Matching Items (3)
Filtering by

Clear all filters

161889-Thumbnail Image.png
Description
Systematic Reviews (SRs) aim to synthesize the totality of evidence for clinical practice and are important in making clinical practice guidelines and health policy decisions. However, conducting SRs manually is a laborious and time-consuming process. This challenge is growing due to the increase in the number of databases to search

Systematic Reviews (SRs) aim to synthesize the totality of evidence for clinical practice and are important in making clinical practice guidelines and health policy decisions. However, conducting SRs manually is a laborious and time-consuming process. This challenge is growing due to the increase in the number of databases to search and the papers being published. Hence, the automation of SRs is an essential task. The goal of this thesis work is to develop Natural Language Processing (NLP)-based classifiers to automate the title and abstract-based screening for clinical SRs based on inclusion/exclusion criteria. In clinical SRs, a high-sensitivity system is a key requirement. Most existing methods for SRs use binary classification systems trained on labeled data to predict inclusion/exclusion. While previous studies have shown that NLP-based classification methods can automate title and abstract-based screening for SRs, methods for achieving high-sensitivity have not been empirically studied. In addition, the training strategy for binary classification has several limitations: (1) it ignores the inclusion/exclusion criteria, (2) lacks generalization ability, (3) suffers from low resource data, and (4) fails to achieve reasonable precision at high-sensitivity levels. This thesis work presents contributions to several aspects of the clinical systematic review domain. First, it presents an empirical study of NLP-based supervised text classification and high-sensitivity methods on datasets developed from six different SRs in the clinical domain. Second, this thesis work provides a novel approach to view SR as a Question Answering (QA) problem in order to overcome the limitations of the binary classification training strategy; and propose a more general abstract screening model for different SRs. Finally, this work provides a new QA-based dataset for six different SRs which is made available to the community.
ContributorsParmar, Mihir Prafullsinh (Author) / Baral, Chitta (Thesis advisor) / Devarakonda, Murthy (Thesis advisor) / Riaz, Irbaz B (Committee member) / Arizona State University (Publisher)
Created2021
Description

SUMMARY: A failed attempt to conduct a systematic review of disparities in racial inclusivity in stroke rehabilitation research: A call to action Group Members: Adeline Beeler & Mikayla McNally Faculty Mentor(s): Dr. Sydney Schaefer & Dr. Keith Lohse Topic Overview: Stroke is responsible for the death of an individual every

SUMMARY: A failed attempt to conduct a systematic review of disparities in racial inclusivity in stroke rehabilitation research: A call to action Group Members: Adeline Beeler & Mikayla McNally Faculty Mentor(s): Dr. Sydney Schaefer & Dr. Keith Lohse Topic Overview: Stroke is responsible for the death of an individual every four minutes in the United States. While all Americans are gravely affected by this statistic, Black Americans are at a significantly increased risk of first stroke incidence when compared to their white counterparts, majorly due to heightened prevalence of stroke risk factors. Not only does race contribute as a factor in stroke incidence, but it also has a considerable impact in the physical impairment of Black Americans following stroke occurrence. While it still remains unclear as to whether or not stroke plays a significant role in stroke rehabilitation efforts, there is a clearly demonstrated need for increased reporting or participation of Black Americans in stroke rehabilitation clinical trials to have the ability to conduct a systematic review of these racial disparities in the near future. In the analysis of 36 stroke rehabilitation-related clinical research studies, 80% of selected trials failed to report any participant racial demographics, with 77.3% of the NIH-funded trials not reporting, as well. Out of the 7 trials that did provide some sort of participant racial information, only 5 successfully provided statistically significant racial data compared to the remainder that simply categorized participants’ race as “white” or “other.” In order to fully investigate the effects of race on stroke rehabilitation, it is imperative that researchers collect and report equally distributed and diverse participant racial data when publishing clinical research. Potential methods of improvement for researchers to include more racially diverse subject populations include more comprehensive and in-depth advertising and recruitment strategies for their studies. Research Methods: In order to produce accurate analyses of the current state of the relationship between race and stroke rehabilitation efforts, 36 stroke rehabilitation clinical research trials from various locations across the United States were identified using the Centralized Open-Access Rehabilitation Database for Stroke (SCOAR). These trials were evaluated in order to extract relevant data, such as number of trial participants, average age of participants, if the research trial was funded by the National Institute of Health (NIH) or not, and any reported participant racial demographic details. Trends across these categories were compared between all trials to determine if any disparities existed in providing data sufficient to support the relationship between varying racial populations and stroke rehabilitation efforts. Future Project Efforts: Future efforts will include the completion of submitting a Point of View/Directions for Research article for publication to offer an opportunity for clinical and basic researchers to examine the discrepancies surrounding racial inclusivity in stroke rehabilitation clinical research. The aim is to improve the ability of clinicians to interpret the literature, translate research studies into practices, and better direct future experiments. Further identification of stroke rehabilitation clinical research trials will be necessary, as well as modifications to current written work content.

