Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799424
Kristen J. Bell, Madeline Hennessy, Michael Henry, Avni Malik
Liver transplantation is a critical, life-saving treatment option for patients with terminal liver disease. Despite an organ shortage, many donated livers are discarded for reasons such as poor organ condition and physical incompatibility with a recipient. Current clinical models for liver risk assessment only utilize tabular data and result in poor precision and recall. Critical information relevant to this decision-making is likely included in the free-text clinical notes from donor evaluations that contain pertinent medical and social history of the donor that is currently unavailable in tabular data sources. This article describes the development of a model using these free-text clinical notes using a variety of Natural Language Processing (NLP) and machine learning (ML) techniques to predict the outcomes of three key metrics: 1) liver utilization rate, 2) 30-day mortality rate, and 3) 1-year mortality rate. The free-text narratives were useful for predicting liver utilization, with an associated area under the curve (AUC) score of 0.81, but were not useful for predicting both mortality outcomes, with associated AUC scores of 0.53 and 0.52, for 30-day and 1-year mortality, respectively. Using a locally interpretable model-agnostic explanations (LIME) algorithm, key phrases, like “dcd” and “alcohol” were found to be associated with unutilized livers, while “brain” and “heroin” were associated with utilized livers. Based on these findings, modeling donor text narratives may substantially contribute to improved decision-making and outcomes of liver transplantation.
{"title":"Predicting Liver Utilization Rate and Post- Transplant Outcomes from Donor Text Narratives with Natural Language Processing","authors":"Kristen J. Bell, Madeline Hennessy, Michael Henry, Avni Malik","doi":"10.1109/sieds55548.2022.9799424","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799424","url":null,"abstract":"Liver transplantation is a critical, life-saving treatment option for patients with terminal liver disease. Despite an organ shortage, many donated livers are discarded for reasons such as poor organ condition and physical incompatibility with a recipient. Current clinical models for liver risk assessment only utilize tabular data and result in poor precision and recall. Critical information relevant to this decision-making is likely included in the free-text clinical notes from donor evaluations that contain pertinent medical and social history of the donor that is currently unavailable in tabular data sources. This article describes the development of a model using these free-text clinical notes using a variety of Natural Language Processing (NLP) and machine learning (ML) techniques to predict the outcomes of three key metrics: 1) liver utilization rate, 2) 30-day mortality rate, and 3) 1-year mortality rate. The free-text narratives were useful for predicting liver utilization, with an associated area under the curve (AUC) score of 0.81, but were not useful for predicting both mortality outcomes, with associated AUC scores of 0.53 and 0.52, for 30-day and 1-year mortality, respectively. Using a locally interpretable model-agnostic explanations (LIME) algorithm, key phrases, like “dcd” and “alcohol” were found to be associated with unutilized livers, while “brain” and “heroin” were associated with utilized livers. Based on these findings, modeling donor text narratives may substantially contribute to improved decision-making and outcomes of liver transplantation.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133183628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799366
Abhinay Dommalapati, Anura Ranasinghe, J. Peele, Stephen Whetzel, Michael Jones, A. Bell, E. Chemyakin, S. Stamnes, Heman Shakeri
A growing awareness of the adverse effects of high concentrations of aerosol pollutants on human health [1] motivates the need to accurately measure and forecast the amount of PM2.5 in the air; that is the particulate matter of aerosol particles with size 2.5 microns or less in diameter [2]. Quantifying concentrations of aerosols, particularly near the surface, is foundational to the understanding of the sources, evolution, and transport of PM2.5 and will help to support environmental justice for communities across America and the world. Moreover, developing improved algorithms to accurately invert or retrieve surface-level PM2.5 from satellite remote sensing is critical to improve neighborhood-scale estimates of air quality [3]. In particular, past and future satellite polarimeter and lidar measurements will be key to understanding surface-level PM2.5 conditions in real-time across the globe. A current solution to the retrieval of accurate aerosol properties from satellite polarimeter measurements has been developed by NASA for the Plankton, Aerosols, Clouds and Ecosystems mission (PACE) mission in the form of the Micro-physical Aerosol Properties from Polarimetry (PACE-MAPP) algorithm [4]. However, because solving the vector radiative transfer is numerically intensive, and solving the non-linear inverse problem requires an iterative approach that for multiple channels involves hundreds of vector radiative transfer calls, this approach delivers products at a rate that has latencies too large for and is prohibitively inefficient for the large-scale datasets that will be needed to resolve PM2.5 at neighborhood-scale resolutions of less than 1 km by 1 km. PACE-MAPP solves this problem by developing a neural network framework to replace the complex and time-consuming vector radiative transfer calculations at each iteration. In this study, we apply the PACE-MAPP framework to polarimetry data gathered from the POLDER instrument (PO-Larization and Directionality of the Earth's Reflectances) [5] onboard PARASOL, a satellite that flew from 2006 to 2013 as a part of efforts to understand the effects of clouds and aerosols on the Earth's climate [6] [7], and demonstrate for the first time ever that a neural-network-based approach using coupled atmosphere-ocean vector radiative transfer can be applied to retrieve aerosol properties from satellite polarimeter data, and to take the first step toward evaluating the algorithm's performance at producing air quality products such as PM2.5. We further demonstrate the feasibility of deploying neural networks to solve the numerical inefficiencies that plague satellite polarimeter retrievals while maintaining high accuracy, and expect to cut the speed of acquisition by a factor of 1000.
