Browsing by Subject "accessible"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Leveraging Machine Learning Tools To Develop Objective, Interpretable, And Accessible Assessments Of Postural Instability In Parkinson'S Disease(2023-04) Herbers, CaraParkinson's disease (PD) is the second most common neurodegenerative disease in the United States, affecting 1 million Americans. PD-related postural instability (PI) is one of the most disabling motor symptoms of PD since it is associated with increased falls and loss of independence. PI has little or no response to current PD treatments, the underlying mechanisms are poorly understood, and the current clinical assessments are subjective and introduce human error. There is a need for improved diagnostic tools of PI for clinicians to better characterize, understand, and treat PD-related PI. Several criteria are necessary to address this clinical need: (1) the clinical rating of PI should be quantified objectively, (2) additional postural tasks should be clinically assessed and quantified, and (3) the assessments of PI should occur more frequently than a biannual clinical assessment. This project sought to develop two novel approaches to address these criteria. First, deep learning markerless pose estimation was leveraged to assess reactive step length in response to shoulder pull and surface translation perturbations for individuals with and without PD. Reactive step length was altered in PD (significantly for treadmill perturbations, and with an insignificant trend for shoulder pull perturbations), and improved by dopamine replacement therapy. Next, insole plantar pressure sensor data from 111 subjects (44 PD, 67 controls) were collected and used to assess PD-related PI during typical daily balance tasks. Machine learning models were developed to accurately identify PD from young controls (area under the curve (AUC) 0.99 +/- 0.00), PD from age-matched controls (AUC 0.99 +/- 0.01), and PD non-fallers from PD fallers (AUC 0.91 +/- 0.08). It was seen that utilizing features from both static and active tasks significantly improved classification performances and that all tasks were useful for separating controls from PD; however, tasks with higher postural threat were preferred for separating PD non-fallers from PD fallers. This work produced numerous clinical and translational implications. Notably, (1) simple and accessible quantitative measures can be used to identify PD and individuals with PD who fall, and (2) machine learning models can be leveraged for implementing, quantifying, and interpreting these measures into something clinically useful.Item The Minnesota Dye Trace Database(http://www.mgwa.org/mgwa-conferences/mgwa-2017-spring-conference/, 2017-04) Wheeler, Betty J; Rutelonis, J. Wes; Barry, John D; Green, Jeffrey A; Alexander Jr., E. CalvinIn the karst regions of Minnesota, groundwater tracing using fluorescent dyes has proven to be an effective method for understanding groundwater flow, travel times and interconnections with surface water (streams, creeks, etc). Dye tracing in Southeast (SE) Minnesota has a long history. The first documented traces were performed by S.P. Kingston, a public safety engineer at the Minnesota Department of Health, in the late 1930s. Kingston used fluorescent dye to discover the source of an outbreak of typhoid fever in Fillmore and Olmsted Counties and published his work in the Journal of the American Water Works Association. Additionally, Ron Spong conducted over 30 traces beginning in the 1970s across several counties in SE Minnesota. Most of the dye tracing in Minnesota since that time has been a collaborative effort between the University of Minnesota and the Minnesota Department of Natural Resources but stakeholders such as towns and cities, soil and water conservation districts, the local caving community and generations of students have often been involved as well. Dye tracing involves using fluorescent dyes to determine groundwater flow direction and velocity by pouring dye into a sinkhole or sinking stream and observing where it emerges (usually at a spring or multiple springs) after flowing through the karst conduit system. Positive sampling results allow scientists to infer approximate groundwater flowpaths, calculate minimum velocities, and begin to delineate springsheds. In general, springsheds are composed of Groundwater Springsheds (GwS), Surface Water Springsheds (SWS) and Regional Groundwater Springsheds (RGS) and understanding their combined extent is important for the protection of trout stream resources and other ecosystems in Minnesota karst areas and elsewhere. Additionally, water protection and management associated with spill response, agriculture, water demands and landscape alteration require effective means for delineating springsheds. Many dye traces and the resulting springshed delineations have been accomplished in SE Minnesota, but the results and reporting have had varying degrees of accessibility. The goal of the current project is to produce a web accessible database containing as many groundwater dye tracing results as possible. This effort involves mining trace reports, data tables, and field notes and organizing their contents using GIS. The DNR Dye Trace Reports webpage currently has a list of links to historic and recent dye trace reports that are catalogued and made publicly available on the University of Minnesota Digital Conservancy. Geospatial data (dye input points, inferred groundwater flowpaths and springshed delineations) are re-evaluated in some cases, quality checked, and then digitized. Eventually this data will be made available via the DNR webpage in the form of an accessible ArcGIS Online map interface where users can query, select and view the data and associated reports with the click of a button. This database is intended to be used in conjunction with the Minnesota Karst Features Database (Gao, Yongli. (2002) “Karst Feature Distribution in Southeastern Minnesota: Extending GIS-Based Database for Spatial Analysis and Resource Management.”. PhD Thesis, Univ. of Minn., Geology & Geophysics Dept., 210 p.) and will likely be incorporated into an enterprise system of spatially related databases built upon the Karst Feature Database and the Minnesota Spring Inventory. The Minnesota Dye Trace Database is an important element to manage and protect groundwater in Minnesota. Revitalizing dye tracing data, making the documentation available, and creating a user friendly interface will add context to the knowledge and expansive inventory of karst in Minnesota and will hopefully allow this significant dataset to live in perpetuity for generations of scientists and policy makers to come.