Document text
Principal Investigator: Timothy William Dunn
Organization: DUKE UNIVERSITY
Fiscal Year: 2024
Award: $584,488
Funding agency: National Institute of Neurological Disorders and Stroke
Scope of Work
Duke will complete all work for the machine learning model building and implementation of the model into the
Duke clinical workflow. For Aim 1 of the project, this work will include data extraction and cleaning, neural network
architecture design, and model optimization and validation. For Aim 2, this work will include establishment of
technical infrastructure for real-time image and access and processing, construction of a front-end dashboard in
close collaboration with frontline clinicians, and deployment and prospective validation of the model. The latter
step will also consist of education and training of hospital users. For Aim 3 of the project, Duke will guide staff at
Jefferson through the model implementation and validation process, with the active integration and training
performed by staff at Jefferson. In Aim 3 Duke will also run the experiments on multi-site model generalization,
using retrospective data at both Duke and Jefferson. Data will be shared between Duke and Jefferson via secure
ethernet transfer between Jefferson’s secure data warehouse and Duke’s Protected Analytics and Computing
Environment. The end goal of the work will be to provide a sophisticated, high-accuracy, and seamlessly
integrated tool for predicting the risk of actionable TBI complications over the course of a TBI patient’s hospital
encounter. This method, which will augment decision-making for treating a complex neurological condition, will
significantly improve overall TBI outcomes, reduce readmission rates, and minimize the extraordinary costs
incurred by inefficient provision of healthcare resources.
Terms: <Accident and Emergency department><Admission><Admission activity><Affect><American><Bleeding><Brain><Brain Nervous System><Brain Trauma><CAT scan><CT X Ray><CT Xray><CT imaging><CT scan><Caring><Categories><Cause of Death><Clinical><Clinical Trials><Collaborations><Complex><Complication><Computed Tomography><Connectionist Models><Country><Data><Data Bases><Data Set><Databases><Decision Making><Diagnosis><ED care><ER care><Early Diagnosis><Education and Training><Emergency Care><Emergency Department><Emergency Department care><Emergency Room care><Emergency health care><Emergency healthcare><Emergency medical care><Emergency room><Encephalon><Environment><Epidemic><Future><Goals><Health Care Systems><Health system><Healthcare><Healthcare Systems><Hemorrhage><Hospitals><Hour><Inflammation><Infrastructure><Injury><Inpatients><Institution><Interpretable ML><Interpretable machine learning><Intervention><Intervention Strategies><Left><MTBI><Medical History><Mental disability><Methods><Modeling><Modernization><Monitor><Neural Network Models><Neural Network Simulation><Neurologic><Neurological><Outcome><Output><Pathway interactions><Patient outcome><Patient risk><Patient-Centered Outcomes><Patient-Focused Outcomes><Patients><Patients with traumatic brain injury><Perceptrons><Performance><Personal Medical History><Personal Medical History Epidemiology><Predicting Risk><Procedures><Process><Prognosis><Prospective cohort><Provider><Research Resources><Resources><Risk><Running><Secure><Sensitivity and Specificity><Site><TBI Patients><TBI therapy><TBI treatment><Technology><Testing><Time><Tomodensitometry><Training><Training and Education><Trauma><Traumatic Brain Injury><Triage><United States><Universities><Update><Validation><Withdrawal><Work><X-Ray CAT Scan><X-Ray Computed Tomography><X-Ray Computerized Tomography><Xray CAT scan><Xray Computed Tomography><Xray computerized tomography><adult youth><blood loss><catscan><clinical care><clinical implementation><clinical risk><cohort><combat><computational infrastructure><computed axial tomography><computer based prediction><computer infrastructure><computer tomography><computerized axial tomography><computerized tomography><cost><dashboard><data base><data infrastructure><data to train><data warehouse><dataset to train><deep learning based model><deep learning based neural network><deep learning model><deep learning neural network><deep neural net><deep neural network><demographics><design><designing><disability><discrete time><early detection><experience><experiment><experimental research><experimental study><experiments><explainable ML><explainable machine learning><forecasting risk><health care><hospital re-admission rates><hospital readmission rate><improved><injuries><interventional strategy><machine learning based model><machine learning model><mild TBI><mild brain trauma><mild traumatic brain injury><model building><nerve cell death><nerve cell loss><network architecture><neural net architecture><neural network architecture><neuron cell death><neuron cell loss><neuron death><neuron loss><neuronal cell death><neuronal cell loss><neuronal death><neuronal loss><neurosurgery><non-contrast CT><noncontrast CT><noncontrast computed tomography><pathway><patient oriented outcomes><physical disability><physically disabled><physically handicapped><predict risk><predict risks><predicted risk><predicted risks><predicting risks><predictive modeling><predictive risk><predictive tools><predicts risk><prognosis model><prognostic model><prospective><re-admission rates><re-hospitalization rate><readmission rates><real-time images><realtime image><rehospitalization rate><risk prediction><risk predictions><tool><training data><traumatic brain damage><traumatic brain injury patients><traumatic brain injury therapy><traumatic brain injury treatment><treatment guidelines><validations><young adult><young adulthood>