{"title":"A neural-network-based forward model to improve air quality estimation from spaceborne polarimeters","authors":"Abhinay Dommalapati, Anura Ranasinghe, J. Peele, Stephen Whetzel, Michael Jones, A. Bell, E. Chemyakin, S. Stamnes, Heman Shakeri","doi":"10.1109/sieds55548.2022.9799366","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799366","url":null,"abstract":"A growing awareness of the adverse effects of high concentrations of aerosol pollutants on human health [1] motivates the need to accurately measure and forecast the amount of PM2.5 in the air; that is the particulate matter of aerosol particles with size 2.5 microns or less in diameter [2]. Quantifying concentrations of aerosols, particularly near the surface, is foundational to the understanding of the sources, evolution, and transport of PM2.5 and will help to support environmental justice for communities across America and the world. Moreover, developing improved algorithms to accurately invert or retrieve surface-level PM2.5 from satellite remote sensing is critical to improve neighborhood-scale estimates of air quality [3]. In particular, past and future satellite polarimeter and lidar measurements will be key to understanding surface-level PM2.5 conditions in real-time across the globe. A current solution to the retrieval of accurate aerosol properties from satellite polarimeter measurements has been developed by NASA for the Plankton, Aerosols, Clouds and Ecosystems mission (PACE) mission in the form of the Micro-physical Aerosol Properties from Polarimetry (PACE-MAPP) algorithm [4]. However, because solving the vector radiative transfer is numerically intensive, and solving the non-linear inverse problem requires an iterative approach that for multiple channels involves hundreds of vector radiative transfer calls, this approach delivers products at a rate that has latencies too large for and is prohibitively inefficient for the large-scale datasets that will be needed to resolve PM2.5 at neighborhood-scale resolutions of less than 1 km by 1 km. PACE-MAPP solves this problem by developing a neural network framework to replace the complex and time-consuming vector radiative transfer calculations at each iteration. In this study, we apply the PACE-MAPP framework to polarimetry data gathered from the POLDER instrument (PO-Larization and Directionality of the Earth's Reflectances) [5] onboard PARASOL, a satellite that flew from 2006 to 2013 as a part of efforts to understand the effects of clouds and aerosols on the Earth's climate [6] [7], and demonstrate for the first time ever that a neural-network-based approach using coupled atmosphere-ocean vector radiative transfer can be applied to retrieve aerosol properties from satellite polarimeter data, and to take the first step toward evaluating the algorithm's performance at producing air quality products such as PM2.5. We further demonstrate the feasibility of deploying neural networks to solve the numerical inefficiencies that plague satellite polarimeter retrievals while maintaining high accuracy, and expect to cut the speed of acquisition by a factor of 1000.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124141805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799346
Emily Aprigliano, Beth Ellinport, Allison Forsyth, H. Rowe
The collapse of the Champlain Tower in Surfside Florida on June 24, 2021 and its subsequent 14-day search and rescue mission caused public and government concerns about the efficiency of urban search and rescue (USAR) strategies. There is, however, no published tool for assessing search findings from a disciplined search methodology, supported by data from USAR missions. Each task force must therefore rely on its own expertise. In this project, we developed a decision support tool prototype that promotes the establishment of a systematic, probability-based strategy to project the survival likelihood for any given area of a collapsed structure. The tool is designed to combine multiple experts' onsite survival probability assessments to assist USAR leaders in making informed decisions about the length and effectiveness of rescue missions based on the unique and evolving factors of a collapse. The probability-based tool is intended to increase the certainty and reduce the time needed for decision makers to conclude that any and all survivors have been found. The time and resources saved by using this tool can then be directed towards other collapse sites or to other post-disaster recovery efforts for the community.
