia. Baseline measures have shown that as the severity of insomnia increases, anxiety severity increases as well. Measurements of ISI and GAD taken at post-treatment show CBT-I decreased ISI scores by 8.8 and 9.34 points in both treatment groups, indicating there was a decreased insomnia severity following CBT-I. GAD-7 scores reduced by 3.0 and 2.7 points at post-treatment in both groups, indicating decreased anxiety severity.

Examining Anxiety Outcomes following Cognitive Behavioral Therapy for Insomnia Read More »

Examining Anxiety Outcomes following Cognitive Behavioral Therapy for Insomnia

Data collected from a randomized controlled noninferiority trial testing cognitive behavior therapy for insomnia (CBTi) delivered face to face versus telemedicine was used to examine the relationship between insomnia and anxiety. Measurements of general anxiety disorder (GAD) and insomnia severity index (ISI) were collected from 65 adults with chronic insomnia at before CBTi treatment, immediately post-treatment, and again 12 weeks post-treatment. ISI scores were measured using a seven- item test with higher scores indicating more severe insomnia. Anxiety was measured using the GAD-7 (General Anxiety Disorder – 7), a seven-item survey that measures anxiety severity with higher scores representing more severe insomnia. Baseline measures have shown that as the severity of insomnia increases, anxiety severity increases as well. Measurements of ISI and GAD taken at post-treatment show CBT-I decreased ISI scores by 8.8 and 9.34 points in both treatment groups, indicating there was a decreased insomnia severity following CBT-I. GAD-7 scores reduced by 3.0 and 2.7 points at post-treatment in both groups, indicating decreased anxiety severity.

Examining Anxiety Outcomes following Cognitive Behavioral Therapy for Insomnia Read More »

Whole Health Educational Resource Development and Evaluation for Veterans and VA Staff

Whole Health is a system of holistic care focusing on physical and social parameters in the care of Veteran patients that is in place at VA hospitals around the country. The aim of this study is to investigate participants’ perceptions of the Whole Health system of care. The study methodology focuses on a survey containing questions regarding different areas of the Circle of Whole Health (a widely used framework for Whole Health at the VA). The survey is designed by a team of undergraduate researchers at the University of Michigan, working with a physician researcher at the VA Ann Arbor Healthcare System. The survey was sent out to Veterans, VA staff, VA volunteers, and family members of Veterans. At the time of publication of this abstract, the data has been collected and preliminary analysis is in process. Analysis of the survey results in terms of descriptive statistics and tests of relationships, using chi-square tests, is being performed. Specific, detailed, and final results will be available at the time of the Symposium presentation. This final information could be used to better understand which modalities are most understood by Veterans, which areas are most understood by those who support Veterans (such as VA staff, VA volunteers, and family members), and which Whole Health modalities are most effective in improving Veterans’ physical or mental health.

Whole Health Educational Resource Development and Evaluation for Veterans and VA Staff Read More »

lsa logoum logo