Emily Wang, who earned her Ph.D. in statistics (STAT) from Rice University last year, has won the 2022 Savage Award for Best Thesis in Applied Methodology from the International Society for Bayesian Analysis.
The award was presented at the Joint Statistical Meeting held Aug. 5-10 in Toronto, the largest gathering of statisticians in North America. Wang’s thesis is titled “Bayesian State-Space Models with Variable Selection for Neural Count Data.”
“Epilepsy researchers are developing statistical methods for estimating latent seizure risk in patients. In clinical practice, seizure risk is gauged empirically by a clinician, based on daily changes in seizure frequency,” said Wang’s adviser, Marina Vannucci, the Noah Harding Professor of STAT at Rice.
Because of the unpredictability of seizures, changes in frequency may not necessarily indicate changes in risk. Wang’s work with Vannucci emphasizes the importance of logging seizures daily and over the long term. That will help establish individual rhythms for patients who experience seizures in cycles and wish to understand why seizures happen when they do, what may trigger them and how best to treat them.
“The logs of more than 1,000 patients, ages two months to 80 years helped us model the relationship between ‘attractor states,’ internal and/or external events like the start of a new medication or an illness, and the peaks and valleys of seizure activity in individual patients,” said Wang, who is pictured above on right.
“The purpose of the model is to try to guide the patient and the doctor, in particular,” Vannucci said. “We want to help doctors say, ‘OK, this medication is really important for this patient with this type of seizure,’ and control their seizures more effectively.”
Another collaborator in the research is Dr. Sharon Chiang, who earned her Ph.D. in STAT from Rice and her M.D. from Baylor College of Medicine in 2018. She is a clinical fellow in neurology at the University of California at San Francisco’s Weill Institute for Neurosciences.
Wang’s thesis has resulted in papers published in the journals Annals of Applied Statistics, Epilepsia, Brain Stimulation and Proceedings of the National Academy of Sciences. While at Rice, Wang was supported by a fellowship from the Gulf Coast Consortia and a National Library of Medicine fellowship in biomedical informatics.
Since leaving Rice, Wang has worked as a data scientist at CommonSpirit Health in Englewood, Colo. The award is named for the American statistician Leonard “Jimmie” Savage and is the highest recognition for Bayesian work done at the doctoral level.
“We hope this work will encourage other researchers to investigate potential applications of Bayesian or state-space models in epilepsy research. With the advent of big data, resulting in large-scale databases of seizure records, data-driven approaches to uncovering the hidden patterns underlying seizures are becoming more promising,” Wang said.
Pictured at top: Emily Wang, right, with Paul Parker (honorable mention) from the University of Missouri and Maria Masotti (finalist) from the University of Minnesota.