{"title":"A Systematic Approach to Maximizing Search Capabilities for Finding Trapped Survivors in Collapsed Structures","authors":"Emily Aprigliano, Beth Ellinport, Allison Forsyth, H. Rowe","doi":"10.1109/sieds55548.2022.9799346","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799346","url":null,"abstract":"The collapse of the Champlain Tower in Surfside Florida on June 24, 2021 and its subsequent 14-day search and rescue mission caused public and government concerns about the efficiency of urban search and rescue (USAR) strategies. There is, however, no published tool for assessing search findings from a disciplined search methodology, supported by data from USAR missions. Each task force must therefore rely on its own expertise. In this project, we developed a decision support tool prototype that promotes the establishment of a systematic, probability-based strategy to project the survival likelihood for any given area of a collapsed structure. The tool is designed to combine multiple experts' onsite survival probability assessments to assist USAR leaders in making informed decisions about the length and effectiveness of rescue missions based on the unique and evolving factors of a collapse. The probability-based tool is intended to increase the certainty and reduce the time needed for decision makers to conclude that any and all survivors have been found. The time and resources saved by using this tool can then be directed towards other collapse sites or to other post-disaster recovery efforts for the community.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123785097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799354
Rahul Dhansinghani, A. Ibrahim, Aditya Kannoth, C. Miller, L. Nguyen, Steven Pham, R. Bailey
Charlottesville City Schools, like many school districts around the country, is interested in expanding the number of children with safe routes to walk to school in response to bus driver shortages. However, there is currently not much walking infrastructure that allows elementary students to do so, and the city would like a way to prioritize infrastructure projects that meet current needs. This project aims to provide decision-makers with a methodology to assess the walkability of school districts in order to prioritize future infrastructure investments. The methodology, built with significant stakeholder involvement, is designed to be transparent to all stakeholders, easy to use, and built on sound decision theory principles while integrating equity in the decision process. The methodology consists of three phases. First, a geospatial information system (GIS) is used to identify areas with the greatest need based on the walkability of roads and socioeconomic factors within communities. Once areas in need have been identified, projects in these areas are compiled. The second step calculates a prioritization score to each project based on the calculated walkability improvement the project will have and how many people will be impacted by the project. The final step visualizes the prioritization score and cost of each project. The methodology was then evaluated against objectives that were determined in collaboration with the primary stakeholders that would be applying the method.