ContributorsBeeler, Adeline (Author) / McNally, Mikayla (Co-author) / Schaefer, Sydney (Thesis director) / Lohse, Keith (Committee member) / Barrett, The Honors College (Contributor) / Harrington Bioengineering Program (Contributor)
Created2021-12
Description

SUMMARY: A failed attempt to conduct a systematic review of disparities in racial inclusivity in stroke rehabilitation research: A call to action Group Members: Adeline Beeler & Mikayla McNally Faculty Mentor(s): Dr. Sydney Schaefer & Dr. Keith Lohse Topic Overview: Stroke is responsible for the death of an individual every

SUMMARY: A failed attempt to conduct a systematic review of disparities in racial inclusivity in stroke rehabilitation research: A call to action Group Members: Adeline Beeler & Mikayla McNally Faculty Mentor(s): Dr. Sydney Schaefer & Dr. Keith Lohse Topic Overview: Stroke is responsible for the death of an individual every four minutes in the United States. While all Americans are gravely affected by this statistic, Black Americans are at a significantly increased risk of first stroke incidence when compared to their white counterparts, majorly due to heightened prevalence of stroke risk factors. Not only does race contribute as a factor in stroke incidence, but it also has a considerable impact in the physical impairment of Black Americans following stroke occurrence. While it still remains unclear as to whether or not stroke plays a significant role in stroke rehabilitation efforts, there is a clearly demonstrated need for increased reporting or participation of Black Americans in stroke rehabilitation clinical trials to have the ability to conduct a systematic review of these racial disparities in the near future. In the analysis of 36 stroke rehabilitation-related clinical research studies, 80% of selected trials failed to report any participant racial demographics, with 77.3% of the NIH-funded trials not reporting, as well. Out of the 7 trials that did provide some sort of participant racial information, only 5 successfully provided statistically significant racial data compared to the remainder that simply categorized participants’ race as “white” or “other.” In order to fully investigate the effects of race on stroke rehabilitation, it is imperative that researchers collect and report equally distributed and diverse participant racial data when publishing clinical research. Potential methods of improvement for researchers to include more racially diverse subject populations include more comprehensive and in-depth advertising and recruitment strategies for their studies. Research Methods: In order to produce accurate analyses of the current state of the relationship between race and stroke rehabilitation efforts, 36 stroke rehabilitation clinical research trials from various locations across the United States were identified using the Centralized Open-Access Rehabilitation Database for Stroke (SCOAR). These trials were evaluated in order to extract relevant data, such as number of trial participants, average age of participants, if the research trial was funded by the National Institute of Health (NIH) or not, and any reported participant racial demographic details. Trends across these categories were compared between all trials to determine if any disparities existed in providing data sufficient to support the relationship between varying racial populations and stroke rehabilitation efforts. Future Project Efforts: Future efforts will include the completion of submitting a Point of View/Directions for Research article for publication to offer an opportunity for clinical and basic researchers to examine the discrepancies surrounding racial inclusivity in stroke rehabilitation clinical research. The aim is to improve the ability of clinicians to interpret the literature, translate research studies into practices, and better direct future experiments. Further identification of stroke rehabilitation clinical research trials will be necessary, as well as modifications to current written work content.

ContributorsMcNally, Mikayla (Author) / Beeler, Adeline (Co-author) / Schaefer, Sydney (Thesis director) / Lohse, Keith (Committee member) / Barrett, The Honors College (Contributor) / Watts College of Public Service & Community Solut (Contributor) / Harrington Bioengineering Program (Contributor)
Created2021-12