Browsing by Subject "predictive modeling"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Evaluation of a Parsimonious COVID-19 Outbreak Prediction Model: Heuristic Modeling Approach Using Publicly Available Data Sets
    (JMIR, 2021-07) Gupta, Agrayan K.; Grannis, Shaun J.; Kasthurirathne, Suranga N.; Family Medicine, School of Medicine
    Background: The COVID-19 pandemic has changed public health policies and human and community behaviors through lockdowns and mandates. Governments are rapidly evolving policies to increase hospital capacity and supply personal protective equipment and other equipment to mitigate disease spread in affected regions. Current models that predict COVID-19 case counts and spread are complex by nature and offer limited explainability and generalizability. This has highlighted the need for accurate and robust outbreak prediction models that balance model parsimony and performance. Objective: We sought to leverage readily accessible data sets extracted from multiple states to train and evaluate a parsimonious predictive model capable of identifying county-level risk of COVID-19 outbreaks on a day-to-day basis. Methods: Our modeling approach leveraged the following data inputs: COVID-19 case counts per county per day and county populations. We developed an outbreak gold standard across California, Indiana, and Iowa. The model utilized a per capita running 7-day sum of the case counts per county per day and the mean cumulative case count to develop baseline values. The model was trained with data recorded between March 1 and August 31, 2020, and tested on data recorded between September 1 and October 31, 2020. Results: The model reported sensitivities of 81%, 92%, and 90% for California, Indiana, and Iowa, respectively. The precision in each state was above 85% while specificity and accuracy scores were generally >95%. Conclusions: Our parsimonious model provides a generalizable and simple alternative approach to outbreak prediction. This methodology can be applied to diverse regions to help state officials and hospitals with resource allocation and to guide risk management, community education, and mitigation strategies.
  • Thumbnail Image
    Item
    Optimizing differential identifiability improves connectome predictive modeling of cognitive deficits from functional connectivity in Alzheimer's disease
    (Wiley, 2021-08) Svaldi, Diana O.; Goñi, Joaquín; Abbas, Kausar; Amico, Enrico; Clark, David G.; Muralidharan, Charanya; Dzemidzic, Mario; West, John D.; Risacher, Shannon L.; Saykin, Andrew J.; Apostolova, Liana G.; Medicine, School of Medicine
    Functional connectivity, as estimated using resting state functional MRI, has shown potential in bridging the gap between pathophysiology and cognition. However, clinical use of functional connectivity biomarkers is impeded by unreliable estimates of individual functional connectomes and lack of generalizability of models predicting cognitive outcomes from connectivity. To address these issues, we combine the frameworks of connectome predictive modeling and differential identifiability. Using the combined framework, we show that enhancing the individual fingerprint of resting state functional connectomes leads to robust identification of functional networks associated to cognitive outcomes and also improves prediction of cognitive outcomes from functional connectomes. Using a comprehensive spectrum of cognitive outcomes associated to Alzheimer's disease (AD), we identify and characterize functional networks associated to specific cognitive deficits exhibited in AD. This combined framework is an important step in making individual level predictions of cognition from resting state functional connectomes and in understanding the relationship between cognition and connectivity.
  • Thumbnail Image
    Item
    Using Community Science to Better Understand Lead Exposure Risks
    (AGU, 2022-02) Dietrich, Matthew; Shukle, John T.; Krekeler, Mark P. S.; Wood, Leah R.; Filippelli, Gabriel M.; Earth Sciences, School of Science
    Lead (Pb) is a neurotoxicant that particularly harms young children. Urban environments are often plagued with elevated Pb in soils and dusts, posing a health exposure risk from inhalation and ingestion of these contaminated media. Thus, a better understanding of where to prioritize risk screening and intervention is paramount from a public health perspective. We have synthesized a large national data set of Pb concentrations in household dusts from across the United States (U.S.), part of a community science initiative called “DustSafe.” Using these results, we have developed a straightforward logistic regression model that correctly predicts whether Pb is elevated (>80 ppm) or low (<80 ppm) in household dusts 75% of the time. Additionally, our model estimated 18% false negatives for elevated Pb, displaying that there was a low probability of elevated Pb in homes being misclassified. Our model uses only variables of approximate housing age and whether there is peeling paint in the interior of the home, illustrating how a simple and successful Pb predictive model can be generated if researchers ask the right screening questions. Scanning electron microscopy supports a common presence of Pb paint in several dust samples with elevated bulk Pb concentrations, which explains the predictive power of housing age and peeling paint in the model. This model was also implemented into an interactive mobile app that aims to increase community-wide participation with Pb household screening. The app will hopefully provide greater awareness of Pb risks and a highly efficient way to begin mitigation.