{"title":"Design of a Prioritization Methodology for Equitable Infrastructure Planning","authors":"Rahul Dhansinghani, A. Ibrahim, Aditya Kannoth, C. Miller, L. Nguyen, Steven Pham, R. Bailey","doi":"10.1109/sieds55548.2022.9799354","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799354","url":null,"abstract":"Charlottesville City Schools, like many school districts around the country, is interested in expanding the number of children with safe routes to walk to school in response to bus driver shortages. However, there is currently not much walking infrastructure that allows elementary students to do so, and the city would like a way to prioritize infrastructure projects that meet current needs. This project aims to provide decision-makers with a methodology to assess the walkability of school districts in order to prioritize future infrastructure investments. The methodology, built with significant stakeholder involvement, is designed to be transparent to all stakeholders, easy to use, and built on sound decision theory principles while integrating equity in the decision process. The methodology consists of three phases. First, a geospatial information system (GIS) is used to identify areas with the greatest need based on the walkability of roads and socioeconomic factors within communities. Once areas in need have been identified, projects in these areas are compiled. The second step calculates a prioritization score to each project based on the calculated walkability improvement the project will have and how many people will be impacted by the project. The final step visualizes the prioritization score and cost of each project. The methodology was then evaluated against objectives that were determined in collaboration with the primary stakeholders that would be applying the method.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121659854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799370
Candace Miu, Jesilyn Gopurathingal, Vineeth Thota, M. Thompson, Niels van Beek, J. Kuczynski, J. Gadewadikar, Tariq Iqbal
Financial literacy is crucial for saving money, avoiding debt, establishing strong credit, and many other skills that help build wealth throughout an individual's life. A very large percentage of Americans from various demographics and backgrounds do not have the basic financial and economic knowledge to sustain themselves financially. Our proposed solution to tackle financial illiteracy is by ensuring students are taught the foundational expertise at a young age so that they make wise financial choices by the time they reach adulthood. We have developed a virtual voice assistant that will improve financial literacy by offering lessons that will cover all topics within the National Standards in K-12 Personal Finance Education educational curricula. Data was collected and analyzed in order to assess the effectiveness, robustness, and engagement of the voice assistant. While further analysis on engagement should be conducted, the bot met baseline goals of effectiveness and robustness which can further be improved through more intent training and testing on potential users.
{"title":"A Financial Literacy AI-Enabled Voice Assistant System for Educational Use","authors":"Candace Miu, Jesilyn Gopurathingal, Vineeth Thota, M. Thompson, Niels van Beek, J. Kuczynski, J. Gadewadikar, Tariq Iqbal","doi":"10.1109/sieds55548.2022.9799370","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799370","url":null,"abstract":"Financial literacy is crucial for saving money, avoiding debt, establishing strong credit, and many other skills that help build wealth throughout an individual's life. A very large percentage of Americans from various demographics and backgrounds do not have the basic financial and economic knowledge to sustain themselves financially. Our proposed solution to tackle financial illiteracy is by ensuring students are taught the foundational expertise at a young age so that they make wise financial choices by the time they reach adulthood. We have developed a virtual voice assistant that will improve financial literacy by offering lessons that will cover all topics within the National Standards in K-12 Personal Finance Education educational curricula. Data was collected and analyzed in order to assess the effectiveness, robustness, and engagement of the voice assistant. While further analysis on engagement should be conducted, the bot met baseline goals of effectiveness and robustness which can further be improved through more intent training and testing on potential users.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122036176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799411
Maddie Robinson, Jackson Sompayrac, Nicole Beachy, Hana Sexton, Aidan Jacobs, A. Clarens
The majority of US buildings use natural gas for heating even though it is a potent greenhouse gas that relies on a leaking infrastructure with significant life cycle fugitive emissions. Recent developments in all-electric heating alternatives or ‘certified’ or ‘renewable’ gas alternatives have made decision making about operating building heating systems more complex given quickly evolving emissions and economic profiles. Here, a novel modeling tool was developed to help provide engineers with full cost-accounting of both the economic and greenhouse gas emissions associated with different heating options. The tool is based on the University of Virginia's model for estimating costs and emissions associated with capital expenditures and it was updated with location-specific fugitive emissions and cost estimates. Users can input various different common options for heating systems to understand how much of an impact each will have on economic factors such as return on investment, estimated lifetime cost as well as full-cost life cycle impacts including carbon dioxide-equivalents avoided per year, and life cycle greenhouse gas emissions. The analysis suggests that in most cases it is economically and environmentally preferable to replace gas infrastructure with a heat pump once fugitive emissions are considered. In support of the University of Virginia's net-zero emissions targets, the tool was used to assess several hypothetical heating upgrade projects on grounds including one for Carr's Hill. The tool contains fugitive emissions data for all the major metropolitan areas in the United States and can be easily adopted for use in other locations to provide first-of-its kind information for building managers.
