Dr. Cao (Danica) Xiao
Director of Machine Learning, Analytics Center of Excellence, IQVIA
Cao (Danica) Xiao is the Director of Machine Learning at Analytics Center of Excellence of IQVIA.
Her research focuses on developing machine learning and deep learning models to solve real world healthcare challenges. Particularly, she is interested in deep computational phenotyping, adverse drug reaction signal detection from heterogeneous real world evidence, interpretable health analytics, and translational informatics research (e.g., drug similarity for drug safety and discovery).The results of her research have been published in leading AI conferences including NIPS, ICLR, KDD, AAAI, IJCAI, SDM, ICDM, and top health informatics journals such as Nature Scientific Reports and JAMIA. She also served as the principal investigator for several MIT-IBM joint projects. Prior to IQVIA, she acquired her Ph.D. degree from University of Washington, Seattle in 2016 and was a research staff member in the AI for Healthcare team at IBM Research from 2017 to 2019.
Dr. Tanya Leise
Tanya Leise has been teaching in the Department of Mathematics & Statistics at Amherst College since 2004. Her courses focus primarily on undergraduate applied mathematics, including multivariable calculus, applied linear algebra, differential equations, mathematical modeling, and Fourier and wavelet analysis. Tanya’s research on biological oscillators focuses on circadian rhythms in mammals and is highly interdisciplinary in nature. She works with colleagues in neuroscience and biology to study the physiological mechanisms of the circadian clock at the cellular and tissue levels in a variety of organisms. She utilizes a mix of mathematical modeling and wavelet-based time series analysis to gain insight into the circadian clock.
Talk title: Rhythms of Life: Analyzing the Circadian Clock
Abstract: Most creatures on earth have internal circadian clocks that regulate our daily rhythms of activity and sleep. Like mechanical clocks, these biological clocks keep regular, precise time and can be reset to match external time, for instance, adjusting to changes in time zone. We’ll take a look at analysis of circadian clock oscillations in behavioral and molecular records of animals like mice, fruit flies, and bears, employing a variety of methods ranging from autocorrelation to wavelet transforms. Circadian data is often noisy and with relatively few cycles, so that reliable estimation of period can be quite challenging.