BME Master’s Defense Announcement for Madeleine Stanik (N. Kong, advisor)
Everyone is welcome to attend the public presentation starting at 10:00am in DLR 131.
Title: Predicting The Risks of Recurrent Stroke and Post-Infection Seizure in Residents of Skilled Nursing Facilities - A Machine Learning Approach
Date: Wednesday, April 3rd
Time: 10:00am
Location:
DLR 131
Thesis Committee: Nan Kong, Chair; Zachary Hass; Fiona Kolbinger
Abstract:
Recurrent stroke, infection, and seizure are some of the most common complications in stroke survivors. Recurrent stroke leads to death in 38.6% of survivors, and infections are the most common
risk factor for seizures, with stroke survivors that experience an infection being at greater risk of experiencing a seizure. Two predictive models were generated, recurrent stroke and post-infection seizure, to determine stroke survivors at greatest risk
to help providers focus on prevention in higher risk patients. This study used the Long-Term Care Minimum Data Set (MDS) 3.0 and applied data balancing, feature selection, and four modeling methods to predict risk for each of the two complications. This work
focused on the interpretation of the models to identify features that contributed most to the prediction. For recurrent stroke, it was indicated that treatment combinations of therapy, therapeutic diet, and medications (antidepressants, anticoagulants, and
diuretics) contributed the most to reducing recurrent stroke risk when compared to individual treatment features. Meaning that stroke patients who received a pairwise combination of these treatments had a reduced risk of recurrent stroke. For post-infection
seizure, interpretation indicated that therapy, independence, and mood related features contributed the most. Meaning, stroke survivors who received fewer therapy hours, were less independent, and had a worse overall mood were at a greater risk of having a
post-infection seizure. Uncovering which factors contribute the most to recurrent stroke and pot-infection seizure risk may aid healthcare professionals in adjusting treatment and rehabilitation plans to improve resident outcomes.