{"title":"Modeling the Implications of Fugitive Gas Emissions on Building Heat Upgrade Decisions","authors":"Maddie Robinson, Jackson Sompayrac, Nicole Beachy, Hana Sexton, Aidan Jacobs, A. Clarens","doi":"10.1109/sieds55548.2022.9799411","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799411","url":null,"abstract":"The majority of US buildings use natural gas for heating even though it is a potent greenhouse gas that relies on a leaking infrastructure with significant life cycle fugitive emissions. Recent developments in all-electric heating alternatives or ‘certified’ or ‘renewable’ gas alternatives have made decision making about operating building heating systems more complex given quickly evolving emissions and economic profiles. Here, a novel modeling tool was developed to help provide engineers with full cost-accounting of both the economic and greenhouse gas emissions associated with different heating options. The tool is based on the University of Virginia's model for estimating costs and emissions associated with capital expenditures and it was updated with location-specific fugitive emissions and cost estimates. Users can input various different common options for heating systems to understand how much of an impact each will have on economic factors such as return on investment, estimated lifetime cost as well as full-cost life cycle impacts including carbon dioxide-equivalents avoided per year, and life cycle greenhouse gas emissions. The analysis suggests that in most cases it is economically and environmentally preferable to replace gas infrastructure with a heat pump once fugitive emissions are considered. In support of the University of Virginia's net-zero emissions targets, the tool was used to assess several hypothetical heating upgrade projects on grounds including one for Carr's Hill. The tool contains fugitive emissions data for all the major metropolitan areas in the United States and can be easily adopted for use in other locations to provide first-of-its kind information for building managers.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131798891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799404
Claire Dozier, Alexandra S. Schmid, Bryce Huffman, Margaret M Cusack, Sarah Saas, Wei Wu, Aram Bahrini, R. Riggs, Kimberly Dowdell, Karen Measells
Many patient throughput inefficiencies result from poor communication practices, inadequate understanding of optimizing healthcare systems to maximize efficiency, and longterm complications caused by the COVID-19 pandemic. The challenges precipitated by the pandemic, combined with the need to provide safe, high-quality care to patients, have further exacerbated existing patient flow and throughput issues. The overarching goal of this project is to improve the patient experience in primary care clinics and reduce the stress placed on providers, nurses, and staff. The authors implemented a two-phased approach that combined qualitative observations with quantitative data analysis, developed a robust methodology for understanding the University Physicians of Charlottesville (UPC) Clinic's processes, and produced structured insights for stakeholders. We established what components comprised a typical patient's journey through system intake through qualitative clinic observations: pre-registration, check-in, and rooming. In contrast to the qualitative observations, the quantitative analysis encompassed the complete patient experience, outs coping to include appointment durations and check-out. All quantitative analyses relied on data from the University of Virginia (UVA) Health's electronic medical record (EMR) system, Epic. In addition to the qualitative analyses, the authors utilized Cadence reports and appointment scheduling data to understand patient flow through the UPC Clinic. Primarily, the data are utilized to understand the distributions between the different patient flow milestones of registration, clinic check-in, rooming, and check-out and what factors, if any, were statistically significant. This approach enabled us to model the distribution of patient arrival times, wait times between arrival and rooming, and other relevant bottlenecks in the flow process.
{"title":"Optimization of Patient Flow and Process for a Primary Care Clinic During the COVID-19 Pandemic","authors":"Claire Dozier, Alexandra S. Schmid, Bryce Huffman, Margaret M Cusack, Sarah Saas, Wei Wu, Aram Bahrini, R. Riggs, Kimberly Dowdell, Karen Measells","doi":"10.1109/sieds55548.2022.9799404","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799404","url":null,"abstract":"Many patient throughput inefficiencies result from poor communication practices, inadequate understanding of optimizing healthcare systems to maximize efficiency, and longterm complications caused by the COVID-19 pandemic. The challenges precipitated by the pandemic, combined with the need to provide safe, high-quality care to patients, have further exacerbated existing patient flow and throughput issues. The overarching goal of this project is to improve the patient experience in primary care clinics and reduce the stress placed on providers, nurses, and staff. The authors implemented a two-phased approach that combined qualitative observations with quantitative data analysis, developed a robust methodology for understanding the University Physicians of Charlottesville (UPC) Clinic's processes, and produced structured insights for stakeholders. We established what components comprised a typical patient's journey through system intake through qualitative clinic observations: pre-registration, check-in, and rooming. In contrast to the qualitative observations, the quantitative analysis encompassed the complete patient experience, outs coping to include appointment durations and check-out. All quantitative analyses relied on data from the University of Virginia (UVA) Health's electronic medical record (EMR) system, Epic. In addition to the qualitative analyses, the authors utilized Cadence reports and appointment scheduling data to understand patient flow through the UPC Clinic. Primarily, the data are utilized to understand the distributions between the different patient flow milestones of registration, clinic check-in, rooming, and check-out and what factors, if any, were statistically significant. This approach enabled us to model the distribution of patient arrival times, wait times between arrival and rooming, and other relevant bottlenecks in the flow process.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131329268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799311
