Abstract:
This paper introduces a Lasso Logistic Regression model based on feature-based time series data to assess COVID-19 disease severity and when to administer drugs or escalate intervention procedures. The dynamic feature-based classification model used advanced features from highly enriched and time series vital sign data of hospitalized COVID-19 patients, including oxygen saturation readings, and patient demographic and comorbidity information. Such dynamic combinations provided deep insights into complex COVID-19 clinical decision-making, including prognosis prediction, drug administration timing, admission to intensive care units, and use of intervention procedures like ventilation and intubation. A leading Texas multi-hospital system used 900 hospitalized COVID-19 patients to develop the patient classification model. The dynamic feature-based classification model can improve COVID-19 patient treatment, prioritize medical resources, and reduce casualties by predicting mortality based on time-series physiologic data, demographics, and clinical records. Our model is unique because it uses only the first 24 hours of vital sign data to make clinical interventions early and effectively. This strategy could prioritize resource allocation and drug treatment for future pandemics.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