R. Jones, Shraddha Joshi, Daniel I. Castaneda
In many engineering fields, it is necessary for engineers to imagine a design and then manifest that design into a physical object. Engineering educators typically engage engineering students who have limited practice in this transference skillset, so we chose to design an instructional project involving casting mortar artifacts using 3D printed molds that students had analytically designed. In preparing this instructional project, we encountered difficulties in casting mortar objects using 3D printed molds that had certain geometries, and we wanted to know what factors in mold geometry contributed to artifact damage during demolding. The scope of this paper focuses on a scholarly project led by an undergraduate research student that explored how the design of 3D printed molds for casting mortar artifacts influenced damage caused during demolding. We designed a series of artifact molds with protrusive features that varied in their aspect ratios and their spatial density to explore how these geometric features contributed toward demolding damage. We experimentally measured the extent of damage by calculating the percent of spike height that was lost during the demolding process. We found that protrusive mold features with large aspect ratios influenced the amount of damage done to those features during demolding. We also found how the spatial density of protrusive features was also a significant cause of damage. From analyzing our data, we identified a clear threshold where mold geometry causes excessive damage during the demolding process. We learned from our scholarly project that casting mortar artifacts with protrusive features in future instructional projects should have surface features designed to be less than a 1:1 aspect ratio to minimize damage during demolding. Understanding these limitations on casting mortar artifacts in 3D printed molds will minimize complications in the instructional project that allows engineering students to analytically design and physically cast artifacts without resulting in excessive damage during demolding.
{"title":"Identifying Challenges in Casting Concrete Artifacts Using 3D Printed Molds","authors":"R. Jones, Shraddha Joshi, Daniel I. Castaneda","doi":"10.1109/sieds55548.2022.9799311","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799311","url":null,"abstract":"In many engineering fields, it is necessary for engineers to imagine a design and then manifest that design into a physical object. Engineering educators typically engage engineering students who have limited practice in this transference skillset, so we chose to design an instructional project involving casting mortar artifacts using 3D printed molds that students had analytically designed. In preparing this instructional project, we encountered difficulties in casting mortar objects using 3D printed molds that had certain geometries, and we wanted to know what factors in mold geometry contributed to artifact damage during demolding. The scope of this paper focuses on a scholarly project led by an undergraduate research student that explored how the design of 3D printed molds for casting mortar artifacts influenced damage caused during demolding. We designed a series of artifact molds with protrusive features that varied in their aspect ratios and their spatial density to explore how these geometric features contributed toward demolding damage. We experimentally measured the extent of damage by calculating the percent of spike height that was lost during the demolding process. We found that protrusive mold features with large aspect ratios influenced the amount of damage done to those features during demolding. We also found how the spatial density of protrusive features was also a significant cause of damage. From analyzing our data, we identified a clear threshold where mold geometry causes excessive damage during the demolding process. We learned from our scholarly project that casting mortar artifacts with protrusive features in future instructional projects should have surface features designed to be less than a 1:1 aspect ratio to minimize damage during demolding. Understanding these limitations on casting mortar artifacts in 3D printed molds will minimize complications in the instructional project that allows engineering students to analytically design and physically cast artifacts without resulting in excessive damage during demolding.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"248 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114551053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799399
Ibrahim H. Hamdy, Maxwell J. St. John, Sidney W. Jennings, Tiago R. Magalhaes, James H. Roberts, Thomas L. Polmateer, Mark C. Manasco, Joi Y. Williams, Daniel C. Hendrickson, Timothy L. Eddy, Davis C. Loose, M. Chowdhury, J. Lambert
Maritime container ports are experiencing a variety of challenges, including the pandemic and other stressors, that are altering perspectives on efficiency, risk, and resilience. This study reviews new methods of operations optimization that serve major goals of logistics systems: Increasing energy and time efficiencies and reducing emissions and congestion. Several computational methods will be assessed, including quantum computing, neural networks, and operations heuristics. The methods are compared by potential for increased efficiencies, including the increase in container volumes, reduction of dwell times, reduction of container moves, utilization of demand forecasts, and decreases in emissions. The results suggest opportunities for reinforcement learning to improve the scheduling of container transactions across transportation modes, including maritime, truck, rail, crane, and barge.
{"title":"Quantum Computing and Machine Learning for Efficiency of Maritime Container Port Operations","authors":"Ibrahim H. Hamdy, Maxwell J. St. John, Sidney W. Jennings, Tiago R. Magalhaes, James H. Roberts, Thomas L. Polmateer, Mark C. Manasco, Joi Y. Williams, Daniel C. Hendrickson, Timothy L. Eddy, Davis C. Loose, M. Chowdhury, J. Lambert","doi":"10.1109/sieds55548.2022.9799399","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799399","url":null,"abstract":"Maritime container ports are experiencing a variety of challenges, including the pandemic and other stressors, that are altering perspectives on efficiency, risk, and resilience. This study reviews new methods of operations optimization that serve major goals of logistics systems: Increasing energy and time efficiencies and reducing emissions and congestion. Several computational methods will be assessed, including quantum computing, neural networks, and operations heuristics. The methods are compared by potential for increased efficiencies, including the increase in container volumes, reduction of dwell times, reduction of container moves, utilization of demand forecasts, and decreases in emissions. The results suggest opportunities for reinforcement learning to improve the scheduling of container transactions across transportation modes, including maritime, truck, rail, crane, and barge.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130377801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799312
Libby H. Welborn, Anna K. Himes, Ida E. Greenlee, Nyna J. DeWitt, Ava T. Burgess, Brandon K. Eberl, O. Pierrakos
In the United States, congenital heart defects affect nearly 40,000 births each year and often will require heart valve replacement [1]. Viable prosthetic heart valve options are limited for pediatric patients that need a valve smaller than 16mm in diameter. When commercially available valve sizes are not available, surgeons often handcraft a valve using expanded polytetrafluoroethylene (ePTFE) to fabricate a valve that is small enough to meet the size constraints of young pediatric patients. There is limited published hemodynamic data for ePTFE valves. A comparison between the two ePTFE handmade valves (trileaflet and quadleaflet) demonstrated hemodynamic differences in regurgitation due to leaflet number. The handmade valves both showed increased regurgitation compared to a Carbomedics valve (commercially available design). Regurgitation had varying effects on pressure gradients and cardiac output. The aim of this paper is to: 1) showcase the design process of a quadleaflet ePTFE valved conduit with a diameter of 16mm or less and 2) offer a hemodynamic performance comparison.
{"title":"Design and Preliminary Testing of a Quadleaflet ePTFE Pediatric Prosthetic Heart Valve","authors":"Libby H. Welborn, Anna K. Himes, Ida E. Greenlee, Nyna J. DeWitt, Ava T. Burgess, Brandon K. Eberl, O. Pierrakos","doi":"10.1109/sieds55548.2022.9799312","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799312","url":null,"abstract":"In the United States, congenital heart defects affect nearly 40,000 births each year and often will require heart valve replacement [1]. Viable prosthetic heart valve options are limited for pediatric patients that need a valve smaller than 16mm in diameter. When commercially available valve sizes are not available, surgeons often handcraft a valve using expanded polytetrafluoroethylene (ePTFE) to fabricate a valve that is small enough to meet the size constraints of young pediatric patients. There is limited published hemodynamic data for ePTFE valves. A comparison between the two ePTFE handmade valves (trileaflet and quadleaflet) demonstrated hemodynamic differences in regurgitation due to leaflet number. The handmade valves both showed increased regurgitation compared to a Carbomedics valve (commercially available design). Regurgitation had varying effects on pressure gradients and cardiac output. The aim of this paper is to: 1) showcase the design process of a quadleaflet ePTFE valved conduit with a diameter of 16mm or less and 2) offer a hemodynamic performance comparison.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129256728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：